Descriptor: "[ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL]" - Searchworks@Jio Institute Digital Library Search Results

Your search keyword '"[ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL]"' showing total 234 results

Start Over Descriptor "[ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL]"

234 results on '"[ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL]"'

1. Mapping the Bentham Corpus: Concept-based Navigation

Author: Pablo Ruiz Fabo and Thierry Poibeau
Subjects: jeremy bentham, manuscripts, corpus navigation, entity linking, keyphrase extraction, [ info.info-cl ] computer science [cs]/computation and language [cs.cl], [ shs.phil ] humanities and social sciences/philosophy, [ shs.langue ] humanities and social sciences/linguistics, History of scholarship and learning. The humanities, AZ20-999, Bibliography. Library science. Information resources
Abstract: British philosopher and reformer Jeremy Bentham (1748-1832) left over 60,000 folios of unpublished manuscripts. The Bentham Project, at University College London, is creating a TEI version of the manuscripts, via crowdsourced transcription verified by experts. We present here an interface to navigate these largely unedited manuscripts, and the language technologies the corpus was enriched with to facilitate navigation, i.e Entity Linking against the DBpedia knowledge base and keyphrase extraction. The challenges of tagging a historical domain-specific corpus with a contemporary knowledge base are discussed. The concepts extracted were used to create interactive co-occurrence networks, that serve as a map for the corpus and help navigate it, along with a search index. These corpus representations were integrated in a user interface. The interface was evaluated by domain experts with satisfactory results , e.g. they found the distributional semantics methods exploited here applicable in order to assist in retrieving related passages for scholarly editing of the corpus.
Published: 2019
Full Text: View/download PDF

2. A Hackathon for Classical Tibetan

Author: Orna Almogi, Lena Dankin, Nachum Dershowitz, and Lior Wolf
Subjects: tibetan, buddhist studies, hackathon, stemming, segmentation, intertextual alignment, text classification, [ info.info-cl ] computer science [cs]/computation and language [cs.cl], [ shs.langue ] humanities and social sciences/linguistics, [ info.info-cy ] computer science [cs]/computers and society [cs.cy], History of scholarship and learning. The humanities, AZ20-999, Bibliography. Library science. Information resources
Abstract: We describe the course of a hackathon dedicated to the development of linguistic tools for Tibetan Buddhist studies. Over a period of five days, a group of seventeen scholars, scientists, and students developed and compared algorithms for intertextual alignment and text classification, along with some basic language tools, including a stemmer and word segmenter.
Published: 2019
Full Text: View/download PDF

3. A rule-based methodology to extract building model views

Author: Christophe Nicolle, Tarcisio Mendes de Farias, Ana Roxin, CheckSem Research Group, Laboratoire Electronique, Informatique et Image ( Le2i ), Université de Bourgogne ( UB ) -Centre National de la Recherche Scientifique ( CNRS ) -AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Université de Bourgogne ( UB ) -Centre National de la Recherche Scientifique ( CNRS ) -AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement, Checksem, Laboratoire Electronique, Informatique et Image [UMR6306] (Le2i), Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Arts et Métiers (ENSAM), Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Arts et Métiers (ENSAM), HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement, Université de Bourgogne (UB)-École Nationale Supérieure d'Arts et Métiers (ENSAM), HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique (CNRS)-Université de Bourgogne (UB)-École Nationale Supérieure d'Arts et Métiers (ENSAM), and HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique (CNRS)
Subjects: Computer science, [INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS], 0211 other engineering and technologies, Building model, 02 engineering and technology, Ontology (information science), [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], 021105 building & construction, Industry Foundation Classes, 0202 electrical engineering, electronic engineering, information engineering, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], RDF, Semantic Web, ComputingMilieux_MISCELLANEOUS, [ INFO.INFO-DS ] Computer Science [cs]/Data Structures and Algorithms [cs.DS], Civil and Structural Engineering, Information retrieval, Syntax (programming languages), Semantic Web Rule Language, [INFO.INFO-LO]Computer Science [cs]/Logic in Computer Science [cs.LO], Rule-based system, Building and Construction, computer.file_format, Control and Systems Engineering, [ INFO.INFO-LO ] Computer Science [cs]/Logic in Computer Science [cs.LO], 020201 artificial intelligence & image processing, computer
Abstract: In this paper, we present a novel approach called IfcView that relies on Semantic Web technologies for creating building views. To do so, we consider an ifcOWL ontology proposed by buildingSMART. The ifcOWL is an Industry Foundation Classes (IFC) based ontology. By combining the ifcOWL ontology with logical rules (expressed in Semantic Web Rule Language, SWRL), we demonstrate through several case studies that our approach can perform a more intuitive and flexible extraction of building views when compared to the Model View Definition (MVD) approach. This is because our rule-based approach dynamically creates sub-graphs (i.e. views) by specifying the IFC elements to extract as Globally Unique Identifiers (GUID), relationships or entities. Another benefit of our approach is the fact that it simplifies the maintenance and definition of building views. Once our rule-based system extracts such a building view (i.e. sub-graph), this view can be exported by using STEP (STandard for the Exchange of Product) or Turtle (a Resource Description Framework (RDF) syntax) formats.
Published: 2018
Full Text: View/download PDF

4. Computational methods for descriptive and theoretical morphology: a brief introduction

Author: Olivier Bonami, Benoît Sagot, Laboratoire de Linguistique Formelle (LLF UMR7110), Université Paris Diderot - Paris 7 (UPD7)-Centre National de la Recherche Scientifique (CNRS), Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), ANR-11-IDEX-0005,EFL,Empirical Foundations of Linguistics : data, methods, models(2011), ANR-11-IDEX-0005,USPC,Université Sorbonne Paris Cité(2011), Laboratoire de Linguistique Formelle ( LLF ), Université Paris Diderot - Paris 7 ( UPD7 ) -Centre National de la Recherche Scientifique ( CNRS ), Automatic Language Modelling and ANAlysis & Computational Humanities ( ALMAnaCH ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), ANR-11-IDEX-0005-02/10-LABX-0083,EFL,Empirical Foundations of Linguistics : data, methods, models ( 2011 ), Centre National de la Recherche Scientifique (CNRS)-Université Paris Diderot - Paris 7 (UPD7), and ANR-11-IDEX-0005-02/10-LABX-0083,EFL,Empirical Foundations of Linguistics : data, methods, models(2011)
Subjects: Computer science, 02 engineering and technology, Sign language, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Language and Linguistics, Linguistics, Theoretical morphology, 030507 speech-language pathology & audiology, 03 medical and health sciences, [ SHS.LANGUE ] Humanities and Social Sciences/Linguistics, 0202 electrical engineering, electronic engineering, information engineering, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], 020201 artificial intelligence & image processing, [SHS.LANGUE]Humanities and Social Sciences/Linguistics, 0305 other medical science, Comparative linguistics, ComputingMilieux_MISCELLANEOUS
Abstract: International audience
Published: 2017
Full Text: View/download PDF

5. Représentation de l’information sémantique lexicale : le modèle wordnet et son application au français

Author: Benoît Sagot, Automatic Language Modelling and ANAlysis & Computational Humanities ( ALMAnaCH ), Inria de Paris, Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), and Sagot, Benoît
Subjects: WOLF, Linguistics and Language, Wordnet, Philosophy, 05 social sciences, WordNet, 050301 education, 02 engineering and technology, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Language and Linguistics, [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Wordnet development, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], 0503 education, Humanities, Développement de wordnets
Abstract: International audience; Le modèle wordnet est le plus répandu des modèles de représentation de la sémantique lexicale reposant sur un inventaire de sens a priori. A la suite du Princeton WordNet de l’anglais, des ressources de type wordnet ont été développées pour plusieurs dizaines de langues, dont le français, le plus souvent au moyen de techniques automatiques ou semi-automatiques. Dans cet article, nous revenons tout d’abord sur les caractéristiques et les limites du modèle wordnet. Nous dressons ensuite un panorama des méthodes utilisées pour le développement de wordnets, avant d’illustrer nos propres travaux dans ce domaine par le développement du WOLF, le WOrdnet Libre du Français.
Published: 2017
Full Text: View/download PDF

6. Representation and Parsing of Multiword Expressions: Current trends

Author: Parmentier, Yannick, Waszczuk, Jakub, Laboratoire d'Informatique Fondamentale d'Orléans (LIFO), Université d'Orléans (UO)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA), Bases de données et traitement des langues naturelles (BDTLN), Laboratoire d'Informatique Fondamentale et Appliquée de Tours (LIFAT), Université de Tours (UT)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université de Tours (UT)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS), Yannick Parmentier, Jakub Waszczuk, ANR-14-CERA-0001,PARSEME-FR,Analyse syntaxique et expressions polylexicales pour le fran?ais(2014), Laboratoire d'Informatique Fondamentale d'Orléans ( LIFO ), Université d'Orléans ( UO ) -Institut National des Sciences Appliquées - Centre Val de Loire ( INSA CVL ), Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ), Bases de données et traitement des langues naturelles ( BDTLN ), Laboratoire d'Informatique de l'Université de Tours ( LI ), Université de Tours-Polytech'Tours-Université de Tours-Polytech'Tours, Centre National de la Recherche Scientifique (CNRS)-Université de Tours-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université de Tours-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL)
Subjects: treebank, [ SHS.LANGUE ] Humanities and Social Sciences/Linguistics, lexicon, grammar, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], parsing, multi-word expressions, [SHS.LANGUE]Humanities and Social Sciences/Linguistics, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: Deep parsing is the fundamental process aiming at the representation of the syntactic structure of phrases and sentences. In the traditional methodology this process is based on lexicons and grammars representing roughly properties of words and interactions of words and structures in sentences. Several linguistic frameworks, such as Head-driven Phrase Structure Grammar (HPSG), Lexical Functional Grammar (LFG), Tree Adjoining Grammar (TAG), Combinatory Categorial Grammar (CCG), etc., offer different structures and combining operations for building grammar rules. These already contain mechanisms for expressing properties of Multiword Expressions (MWE), which, however, need improvement in how they account for idiosyncrasies of MWEs on the one hand and their similarities to regular structures on the other hand. This collaborative book constitutes a survey on various attempts at representing and parsing MWEs in the context of linguistic theories and applications.
Published: 2019

7. A Hackathon for Classical Tibetan

Author: Lena Dankin, Nachum Dershowitz, Orna Almogi, Lior Wolf, Universität Hamburg (UHH), School of Computer Science (TAU-CS), and Tel Aviv University [Tel Aviv]
Subjects: FOS: Computer and information sciences, Buddhist studies, text classification, Computer science, Tibetan Buddhist, intertextual alignment, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], [shs.langue] humanities and social sciences/linguistics, stemming, Computer Science - Computers and Society, [INFO.INFO-CY]Computer Science [cs]/Computers and Society [cs.CY], Computers and Society (cs.CY), lcsh:AZ20-999, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [SHS.LANGUE]Humanities and Social Sciences/Linguistics, [info.info-cl] computer science [cs]/computation and language [cs.cl], Computer Science - Computation and Language, segmentation, Basic language, lcsh:History of scholarship and learning. The humanities, Linguistics, [info.info-cy] computer science [cs]/computers and society [cs.cy], lcsh:Z, lcsh:Bibliography. Library science. Information resources, [ INFO.INFO-CY ] Computer Science [cs]/Computers and Society [cs.CY], hackathon, [ SHS.LANGUE ] Humanities and Social Sciences/Linguistics, Computation and Language (cs.CL), Period (music), Tibetan
Abstract: We describe the course of a hackathon dedicated to the development of linguistic tools for Tibetan Buddhist studies. Over a period of five days, a group of seventeen scholars, scientists, and students developed and compared algorithms for intertextual alignment and text classification, along with some basic language tools, including a stemmer and word segmenter.
Published: 2019

8. Distant Speech Processing for Smart Home Comparison of ASR approaches in distributed microphone network for voice command

Author: Benjamin Lecouteux, François Portet, Michel Vacher, Laboratoire d'Informatique de Grenoble (LIG ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole (GETALP ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Centre National de la Recherche Scientifique (CNRS), Institut National Polytechnique de Grenoble (INPG), ANR-09-VERS-0011,SWEET-HOME,Système Domotique d'Assistance au Domicile(2009), Laboratoire d'Informatique de Grenoble ( LIG ), Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ), Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole ( GETALP ), Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ) -Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ), Université Grenoble Alpes ( UGA ), Centre National de la Recherche Scientifique ( CNRS ), and Institut National Polytechnique de Grenoble ( INPG )
Subjects: Linguistics and Language, Subspace Gaussian Mixture Model, Computer science, Microphone, Feature vector, Speech recognition, Word error rate, 02 engineering and technology, Speech processing, Language and Linguistics, FMLLR, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Human-Computer Interaction, Background noise, 030507 speech-language pathology & audiology, 03 medical and health sciences, Robustness (computer science), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Computer Vision and Pattern Recognition, 0305 other medical science, Software
Abstract: International audience; Voice command in multi-room smart homes for assisting people in loss of autonomy in their daily activities faces several challenges, one of them being the distant condition which impacts ASR performance. This paper presents an overview of multiple techniques for fusion of multi-source audio (pre, middle, post fusion) for automatic speech recognition for in-home voice command. The robustness of the models of speech is obtained by adaptation to the environment and to the task. Experiments are based on several publicly available realistic datasets with participants enacting activities of daily life. The corpora were recorded in natural condition, meaning background noise is sporadic, so there is no extensive background noise in the data. The smart home is equipped with one or two microphones in each room, the distance between them being larger than 1 meter. An evaluation of the most suited techniques improves voice command recognition at the decoding level, by using multiple sources and model adaptation. Although Word Error Rate (WER) is between 26% and 40%, Domotic Error Rate (identical to the WER, but at the level of the voice command) is less than 5.8% for deep neural network models , the method using Feature space Maximum Likelihood Linear Regression (fMLLR) with speaker adaptation training and Subspace Gaussian Mixture Model (SGMM) exhibits comparable results.
Published: 2018
Full Text: View/download PDF

9. Text Deconvolution Saliency (TDS) : a deep tool box for linguistic analysis

Author: Laurent Vanni, Mélanie Ducoffe, Damon Mayaffre, Frederic Precioso, Dominique Longrée, Veeresh Elango, Nazly Santos Buitrago, Juan Gonzales Huesca, Luis Galdo, Carlos Aguilar, BCL, équipe Logométrie : corpus, traitements, modèles, Bases, Corpus, Langage (UMR 7320 - UCA / CNRS) (BCL), Université Côte d'Azur (UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Université Côte d'Azur (UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Projet MinD, Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S - SPARKS), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Laboratoire d'Analyse Statistique des Langues Anciennes (LASLA), Université de Liège, BCL, équipe Langage et Cognition, BCL, équipe Logométrie et corpus politiques, médiatiques et littéraires, Bases, Corpus, Langage (UMR 7320 - UNS / CNRS) ( BCL ), Université Nice Sophia Antipolis ( UNS ), Université Côte d'Azur ( UCA ) -Université Côte d'Azur ( UCA ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Nice Sophia Antipolis ( UNS ), Université Côte d'Azur ( UCA ) -Université Côte d'Azur ( UCA ) -Centre National de la Recherche Scientifique ( CNRS ), Scalable and Pervasive softwARe and Knowledge Systems ( SPARKS ), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis ( I3S ), Université Côte d'Azur ( UCA ) -Université Côte d'Azur ( UCA ) -Centre National de la Recherche Scientifique ( CNRS ) -Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis ( I3S ), and Laboratoire d'Analyse Statistique des Langues Anciennes ( LASLA )
Subjects: [SHS.STAT]Humanities and Social Sciences/Methods and statistics, [ SHS.LANGUE ] Humanities and Social Sciences/Linguistics, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, ComputingMethodologies_DOCUMENTANDTEXTPROCESSING, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [SHS.LANGUE]Humanities and Social Sciences/Linguistics, [ INFO.INFO-AI ] Computer Science [cs]/Artificial Intelligence [cs.AI], [ SHS.STAT ] Humanities and Social Sciences/Methods and statistics, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract: International audience; In this paper, we propose a new strategy , called Text Deconvolution Saliency (TDS), to visualize linguistic information detected by a CNN for text classification. We extend Deconvolution Networks to text in order to present a new perspective on text analysis to the linguistic community. We empirically demonstrated the efficiency of our Text Decon-volution Saliency on corpora from three different languages: English, French, and Latin. For every tested dataset, our Text Deconvolution Saliency automatically encodes complex linguistic patterns based on co-occurrences and possibly on grammatical and syntax analysis.
Published: 2018

10. Fine-grained discourse structures in continuation semantics

Author: Timothée Bernard, Laboratoire de Linguistique Formelle (LLF UMR7110), Université Paris Diderot - Paris 7 (UPD7)-Centre National de la Recherche Scientifique (CNRS), Semantic Analysis of Natural Language (SEMAGRAMME), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS)-Université Paris Diderot - Paris 7 (UPD7), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL), Laboratoire de Linguistique Formelle ( LLF ), Université Paris Diderot - Paris 7 ( UPD7 ) -Centre National de la Recherche Scientifique ( CNRS ), Semantic Analysis of Natural Language ( SEMAGRAMME ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Department of Natural Language Processing & Knowledge Discovery ( LORIA - NLPKD ), Laboratoire Lorrain de Recherche en Informatique et ses Applications ( LORIA ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Université de Lorraine ( UL ) -Centre National de la Recherche Scientifique ( CNRS ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Université de Lorraine ( UL ) -Centre National de la Recherche Scientifique ( CNRS ) -Laboratoire Lorrain de Recherche en Informatique et ses Applications ( LORIA ), and Institut National de Recherche en Informatique et en Automatique ( Inria ) -Université de Lorraine ( UL ) -Centre National de la Recherche Scientifique ( CNRS ) -Université de Lorraine ( UL ) -Centre National de la Recherche Scientifique ( CNRS )
Subjects: 060201 languages & linguistics, [ INFO.INFO-TT ] Computer Science [cs]/Document and Text Processing, Computer science, Semantics (computer science), Computation, Event (relativity), 06 humanities and the arts, 16. Peace & justice, Discourse connectives, Linguistics, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, Continuation, 0602 languages and literature, [ SHS.LANGUE ] Humanities and Social Sciences/Linguistics, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [SHS.LANGUE]Humanities and Social Sciences/Linguistics
Abstract: International audience; In this work, we are interested in the computation of logical representations of discourse. We argue that all discourse connectives are anaphors obeying different sets of constraints and show how this view allows one to account for the semantically parenthetical use of attitude verbs and verbs of report (e.g., think, say) and for sequences of conjunctions (A CONJ 1 B CONJ 2 C). We implement this proposal in event semantics using de Groote (2006)’s dynamic framework.
Published: 2018

11. Semantic Polyhedral Model for Arrays and Lists

Author: Gonnord , Laure, Iannetta , Paul, Morel , Lionel, Laboratoire de l'Informatique du Parallélisme (LIP), École normale supérieure - Lyon (ENS Lyon)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS), CASH - Compilation and Analysis, Software and Hardware (CASH), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire de l'Informatique du Parallélisme (LIP), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Lyon (ENS Lyon)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Centre National de la Recherche Scientifique (CNRS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon, École normale supérieure - Lyon (ENS Lyon), Laboratoire d'Intégration des Systèmes et des Technologies (LIST), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Inria Grenoble Rhône-Alpes, UCBL, LIP - ENS Lyon, CEA List, Laboratoire de l'Informatique du Parallélisme ( LIP ), École normale supérieure - Lyon ( ENS Lyon ) -Université Claude Bernard Lyon 1 ( UCBL ), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique ( Inria ) -Centre National de la Recherche Scientifique ( CNRS ), CASH - Compilation and Analysis, Software and Hardware ( CASH ), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique ( Inria ) -Centre National de la Recherche Scientifique ( CNRS ) -École normale supérieure - Lyon ( ENS Lyon ) -Université Claude Bernard Lyon 1 ( UCBL ), Université Claude Bernard Lyon 1 ( UCBL ), Ecole Normale Supérieure de Lyon ( ENS de Lyon ), Software and Cognitive radio for telecommunications ( SOCRATE ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -CITI Centre of Innovation in Telecommunications and Integration of services ( CITI ), Institut National des Sciences Appliquées de Lyon ( INSA Lyon ), Université de Lyon-Institut National des Sciences Appliquées ( INSA ) -Université de Lyon-Institut National des Sciences Appliquées ( INSA ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National des Sciences Appliquées de Lyon ( INSA Lyon ), Université de Lyon-Institut National des Sciences Appliquées ( INSA ) -Université de Lyon-Institut National des Sciences Appliquées ( INSA ), Centre d'énergie atomique ( CEA LIST ), and CEA/ DRT/LIST
Subjects: High-Performance Computing, Calcul Haute Performances, Modèle polyédrique, Dependencies, [INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS], Polyhedral Model, Sémantique, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Dépendances, Compilation, [ INFO.INFO-DS ] Computer Science [cs]/Data Structures and Algorithms [cs.DS], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Semantics
Abstract: The polyhedral model is a powerful reasonning framework that permits to optimize intensive computation kernels (piece of mperative code). However in this report we propose to define a “Semantic Polyhedral Model”, a formalisation of the main concepts on which the polyhedral model is built, from the notion of operation to data dependencies. This formulation, which is no longer based on syntactic computations but rather on semantic definitions, enables us to characterize the domain on which the polyhedral domain optimisations will apply. We also propose some extensions on programs with lists and memory sharing.; Le modèle polyédrique est un modèle puissant qui permet d’optimiser des noyau de calculs intensifs (des morceaux de code impératif). Dans ce rapport on se propose de définir un « Modèle Polyédrique Sémantique » qui se veut une formalisation des concepts présent dans le modèle original en repartant de la notion d’opération jusqu’au concept de dépendance en données.Cette reformulation qui repose non plus sur des concepts syntaxiques mais sémantiques permet alors de caractériser le spectre d’application du modèle polyédrique. Nous proposons aussi des extensions pour des programmes utilisant des listes et qui font du partage mémoire.
Published: 2018

12. On-Chip Implementation of Pipeline Digit-Slicing Multiplier-Less Butterfly for Fast Fourier Transform Architecture

Author: Shabiul Islam, Masuri Othman, Rozita Teymourzadeh, Yazan Samir Algnabi, Mok Vee Hong, University of Calgary, and Teymourzadeh, Rozita
Subjects: Signal Processing (eess.SP), Fast Fourier Transform (FFT), [INFO.INFO-AR] Computer Science [cs]/Hardware Architecture [cs.AR], Environmental Engineering, [ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing, General Computer Science, Computer science, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, General Chemical Engineering, Pipeline (computing), Clock rate, Fast Fourier transform, Energy Engineering and Power Technology, [INFO.INFO-DS] Computer Science [cs]/Data Structures and Algorithms [cs.DS], Gate count, FOS: Electrical engineering, electronic engineering, information engineering, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [ INFO.INFO-ES ] Computer Science [cs]/Embedded Systems, Verilog HDL, Hardware_ARITHMETICANDLOGICSTRUCTURES, Electrical Engineering and Systems Science - Signal Processing, Field-programmable gate array, Xilinx, [ INFO.INFO-DS ] Computer Science [cs]/Data Structures and Algorithms [cs.DS], Virtex, Decimation, business.industry, General Engineering, Geotechnical Engineering and Engineering Geology, [INFO.INFO-ES] Computer Science [cs]/Embedded Systems, Pipelined digit-slicing multiplier-less, [ INFO.INFO-CC ] Computer Science [cs]/Computational Complexity [cs.CC], [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], Multiplier (economics), [INFO.INFO-CC] Computer Science [cs]/Computational Complexity [cs.CC], [ INFO.INFO-AR ] Computer Science [cs]/Hardware Architecture [cs.AR], business, Computer hardware
Abstract: The need for wireless communication has driven the communication systems to high performance. However, the main bottleneck that affects the communication capability is the Fast Fourier Transform (FFT), which is the core of most modulators. This study presents an on-chip implementation of pipeline digit-slicing multiplier-less butterfly for FFT structure. The approach is taken, in order to reduce computation complexity in the butterfly, digit-slicing multiplier-less single constant technique was utilized in the critical path of Radix-2 Decimation In Time (DIT) FFT structure. The proposed design focused on the trade-off between the speed and active silicon area for the chip implementation. The new architecture was investigated and simulated with MATLAB software. The Verilog HDL code in Xilinx ISE environment was derived to describe the FFT Butterfly functionality and was downloaded to Virtex II FPGA board. Consequently, the Virtex-II FG456 Proto board was used to implement and test the design on the real hardware. As a result, from the findings, the synthesis report indicates the maximum clock frequency of 549.75 MHz with the total equivalent gate count of 31,159 is a marked and significant improvement over Radix 2 FFT butterfly. In comparison with the conventional butterfly architecture, the design that can only run at a maximum clock frequency of 198.987 MHz and the conventional multiplier can only run at a maximum clock frequency of 220.160 MHz, the proposed system exhibits better results. The resulting maximum clock frequency increases by about 276.28% for the FFT butterfly and about 277.06% for the multiplier. It can be concluded that on-chip implementation of pipeline digit-slicing multiplier-less butterfly for FFT structure is an enabler in solving problems that affect communications capability in FFT and possesses huge potentials for future related works and research areas., arXiv admin note: substantial text overlap with arXiv:1806.04570
Published: 2018

13. A protoype-based approach to object reclassification

Author: Ciaffaglione , Alberto, Gianantonio , Pietro, Honsell , Furio, Liquori , Luigi, Dipartimento di Matematica e Informatica - Universita Udine ( DIMI ), Università degli Studi di Udine - University of Udine [Italie], Logical Networks: Self-organizing Overlay Networks and Programmable Overlay Computing Systems ( LOGNET ), Inria Sophia Antipolis - Méditerranée ( CRISAM ), and Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria )
Subjects: object reclassification, TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES, TheoryofComputation_LOGICSANDMEANINGSOFPROGRAMS, static typing, Prototype-based calculi, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [ INFO.INFO-LO ] Computer Science [cs]/Logic in Computer Science [cs.LO]
Abstract: We investigate, in the context of functional prototype-based languages , a calculus of objects which might extend themselves upon receiving a message, a possibility referred to by Cardelli as a self-inflicted operation. We present a sound type system for this calculus which guarantees that evaluating a well-typed expression will never yield a message-not-found runtime error. The resulting calculus is an attempt towards the definition of a language combining the safety advantage of static type check with the flexibility normally found in dynamically typed languages.
Published: 2018

14. Evaluating Discourse Phenomena in Neural Machine Translation

Author: Rico Sennrich, Alexandra Birch, Barry Haddow, Rachel Bawden, University of Zurich, Bawden, Rachel, Université Paris-Sud - Paris 11 ( UP11 ), Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur ( LIMSI ), Université Paris-Sud - Paris 11 ( UP11 ) -Centre National de la Recherche Scientifique ( CNRS ), University of Edinburgh, Institute of Computational Linguistics, University of Zurich, Université Paris-Sud - Paris 11 (UP11), Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI), Université Paris Saclay (COmUE)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université - UFR d'Ingénierie (UFR 919), and Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Université Paris-Sud - Paris 11 (UP11)
Subjects: FOS: Computer and information sciences, Machine translation, Computer science, 410 Linguistics, 02 engineering and technology, 000 Computer science, knowledge & systems, computer.software_genre, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], BLEU, Coreference, Linguistic context, Computer Science - Computation and Language, business.industry, Cohesion (linguistics), [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], 10105 Institute of Computational Linguistics, 020201 artificial intelligence & image processing, Artificial intelligence, business, Computation and Language (cs.CL), computer, Natural language processing, Sentence
Abstract: For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally evaluated with standard automatic metrics, poorly adapted to evaluating discourse phenomena. In this article, we present hand-crafted, discourse test sets, designed to test the models' ability to exploit previous source and target sentences. We investigate the performance of recently proposed multi-encoder NMT models trained on subtitles for English to French. We also explore a novel way of exploiting context from the previous sentence. Despite gains using BLEU, multi-encoder models give limited improvement in the handling of discourse phenomena: 50% accuracy on our coreference test set and 53.5% for coherence/cohesion (compared to a non-contextual baseline of 50%). A simple strategy of decoding the concatenation of the previous and current sentence leads to good performance, and our novel strategy of multi-encoding and decoding of two sentences leads to the best performance (72.5% for coreference and 57% for coherence/cohesion), highlighting the importance of target-side context., Final version of paper to appear in Proceedings of NAACL 2018
Published: 2018
Full Text: View/download PDF

15. Automatically Selecting the Best Dependency Annotation Design with Dynamic Oracles

Author: Guillaume Wisniewski, François Yvon, Ophélie Lacroix, Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur ( LIMSI ), Université Paris-Sud - Paris 11 ( UP11 ) -Centre National de la Recherche Scientifique ( CNRS ), Association for Computational Linguistics, Traitement du Langage Parlé (TLP), Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI), Université Paris Saclay (COmUE)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université - UFR d'Ingénierie (UFR 919), Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Université Paris-Sud - Paris 11 (UP11)-Université Paris Saclay (COmUE)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université - UFR d'Ingénierie (UFR 919), Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Université Paris-Sud - Paris 11 (UP11), University of Copenhagen = Københavns Universitet (KU), and ANR-16-CE33-0021,PARSITI,Analyser l'impossible, Traduire l'improbable(2016)
Subjects: Dependency (UML), [ INFO ] Computer Science [cs], Computer science, 02 engineering and technology, computer.software_genre, Oracle, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Set (abstract data type), 03 medical and health sciences, Annotation, 0302 clinical medicine, Dependency grammar, 0202 electrical engineering, electronic engineering, information engineering, [INFO]Computer Science [cs], [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Parsing, business.industry, Syntax, dependency parsing, TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES, 030221 ophthalmology & optometry, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, Natural language processing, Sentence
Abstract: This work introduces a new strategy to compare the numerous conventions that have been proposed over the years for expressing dependency structures and discover the one for which a parser will achieve the highest parsing performance. Instead of associating each sentence in the training set with a single gold reference, we propose to consider a set of references encoding alternative syntactic representations. Training a parser with a dynamic oracle will then automatically select among all alternatives the reference that will be predicted with the highest accuracy. Experiments on the UD corpora show the validity of this approach.
Published: 2018
Full Text: View/download PDF

16. Towards a Variability Measure for Multiword Expressions

Author: Jean-Yves Antoine, Carlos Ramisch, Caroline Pasquer, Agata Savary, Bases de données et traitement des langues naturelles ( BDTLN ), Laboratoire d'Informatique de l'Université de Tours ( LI ), Université de Tours-Polytech'Tours-Université de Tours-Polytech'Tours, Laboratoire d'informatique Fondamentale de Marseille ( LIF ), Aix Marseille Université ( AMU ) -Ecole Centrale de Marseille ( ECM ) -Centre National de la Recherche Scientifique ( CNRS ), Pasquer, Caroline, Analyse syntaxique et expressions polylexicales pour le fran?ais - - PARSEME-FR2014 - ANR-14-CERA-0001 - Appel à projets générique - VALID, Bases de données et traitement des langues naturelles (BDTLN), Laboratoire d'Informatique Fondamentale et Appliquée de Tours (LIFAT), Université de Tours (UT)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université de Tours (UT)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS), Traitement Automatique du Langage Ecrit et Parlé (TALEP), Laboratoire d'Informatique et Systèmes (LIS), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), ANR-14-CERA-0001,PARSEME-FR,Analyse syntaxique et expressions polylexicales pour le fran?ais(2014), Centre National de la Recherche Scientifique (CNRS)-Université de Tours-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université de Tours-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA), and Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)
Subjects: Computer science, business.industry, Property (programming), Scale (chemistry), Theoretical models, 02 engineering and technology, computer.software_genre, Syntax, Measure (mathematics), [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Identification (information), [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Benchmark (computing), 020201 artificial intelligence & image processing, Relevance (information retrieval), [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Artificial intelligence, business, computer, Natural language processing
Abstract: International audience; One of the outstanding properties of multi-word expressions (MWEs), especially verbal ones (VMWEs), important both in theoretical models and applications, is their idiosyncratic variability. Some MWEs are always continuous , while some others admit certain types of insertions. Components of some MWEs are rarely or never modified, while some others admit either specific or unrestricted modification. This unpredictable variability profile of MWEs hinders modeling and processing them as " words-with-spaces " on the one hand, and as regular syntactic structures on the other hand. Since variability of MWEs is a matter of scale rather than a binary property, we propose a 2-dimensional language-independent measure of variability dedicated to verbal MWEs based on syntactic and discontinuity-related clues. We assess its relevance with respect to a linguistic benchmark and its utility for the tasks of VMWE classification and variant identification on a French corpus.
Published: 2018

17. Automatic quality estimation for speech translation using joint ASR and MT features

Author: Laurent Besacier, Benjamin Lecouteux, Ngoc-Tien Le, Laboratoire d'Informatique de Grenoble ( LIG ), Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ), Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole ( GETALP ), Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ) -Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ), Université Grenoble Alpes ( UGA ), Institut Universitaire de France ( IUF ), Ministère de l'Éducation nationale, de l’Enseignement supérieur et de la Recherche ( M.E.N.E.S.R. ), Laboratoire d'Informatique de Grenoble (LIG ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole (GETALP ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Institut Universitaire de France (IUF), and Ministère de l'Education nationale, de l’Enseignement supérieur et de la Recherche (M.E.N.E.S.R.)
Subjects: Linguistics and Language, Computer science, Speech recognition, Feature selection, 02 engineering and technology, Translation (geometry), Language and Linguistics, Quality estimation, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Task (project management), Artificial Intelligence, Speech translation, 0202 electrical engineering, electronic engineering, information engineering, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Feature Selection, Spoken, ComputingMilieux_MISCELLANEOUS, 060201 languages & linguistics, Joint Features, Word confidence estimation (WCE), Language Translation (SLT), 06 humanities and the arts, 0602 languages and literature, 020201 artificial intelligence & image processing, Transcription (software), Computational linguistics, Joint (audio engineering), Software, Word (computer architecture)
Abstract: This paper addresses the automatic quality estimation of spoken language translation (SLT). This relatively new task is defined and formalized as a sequence-labeling problem where each word in the SLT hypothesis is tagged as good or bad according to a large feature set. We propose several word confidence estimators (WCE) based on our automatic evaluation of transcription (ASR) quality, translation (MT) quality, or both (combined ASR + MT). This research work is possible because we built a specific corpus, which contains 6.7k utterances comprising the quintuplet: ASR output, verbatim transcript, text translation, speech translation, and post-edition of the translation. The conclusion of our multiple experiments using joint ASR and MT features for WCE is that MT features remain the most influential while ASR features can bring interesting complementary information. In addition, the last part of the paper proposes to disentangle ASR errors and MT errors where each word in the SLT hypothesis is tagged as good, $$asr\_error$$ or $$mt\_error$$ . Robust quality estimators for SLT can be used for re-scoring speech translation graphs or for providing feedback to the user in interactive speech translation or computer-assisted speech-to-text scenarios.
Published: 2018

18. Conception d’une application web pour la supervision centralisée des onduleurs de secours

Author: RAKOTOZANDRY , Tafitasoaniaina Christiany, Service Instrumentation Conception Caractérisation ( LAAS-I2C ), Laboratoire d'analyse et d'architecture des systèmes [Toulouse] ( LAAS ), Institut National Polytechnique [Toulouse] ( INP ) -Institut National des Sciences Appliquées - Toulouse ( INSA Toulouse ), Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ) -Université Paul Sabatier - Toulouse 3 ( UPS ) -Centre National de la Recherche Scientifique ( CNRS ) -Institut National Polytechnique [Toulouse] ( INP ) -Institut National des Sciences Appliquées - Toulouse ( INSA Toulouse ), Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ) -Université Paul Sabatier - Toulouse 3 ( UPS ) -Centre National de la Recherche Scientifique ( CNRS ), Service Informatique : Développement, Exploitation et Assistance ( LAAS-IDEA ), ECOLE SUPERIEURE POLYTECHNIQUE D’ANTANANARIVO, Lionel SEGUIER, David GAUCHARD, Service Instrumentation Conception Caractérisation (LAAS-I2C), Laboratoire d'analyse et d'architecture des systèmes (LAAS), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Service Informatique : Développement, Exploitation et Assistance (LAAS-IDEA), Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse 1 Capitole (UT1), and Université Fédérale Toulouse Midi-Pyrénées
Subjects: supervision, monitoring, onduleur, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], web, SNMP, Python
Abstract: National audience; Ce stage consiste à développer une application web pour la supervision centralisée desonduleurs de secours dans un laboratoire de recherche. L’envoi des informations côtéonduleur se fait à partir de cartes de supervisions qui utilisent le protocole SNMP. Troisdémons ont été développés au cours de ce projet : le premier réalise la collecte régulièredes mesures des caractéristiques physiques des onduleurs, un autre écoute en permanenceles onduleurs au cas où ces derniers envoient des alertes et informe le responsable selonl’urgence des problèmes détectés et le dernier offre un service web qui permet à l’utilisateurd’accéder aux données temps réel de chaque onduleur, d’afficher l’historique des mesureset des alertes sous forme graphique et d’interagir avec la base de données. Le langage deprogrammation principal utilisé pour ce développement est Python. Cette application peutfonctionner avec d’autres matériels utilisant également le protocole SNMP.
Published: 2018

19. HLL v.2.7 Modelling Language Specification

Author: ORDIONI , Julien, BRETON , Nicolas, Colaço , Jean-Louis, RATP - Département ING/STF/QS [Fontenay-sous-Bois] (RATP), Régie Autonome des Transports Parisiens ( RATP ), and RATP
Subjects: Modelling language, Formal language, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], HLL, RATP, Specification, Prover technology
Abstract: This RATP document, based on an original document from Prover Technology, details the syntax and semantics of the formal modelling language " High Level Language " (HLL).HLL is used for several years by RATP to perform formal verification on CBTC and interlocking safety critical software.; Ce document RATP, basé sur un document original de Prover Technology, détaille la syntaxe ainsi que la sémantique du langage de modélisation formelle HLL (pour High Level Language).HLL est utilisé depuis plusieurs années maintenant à la RATP pour réaliser des vérifications formelles sur les logiciels critiques des CBTC et postes de signalisation.
Published: 2018

20. The MegaM@Rt2 ECSEL project: MegaModelling at Runtime – Scalable model-based framework for continuous development and runtime validation of complex systems

Author: Hugo Bruneliere, Jordi Cabot, Luigi Pomante, Pavel Smrz, Andrey Sadovykh, Davide Di Ruscio, Silvia Mazzini, Wasif Afzal, Abel Gómez, Dragos Truscan, Eric Cariou, Jesus Gorronogoitia, Mälardalen University College ( MDH ), NaoMod - Nantes Software Modeling Group ( NaoMod ), Laboratoire des Sciences du Numérique de Nantes ( LS2N ), Université de Nantes ( UN ) -École Centrale de Nantes ( ECN ) -Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ) -Université de Nantes ( UN ) -École Centrale de Nantes ( ECN ) -Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ), Automatique, productique et informatique ( DAPI ), IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ), University of L'Aquila [Italy] ( UNIVAQ ), SOFTEAM, INTECS, Laboratoire Informatique de l'Université de Pau et des Pays de l'Adour ( LIUPPA ), Université de Pau et des Pays de l'Adour ( UPPA ), Abo Akademi University [Turku], Institució Catalana de Recerca i Estudis Avançats [Barcelona] ( ICREA ), Universitat de Barcelona ( UB ) -Fundació Catalana per a la Recerca i la Innovació (FCRI)-ICREA, Universitat Oberta de Catalunya [Barcelona] ( UOC ), ATOS [madrid], ATOS Origin, Brno University of Technology, European Project : 737494,H2020,MegaM@Rt2 ( 2017 ), Mälardalen University (MDH), NaoMod - Nantes Software Modeling Group (LS2N - équipe NaoMod), Laboratoire des Sciences du Numérique de Nantes (LS2N), Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), Université de Nantes (UN)-Université de Nantes (UN)-École Centrale de Nantes (ECN)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Département Automatique, Productique et Informatique (IMT Atlantique - DAPI), IMT Atlantique (IMT Atlantique), University of L'Aquila [Italy] (UNIVAQ), Laboratoire Informatique de l'Université de Pau et des Pays de l'Adour (LIUPPA), Université de Pau et des Pays de l'Adour (UPPA), Åbo Akademi University [Turku], Institució Catalana de Recerca i Estudis Avançats (ICREA), Universitat Oberta de Catalunya [Barcelona] (UOC), Brno University of Technology [Brno] (BUT), European Project: 737494,H2020 ,H2020-ECSEL-2016-1-RIA-two-stage,MegaMaRt2(2017), NaoMod - Nantes Software Modeling Group (NaoMod), Université de Nantes (UN)-Université de Nantes (UN)-École Centrale de Nantes (ECN)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Università degli Studi dell'Aquila, Åbo Akademi University, Université de Pau et des Pays de l'Adour, Mälardalen University, and Universitat Oberta de Catalunya. Internet Interdisciplinary Institute (IN3)
Subjects: Work package, Computer science, Research and development management, Adaptive computing systems, 02 engineering and technology, System lifecycle, Design Time, tiempo de ejecución, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], temps de disseny, 0202 electrical engineering, electronic engineering, information engineering, Use case, Continuous development, computer.programming_language, Sistemes adaptatius (Informàtica), ingeniería dirigida por modelos, Model-Driven Engineering, Industrial enterprise, 020202 computer hardware & architecture, Electronic industries, Runtime, Hardware and Architecture, Scalability, enginyeria dirigida per models, Design time, Computer and Information Sciences, Traceability, Computer Networks and Communications, Life cycle, [INFO.INFO-SE]Computer Science [cs]/Software Engineering [cs.SE], [ INFO.INFO-SE ] Computer Science [cs]/Software Engineering [cs.SE], Deliverable, Artificial Intelligence, Sistemas adaptativos (Informática), Runtimes, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], business.industry, 020207 software engineering, Data- och informationsvetenskap, Megamodelling, Industrial research, temps d'execució, Model-driven engineering, Software, Software deployment, Systems design, tiempo de diseño, Model-driven architecture, Software engineering, business, computer, Traceability managements
Abstract: International audience; A major challenge for the European electronic industry is to enhance productivity by ensuring quality of development, integration and maintenance while reducing the associated costs. Model-Driven Engineering (MDE) principles and techniques have already shown promising capabilities, but they still need to scale up to support real-world scenarios implied by the full deployment and use of complex electronic components and systems. Moreover, maintaining efficient traceability, integration, and communication between two fundamental system life cycle phases (design time and runtime) is another challenge requiring the scalability of MDE. This paper presents an overview of the ECSEL1 project entitled “MegaModelling at runtime – Scalable model-based framework for continuous development and runtime validation of complex systems” (MegaM@Rt2), whose aim is to address the above mentioned challenges facing MDE. Driven by both large and small industrial enterprises, with the support of research partners and technology providers, MegaM@Rt2 aims to deliver a framework of tools and methods for: 1) system engineering/design and continuous development, 2) related runtime analysis and 3) global models and traceability management. Diverse industrial use cases (covering strategic domains such as aeronautics, railway, construction and telecommunications) will integrate and demonstrate the validity of the MegaM@Rt2 solution. This paper provides an overview of the MegaM@Rt2 project with respect to its approach, mission, objectives as well as to its implementation details. It further introduces the consortium as well as describes the work packages and few already produced deliverables.
Published: 2018
Full Text: View/download PDF

21. Construction of a multilingual corpus annotated with translation relations

Author: Zhai, Yuming, Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI), Université Paris Saclay (COmUE)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université - UFR d'Ingénierie (UFR 919), Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Université Paris-Sud - Paris 11 (UP11), Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur ( LIMSI ), and Université Paris-Sud - Paris 11 ( UP11 ) -Centre National de la Recherche Scientifique ( CNRS )
Subjects: [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, [ INFO.INFO-TT ] Computer Science [cs]/Document and Text Processing, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: International audience; Translation relations, which distinguish literal translation from other translation techniques, constitute an important subject of study for human translators (Chuquet & Paillard, 1989). However, automatic processing techniques based on interlingual relations, such as machine translation or paraphrase generation exploiting translation equivalence, have not exploited these relations explicitly until now. In this work, we present a categorisation of translation relations and annotate them in a parallel multilingual (English, French, Chinese) corpus of oral presentations, the TED Talks. Our long term objective will be to automatically detect these relations in order to integrate them as important characteristics for the search of monolingual segments in relation of equivalence (paraphrases) or of entailment. The annotated corpus resulting from our work will be made available to the community.; Les relations de traduction, qui distinguent la traduction littérale d'autres procédés, constituent un sujet d'étude important pour les traducteurs humains (Chuquet & Paillard, 1989). Or les traitements automatiques fondés sur des relations entre langues, tels que la traduction automatique ou la méthode de génération de paraphrases par équivalence de traduction, ne les ont pas exploitées explicitement jusqu'à présent. Dans ce travail, nous présentons une catégorisation des relations de traduction et nous les annotons dans un corpus parallèle multilingue (anglais, français, chinois) de présentations orales, les TED Talks. Notre objectif à plus long terme sera d'en faire la détection de manière automatique afin de pouvoir les intégrer comme caractéristiques importantes pour la recherche de segments monolingues en relation d'équivalence (paraphrases) ou d'implication. Le corpus annoté résultant de notre travail sera mis à disposition de la communauté.
Published: 2018

22. Traduction automatique du japonais vers le français: Bilan et perspectives

Author: Blin, Raoul, Centre de Recherches Linguistiques sur l'Asie Orientale ( CRLAO ), École des hautes études en sciences sociales ( EHESS ) -Institut National des Langues et Civilisations Orientales ( Inalco ) -Centre National de la Recherche Scientifique ( CNRS ), Centre de Recherches Linguistiques sur l'Asie Orientale (CRLAO), and École des hautes études en sciences sociales (EHESS)-Institut National des Langues et Civilisations Orientales (Inalco)-Centre National de la Recherche Scientifique (CNRS)
Subjects: French, japonais, Japanese, [ SHS.LANGUE ] Humanities and Social Sciences/Linguistics, français, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [SHS.LANGUE]Humanities and Social Sciences/Linguistics, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], machine translation, traduction automatique
Abstract: International audience; In this paper, we discuss the feasability of a neural machine translation system from Japanese to French, which would be able to obtain results that are equivalent to the state of the art. We first describe the state of the art for Ja>Fr and see many improvements compared to statistical machine translation. Second, we evaluate one free open baseline, OpenNMT, which achieves encouraging results. Based on these experiments, we suggest some ways to improve the results, taking into account the lack of improved and large corpora.; Nous étudions la possibilité de construire un dispositif de traduction automatique neuronale du japonais vers le français, capable d'obtenir des résultats à la hauteur de l'état de l'art, sachant que l'on ne peut disposer de grands corpus alignés bilingues. Nous proposons un état de l'art et relevons de nombreux signes d'amélioration de la qualité des traductions, en comparaison aux traductions statistiques jusque-là prédominantes. Nous testons ensuite un des baselines librement disponibles, OpenNMT, qui produit des résultats encourageants. Sur la base de cette expérience, nous proposons plusieurs pistes pour améliorer à terme la traduction et pour compenser le manque de corpus.
Published: 2018

23. CoNLL-UL: Universal Morphological Lattices for Universal Dependency Parsing

Author: More, A., Çetinoglu, Ö, Çöltekin, Ç, Habash, N., Sagot, B., Seddah, D., Dima Taji, Tsarfaty, R., Open University of Israël, Institute for Natural Language Processing [Stuttgart], University of Stuttgart, University of Tübingen, New York University [Abu Dhabi], NYU System (NYU), Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), ANR-16-CE33-0021,PARSITI,Analyser l'impossible, Traduire l'improbable(2016), ANR-15-CE38-0011,SoSweet,Une sociolinguistique de Twitter : liens sociaux et variations linguistiques(2015), ANR-11-IDEX-0005,USPC,Université Sorbonne Paris Cité(2011), New York University Abu Dhabi, Automatic Language Modelling and ANAlysis & Computational Humanities ( ALMAnaCH ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), ANR-16-CE33-0021,Parsiti,Parsing the Improbable : Translating the Improbable, ANR-15-CE38-0011-03,SoSweet,A Sociolinguistics of Twitter: Social Networks and Linguistic Variations, ANR-11-IDEX-0005-02/10-LABX-0083,EFL,Empirical Foundations of Linguistics : data, methods, models ( 2011 ), and ANR-11-IDEX-0005,EFL,Empirical Foundations of Linguistics : data, methods, models(2011)
Subjects: Morphology, Universal Dependencies, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Morphological Ambiguity, Morphological Analysis, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: International audience; Following the development of the universal dependencies (UD) framework and the CoNLL 2017 Shared Task on end-to-end UD parsing, we address the need for a universal representation of morphological analysis which on the one hand can capture a range of different alternative morphological analyses of surface tokens, and on the other hand is compatible with the segmentation and morphological annotation guidelines prescribed for UD treebanks. We propose the CoNLL universal lattices (CoNLL-UL) format, a new annotation format for word lattices that represent morphological analyses, and provide resources that obey this format for a range of typologically different languages. The resources we provide are harmonized with the two-level representation and morphological annotation in their respective UD v2 treebanks, thus enabling research on universal models for morphological and syntactic parsing , in both pipeline and joint settings, and presenting new opportunities in the development of UD resources for low-resource languages.
Published: 2018

24. Cheating a Parser to Death: Data-driven Cross-Treebank Annotation Transfer

Author: Seddah, Djamé, Villemonte de La Clergerie, Éric, Sagot, Benoît, Martinez Alonso, Hector, Candito, Marie, Université Paris-Sorbonne ( UP4 ), Automatic Language Modelling and ANAlysis & Computational Humanities ( ALMAnaCH ), Inria de Paris, Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), Thomson Reuters, Laboratoire de Linguistique Formelle ( LLF ), Université Paris Diderot - Paris 7 ( UPD7 ) -Centre National de la Recherche Scientifique ( CNRS ), ANR-16-CE33-0021,Parsiti,Parsing the Improbable : Translating the Improbable, ANR-15-CE38-0011-03,SoSweet,A Sociolinguistics of Twitter: Social Networks and Linguistic Variations, ANR-11-IDEX-0005-02/10-LABX-0083,EFL,Empirical Foundations of Linguistics : data, methods, models ( 2011 ), Université Paris-Sorbonne (UP4), Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Laboratoire de Linguistique Formelle (LLF UMR7110), Université Paris Diderot - Paris 7 (UPD7)-Centre National de la Recherche Scientifique (CNRS), ANR-16-CE33-0021,PARSITI,Analyser l'impossible, Traduire l'improbable(2016), ANR-15-CE38-0011,SoSweet,Une sociolinguistique de Twitter : liens sociaux et variations linguistiques(2015), ANR-11-IDEX-0005,USPC,Université Sorbonne Paris Cité(2011), Centre National de la Recherche Scientifique (CNRS)-Université Paris Diderot - Paris 7 (UPD7), ANR-11-IDEX-0005-02/10-LABX-0083,EFL,Empirical Foundations of Linguistics : data, methods, models(2011), and ANR-11-IDEX-0005,EFL,Empirical Foundations of Linguistics : data, methods, models(2011)
Subjects: Automatic Correction, Universal Dependencies, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Syntax, Treebanking, Cross-annotation Transfer, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: International audience; We present an efficient and accurate method for transferring annotations between two different treebanks of the same language. This method led to the creation of a new instance of the French Treebank (Abeillé et al., 2003), which follows the Universal Dependency annotation scheme and which was proposed to the participants of the CoNLL 2017 Universal Dependency parsing shared task (Zeman et al., 2017). Strong results from an evaluation on our gold standard (94.75% of LAS, 99.40% UAS on the test set) demonstrate the quality of this new annotated data set and validate our approach.
Published: 2018

25. DECO-MWE: Building a Linguistic Resource of Korean Multiword Expressions for Feature-Based Sentiment Analysis

Author: Jaeho Han, Changhoe Hwang, Seongyong Choi, Gwanghoon Yoo, Eric Laporte, Jeesun Nam, Digital Language & Knowledge Contents Research Association ( DICORA ), Hankuk University of Foreign Studies ( HUFS ), Hankuk University of Foreign Studies, Laboratoire d'Informatique Gaspard-Monge ( LIGM ), Université Paris-Est Marne-la-Vallée ( UPEM ) -École des Ponts ParisTech ( ENPC ) -ESIEE Paris-Fédération de Recherche Bézout-Centre National de la Recherche Scientifique ( CNRS ), Kiyoaki Shirai, Digital Language & Knowledge Contents Research Association (DICORA), Hankuk University of Foreign Studies (HUFS), Laboratoire d'Informatique Gaspard-Monge (LIGM), Université Paris-Est Marne-la-Vallée (UPEM)-École des Ponts ParisTech (ENPC)-ESIEE Paris-Fédération de Recherche Bézout-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-École des Ponts ParisTech (ENPC)-Université Paris-Est Marne-la-Vallée (UPEM), and Laporte, Eric
Subjects: [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, Sentiment analysis, [ INFO.INFO-TT ] Computer Science [cs]/Document and Text Processing, Feature-Based Sentiment Analysis, [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], Multiword Expression, DECO-MWE, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Local Grammar Graph
Abstract: International audience; This paper aims to construct a linguistic resource of Korean Multiword Expressions for Feature-Based Sentiment Analysis (FBSA): DECO-MWE. Dealing with multiword expressions (MWEs) has been a critical issue in FBSA since many constructs reveal lexical idiosyncrasy. To construct linguistic resources of sentiment MWEs efficiently, we utilize the Local Grammar Graph (LGG) methodology: DECO-MWE is formalized as a Finite-State Transducer that represents lexical-syntactic restrictions on MWEs. In this study, we built a corpus of cosmetics review texts, which show particularly frequent occurrences of MWEs. Based on an empirical examination of the corpus, four types of MWEs have been distinguished. The DECO-MWE thus covers the following four categories: Standard Polarity MWEs (SMWEs), Domain-Dependent Polarity MWEs (DMWEs), Compound Named Entity MWEs (EMWEs) and Compound Feature MWEs (FMWEs). The retrieval performance of the DECO-MWE shows 0.806 f-measure in the test corpus. This study brings a twofold outcome: first, a sizeable general-purpose polarity MWE lexicon, which may be broadly used in FBSA; second, a finite-state methodology adopted in this study to treat domain-dependent MWEs such as idiosyncratic polarity expressions, named entity expressions or feature expressions, and which may be reused in describing linguistic properties of other corpus domains.
Published: 2018

26. A multilingual collection of CoNLL-U-compatible morphological lexicons

Author: Sagot , Benoît, Automatic Language Modelling and ANAlysis & Computational Humanities ( ALMAnaCH ), Inria de Paris, Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), Sagot, Benoît, Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], Freely Available Language Resources, Universal Dependencies, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Morphological Lexicons, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: International audience; We introduce UDLexicons, a multilingual collection of morphological lexicons that follow the guidelines and format of the Universal Dependencies initiative. We describe the three approaches we use to create 53 morphological lexicons covering 38 languages, based on existing resources. These lexicons, which are freely available, have already proven useful for improving part-of-speech tagging accuracy in state-of-the-art architectures.
Published: 2018

27. Étiquetage en parties du discours de langues peu dotées par spécialisation des plongements lexicaux

Author: Pierre Magistry, Anne-Laure Ligozat, Sophie Rosset, Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI), Université Paris Saclay (COmUE)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université - UFR d'Ingénierie (UFR 919), Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Université Paris-Sud - Paris 11 (UP11), ANR-14-CE24-0003,RESTAURE,RESsources informatisées et Traitement AUtomatique pour les langues REgionales(2014), Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur ( LIMSI ), Université Paris-Sud - Paris 11 ( UP11 ) -Centre National de la Recherche Scientifique ( CNRS ), and ANR-14-CE24-0003,RESTAURE,RESsources informatisées et Traitement AUtomatique pour les langues REgionales ( 2014 )
Subjects: [ INFO ] Computer Science [cs], étiquetage en parties du discours, langues peu dotées, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [INFO]Computer Science [cs], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: Cet article présente une nouvelle méthode d'étiquetage en parties du discours adaptée aux langues peu dotées : la définition du contexte utilisé pour construire les plongements lexicaux est adaptée à la tâche, et de nouveaux vecteurs sont créés pour les mots inconnus. Les expériences menées sur le picard, le malgache et l'alsacien montrent que cette méthode améliore l'état de l'art pour ces trois langues peu dotées.
Published: 2018

28. Knowledge Base Population based on Entity Graph Analysis

Author: Rahman , Md Rashedur, Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur ( LIMSI ), Université Paris-Sud - Paris 11 ( UP11 ) -Centre National de la Recherche Scientifique ( CNRS ), Université Paris-Saclay, Brigitte Grau, Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI), Université Paris Saclay (COmUE)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université - UFR d'Ingénierie (UFR 919), Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Université Paris-Sud - Paris 11 (UP11), Université Paris Saclay (COmUE), and STAR, ABES
Subjects: Validation de relation, Relation validation, [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], Knowledge base population, Graphe de communauté, Peuplement de base de connaissance, Relation extraction, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Traitement des langues naturelles, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Community graph, Natural Language Processing, Extraction de relation
Abstract: Knowledge Base Population (KBP) is an important and challenging task specially when it has to be done automatically. The objective of KBP task is to make a collection of facts of the world. A Knowledge Base (KB) contains different entities, relationships among them and various properties of the entities. Relation extraction (RE) between a pair of entity mentions from text plays a vital role in KBP task. RE is also a challenging task specially for open domain relations. Generally, relations are extracted based on the lexical and syntactical information at the sentence level. However, global information about known entities has not been explored yet for RE task. We propose to extract a graph of entities from the overall corpus and to compute features on this graph that are able to capture some evidence of holding relationships between a pair of entities. In order to evaluate the relevance of the proposed features, we tested them on a task of relation validation which examines the correctness of relations that are extracted by different RE systems. Experimental results show that the proposed features lead to outperforming the state-of-the-art system., Le peuplement de base de connaissance (KBP) est une tâche importante qui présente de nombreux défis pour le traitement automatique des langues. L'objectif de cette tâche est d'extraire des connaissances de textes et de les structurer afin de compléter une base de connaissances. Nous nous sommes intéressés à la reconnaissance de relations entre entités. L'extraction de relations (RE) entre une paire de mentions d'entités est une tâche difficile en particulier pour les relations en domaine ouvert. Généralement, ces relations sont extraites en fonction des informations lexicales et syntaxiques au niveau de la phrase. Cependant, l'exploitation d'informations globales sur les entités n'a pas encore été explorée. Nous proposons d'extraire un graphe d'entités du corpus global et de calculer des caractéristiques sur ce graphe afin de capturer des indices des relations entre paires d'entités. Pour évaluer la pertinence des fonctionnalités proposées, nous les avons testées sur une tâche de validation de relation dont le but est de décider l'exactitude de relations extraites par différents systèmes. Les résultats expérimentaux montrent que les caractéristiques proposées conduisent à améliorer les résultats de l'état de l'art.
Published: 2018

29. End-to-End Automatic Speech Translation of Audiobooks

Author: Laurent Besacier, Alexandre Berard, Olivier Pietquin, Ali Can Kocabiyikoglu, Laboratoire d'Informatique de Grenoble (LIG ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole (GETALP ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Institut Universitaire de France (IUF), Ministère de l'Education nationale, de l’Enseignement supérieur et de la Recherche (M.E.N.E.S.R.), DeepMind Technologies, Sequential Learning (SEQUEL), Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), ANR-14-CE24-0016,KEHATH,Méthodes qualité avancées pour la post-édition de traduction automatique(2014), ANR-11-LABX-0025,PERSYVAL-lab,Systemes et Algorithmes Pervasifs au confluent des mondes physique et numérique(2011), Laboratoire d'Informatique de Grenoble ( LIG ), Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ), Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole ( GETALP ), Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ) -Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ), Institut Universitaire de France ( IUF ), Ministère de l'Éducation nationale, de l’Enseignement supérieur et de la Recherche ( M.E.N.E.S.R. ), Sequential Learning ( SEQUEL ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189 ( CRIStAL ), and Ecole Centrale de Lille-Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS ) -Ecole Centrale de Lille-Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS )
Subjects: FOS: Computer and information sciences, Vocabulary, Computer science, media_common.quotation_subject, Speech recognition, 02 engineering and technology, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], 030507 speech-language pathology & audiology, 03 medical and health sciences, End-to-end principle, Speech translation, 0202 electrical engineering, electronic engineering, information engineering, Automatic speech, Target text, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], media_common, Speech Translation, Computer Science - Computation and Language, LibriSpeech, Task analysis, 020201 artificial intelligence & image processing, Transcription (software), 0305 other medical science, End-to-end models, Computation and Language (cs.CL), Decoding methods
Abstract: We investigate end-to-end speech-to-text translation on a corpus of audiobooks specifically augmented for this task. Previous works investigated the extreme case where source language transcription is not available during learning nor decoding, but we also study a midway case where source language transcription is available at training time only. In this case, a single model is trained to decode source speech into target text in a single pass. Experimental results show that it is possible to train compact and efficient end-to-end speech translation models in this setup. We also distribute the corpus and hope that our speech translation baseline on this corpus will be challenged in the future., Accepted to ICASSP 2018 (poster presentation)
Published: 2018

30. Initial Sets in Abstract Argumentation Frameworks

Author: Claudette Cayrol, Yuming Xu, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Shandong University - SDU (CHINA), Institut de Recherche en Informatique de Toulouse - IRIT (Toulouse, France), Shandong University, Institut de recherche en informatique de Toulouse ( IRIT ), Institut National Polytechnique [Toulouse] ( INP ) -Université Toulouse 1 Capitole ( UT1 ) -Université Toulouse - Jean Jaurès ( UT2J ) -Université Paul Sabatier - Toulouse 3 ( UPS ) -Centre National de la Recherche Scientifique ( CNRS ), Argumentation, Décision, Raisonnement, Incertitude et Apprentissage (IRIT-ADRIA), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, and Institut National Polytechnique de Toulouse - INPT (FRANCE)
Subjects: Logic, Computer science, Semantics (computer science), media_common.quotation_subject, 0102 computer and information sciences, 02 engineering and technology, computer.software_genre, 01 natural sciences, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], [ INFO.INFO-LG ] Computer Science [cs]/Machine Learning [cs.LG], Argumentation theory, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 0202 electrical engineering, electronic engineering, information engineering, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [ INFO.INFO-AI ] Computer Science [cs]/Artificial Intelligence [cs.AI], Abstract argumentation, Skepticism, media_common, Logique en informatique, Initial semantics, business.industry, Programming language, [INFO.INFO-LO]Computer Science [cs]/Logic in Computer Science [cs.LO], Informatique et langage, Extension (predicate logic), Intelligence artificielle, Apprentissage, Philosophy, 010201 computation theory & mathematics, 020201 artificial intelligence & image processing, [ INFO.INFO-LO ] Computer Science [cs]/Logic in Computer Science [cs.LO], Artificial intelligence, Extension-based semantics, business, computer, AND gate
Abstract: International audience; Dung’s abstract argumentation provides us with a general framework to deal with argumentation, non-monotonic reasoning and logic programming. For the extension-based semantics, one of the basic principles is I-maximality which is in particular related with the notion of skeptical justification. Another one is directionality which can be employed for the study of dynamics of argumentation. In this paper, we introduce two new extension-based semantics into Dung’s abstract argumentation, called grounded-like semantics and initial semantics which satisfy the I-maximality and directionality principles. The initial semantics has many good properties and can be expected to play a central role in studying other extension-based semantics, such as admissible, complete and preferred semantics.
Published: 2018

31. Inferring inflection classes with description length

Author: Benoît Sagot, Olivier Bonami, Sacha Beniamine, Laboratoire de Linguistique Formelle (LLF UMR7110), Centre National de la Recherche Scientifique (CNRS)-Université Paris Diderot - Paris 7 (UPD7), Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), ANR-11-IDEX-0005-02/10-LABX-0083,EFL,Empirical Foundations of Linguistics : data, methods, models(2011), Université Paris Diderot - Paris 7 (UPD7)-Centre National de la Recherche Scientifique (CNRS), ANR-11-IDEX-0005,EFL,Empirical Foundations of Linguistics : data, methods, models(2011), ANR-11-IDEX-0005,USPC,Université Sorbonne Paris Cité(2011), Sagot, Benoît, Université Sorbonne Paris Cité - - USPC2011 - ANR-11-IDEX-0005 - IDEX - VALID, Laboratoire de Linguistique Formelle ( LLF ), Université Paris Diderot - Paris 7 ( UPD7 ) -Centre National de la Recherche Scientifique ( CNRS ), Automatic Language Modelling and ANAlysis & Computational Humanities ( ALMAnaCH ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), and ANR-11-IDEX-0005-02/10-LABX-0083,EFL,Empirical Foundations of Linguistics : data, methods, models ( 2011 )
Subjects: Morphology, Linguistics and Language, Computer science, MDL, P1-1091, computer.software_genre, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], 030507 speech-language pathology & audiology, 03 medical and health sciences, European Portuguese, Inflection, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [SHS.LANGUE]Humanities and Social Sciences/Linguistics, Philology. Linguistics, 060201 languages & linguistics, business.industry, 06 humanities and the arts, [SHS.LANGUE] Humanities and Social Sciences/Linguistics, language.human_language, Computer Science Applications, Inflection classes, [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], Modeling and Simulation, 0602 languages and literature, [ SHS.LANGUE ] Humanities and Social Sciences/Linguistics, language, Pairwise comparison, Artificial intelligence, 0305 other medical science, business, computer, Natural language processing, Intuition
Abstract: International audience; We discuss the notion of an inflection class system, a traditional ingredient of the description of inflection systems of nontrivial complexity. We distinguish systems of microclasses, which partition a set of lexemes in classes with identical behavior, and systems of macroclasses, which group lexemes that are similar enough in a few larger classes. On the basis of the intuition that macroclasses should contribute to a concise description of the system, we propose one algorithmic method for inferring macroclasses from raw inflectional paradigms, based on minimisation of the description length of the system under a given strategy of identifying morphological alternations in paradigms. We then exhibit classifications produced by our implementation on French and European Portuguese conjugation data and argue that they constitute an appropriate systematisation of traditional classifications. To arrive at such a convincing systematisation, it was crucial for us to use a local approach to inflection class similarity (based on pairwise comparisons of paradigm cells) rather than a global approach (based on the simultaneous comparison of all cells). We conclude that it is indeed possible to infer inflectional macroclasses objectively.
Published: 2018

32. Model-Based Design, Analysis and Synthesis for TSP Multi-Core Space systems

Author: Honvault , Christophe, Hugues , Jerome, Pagetti , Claire, Laboratoire Traitement et Communication de l'Information ( LTCI ), Télécom ParisTech-Institut Mines-Télécom [Paris]-Centre National de la Recherche Scientifique ( CNRS ), ONERA - The French Aerospace Lab ( Toulouse ), ONERA, IRIT-ENSEEIHT, Institut de recherche en informatique de Toulouse ( IRIT ), Institut National Polytechnique [Toulouse] ( INP ) -Université Toulouse 1 Capitole ( UT1 ) -Université Toulouse - Jean Jaurès ( UT2J ) -Université Paul Sabatier - Toulouse 3 ( UPS ) -Centre National de la Recherche Scientifique ( CNRS ) -Institut National Polytechnique [Toulouse] ( INP ) -Université Toulouse 1 Capitole ( UT1 ) -Université Toulouse - Jean Jaurès ( UT2J ) -Université Paul Sabatier - Toulouse 3 ( UPS ) -Centre National de la Recherche Scientifique ( CNRS ), Pagetti, Claire, European Space Agency (ESA), Institut Supérieur de l'Aéronautique et de l'Espace (ISAE-SUPAERO), ONERA / DTIS, Université de Toulouse [Toulouse], and ONERA-PRES Université de Toulouse
Subjects: [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: International audience; —Symmetric multiprocessing (SMP) and Time and Space Partitioning (TSP) are two complementary paradigms for the design of multi-core-based aerospace systems. They impose new steps in the development process: capturing complex configuration attributes, analyzing their correctness – in particular their predictability – while guaranteeing performance. In this context, model-based techniques provide a well-suited framework to design, analyze and automatically synthesize those systems. In this paper, we report on a set of extenstions of TASTE to support SMP and TSP-based multi-core platforms. We first present the key architectural elements of these systems and then detail how these have been integrated as part of the code generation tool-chain. We then present experiments realized on two case studies and two hardware targets, both provided with the RTEMS operating system and XTRATUM hypervisor.
Published: 2018

33. A model-based certification approach for multi/many-core embedded systems

Author: Bieber, Pierre, Boniol, Frédéric, Bouchebaba, Youcef, Brunel, Julien, Pagetti, Claire, Poitou, Olivier, Polacsek, Thomas, Santinelli, Luca, Sensfelder, Nathanaël, ONERA - The French Aerospace Lab ( Palaiseau ), ONERA, ONERA - The French Aerospace Lab ( Toulouse ), Pagetti, Claire, ONERA / DTIS, Université de Toulouse [Toulouse], and ONERA-PRES Université de Toulouse
Subjects: CERTIFICATION, [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], MULTI-CORE PROCESSORS, FORMAL METHODS, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: International audience; —This article presents the first year results of the PHY-LOG project that aims at providing a model-based certification framework for aeronautics systems designers when developing multi/many-core-based architectures. After a brief reminder of the certification objectives, we present an overview of the PHYLOG approach. We then detail two points of the methodology: (1) a certification oriented meta-model for multi-and many-core platforms, and (2) an interference prediction method based on this meta-model. This method is then illustrated on a sub-part of the many-core Kalray MPPA R-256.
Published: 2018

34. Evaluation of DREAMS resource management solutions on a mixed-critical demonstrator

Author: Fohler, Gerhard, Gala, Gautam, Gracia Pérez, Daniel, Pagetti, Claire, Thales Research and Technologies [Orsay] ( TRT ), THALES, ONERA - The French Aerospace Lab ( Toulouse ), ONERA, IRIT-ENSEEIHT, Institut de recherche en informatique de Toulouse ( IRIT ), Institut National Polytechnique [Toulouse] ( INP ) -Université Toulouse 1 Capitole ( UT1 ) -Université Toulouse - Jean Jaurès ( UT2J ) -Université Paul Sabatier - Toulouse 3 ( UPS ) -Centre National de la Recherche Scientifique ( CNRS ) -Institut National Polytechnique [Toulouse] ( INP ) -Université Toulouse 1 Capitole ( UT1 ) -Université Toulouse - Jean Jaurès ( UT2J ) -Université Paul Sabatier - Toulouse 3 ( UPS ) -Centre National de la Recherche Scientifique ( CNRS ), Thales Research and Technologies [Orsay] (TRT), ONERA - The French Aerospace Lab [Toulouse], Réseaux, Mobiles, Embarqués, Sans fil, Satellites (IRIT-RMESS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), and Université Fédérale Toulouse Midi-Pyrénées
Subjects: [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: International audience; —The paper describes the resource management developed within the DREAMS middleware and how it is able to support core failures and temporal overload situations. Those capabilities are then highlighted and assessed in the industrial mixed-critical demonstrator of the project. 1
Published: 2018

35. Modularizing Behavioral and Architectural Crosscutting Concerns in Formal Component-Based Systems - Application to the Behavior Interaction Priority Framework

Author: Mohamad Y. Jaber, Antoine El-Hokayem, Yliès Falcone, Compiler Optimization and Run-time Systems ( CORSE ), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Laboratoire d'Informatique de Grenoble ( LIG ), Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ) -Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ), Laboratoire d'Informatique de Grenoble ( LIG ), Université Pierre Mendès France - Grenoble 2 ( UPMF ) -Université Joseph Fourier - Grenoble 1 ( UJF ) -Institut National Polytechnique de Grenoble ( INPG ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Grenoble Alpes ( UGA ), Université Grenoble Alpes - UFR Informatique et Mathématiques Appliquées ( UGA UFR IMAG ), Université Grenoble Alpes ( UGA ), American University of Beirut [Beyrouth], Compiler Optimization and Run-time Systems (CORSE), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Informatique de Grenoble (LIG ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Laboratoire d'Informatique de Grenoble (LIG ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Université Grenoble Alpes - UFR Informatique et Mathématiques Appliquées (UGA UFR IMAG), Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), and American University of Beirut [Beyrouth] (AUB)
Subjects: FOS: Computer and information sciences, Logic, Computer science, Aspect-oriented programming, [INFO.INFO-SE]Computer Science [cs]/Software Engineering [cs.SE], 02 engineering and technology, [ INFO.INFO-SE ] Computer Science [cs]/Software Engineering [cs.SE], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Operational semantics, Theoretical Computer Science, Computer Science - Software Engineering, [ INFO.INFO-DC ] Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], Component (UML), Synchronization (computer science), 0202 electrical engineering, electronic engineering, information engineering, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [ INFO.INFO-ES ] Computer Science [cs]/Embedded Systems, business.industry, Separation of concerns, Runtime verification, 020207 software engineering, Fault tolerance, Software Engineering (cs.SE), Computational Theory and Mathematics, [INFO.INFO-ES]Computer Science [cs]/Embedded Systems, 020201 artificial intelligence & image processing, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], Communications protocol, Software engineering, business, Software
Abstract: International audience; We define a method to modularize crosscutting concerns in Component-Based Systems (CBSs) expressed using the Behavior Interaction Priority (BIP) framework. Our method is inspired from the Aspect Oriented Programming (AOP) paradigm which was initially conceived to support the separation of concerns during the development of monolithic systems. BIP has a formal operational semantics and makes a clear separation between architecture and behavior to allow for compositional and incremental design and analysis of systems. We distinguish local from global aspects. Local aspects model concerns at the component level and are used to refine the behavior of components. Global aspects model concerns at the architecture level, and hence refine communications (synchronization and data transfer) between components. We formalize local and global aspects as well as their composition and integration into a BIP system through rigorous transformation primitives. We present AOP-BIP, a tool for Aspect-Oriented Programming of BIP systems, demonstrate its use to modularize logging, security, and fault tolerance in a network protocol, and discuss its possible use in runtime verification of CBSs.
Published: 2018
Full Text: View/download PDF

36. Towards Qualitative Word Embeddings Evaluation: Measuring Neighbors Variation

Author: Bénédicte Pierrejean, Ludovic Tanguy, Tanguy, Ludovic, Cognition, Langues, Langage, Ergonomie (CLLE-ERSS), Université Bordeaux Montaigne-École pratique des hautes études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Université Toulouse - Jean Jaurès (UT2J)-Centre National de la Recherche Scientifique (CNRS), Cognition, Langues, Langage, Ergonomie ( CLLE-ERSS ), École pratique des hautes études ( EPHE ) -Université Toulouse - Jean Jaurès ( UT2J ) -Université Bordeaux Montaigne-Centre National de la Recherche Scientifique ( CNRS ), École pratique des hautes études (EPHE), and Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Université Toulouse - Jean Jaurès (UT2J)-Université Bordeaux Montaigne-Centre National de la Recherche Scientifique (CNRS)
Subjects: Computer science, business.industry, Pattern recognition, Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing), 02 engineering and technology, [SHS.LANGUE] Humanities and Social Sciences/Linguistics, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], 03 medical and health sciences, 0302 clinical medicine, Variation (linguistics), [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], 030221 ophthalmology & optometry, 0202 electrical engineering, electronic engineering, information engineering, [ SHS.LANGUE ] Humanities and Social Sciences/Linguistics, 020201 artificial intelligence & image processing, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Artificial intelligence, [SHS.LANGUE]Humanities and Social Sciences/Linguistics, business, Value (mathematics), Word (computer architecture)
Abstract: International audience; We propose a method to study the variation lying between different word embeddings models trained with different parameters. We explore the variation between models trained with only one varying parameter by observing the distributional neighbors variation and show how changing only one parameter can have a massive impact on a given semantic space. We show that the variation is not affecting all words of the semantic space equally. Variation is influenced by parameters such as setting a parameter to its minimum or maximum value but it also depends on the corpus intrinsic features such as the frequency of a word. We identify semantic classes of words remaining stable across the models trained and specific words having high variation.
Published: 2018

37. Digitization and preservation of cultural heritage: The CEPROQHA approach

Author: Abdelhak Belhi, Sebti Foufou, Abdelaziz Bouras, Décision et Information pour les Systèmes de Production ( DISP ), Université Lumière - Lyon 2 ( UL2 ) -Université Claude Bernard Lyon 1 ( UCBL ), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon ( INSA Lyon ), Université de Lyon-Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ), Qatar University, Laboratoire d'Electronique, d'Informatique et d'Image UMR CNRS 6306 ( Le2i ), Université de Technologie de Belfort-Montbeliard ( UTBM ) -Centre National de la Recherche Scientifique ( CNRS ) -École Nationale Supérieure d'Arts et Métiers ( ENSAM ) -Université de Bourgogne ( UB ) -AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement, Décision et Information pour les Systèmes de Production (DISP), Université Lumière - Lyon 2 (UL2)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA), Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508] (Le2i), Université de Technologie de Belfort-Montbeliard (UTBM)-Université de Bourgogne (UB)-École Nationale Supérieure d'Arts et Métiers (ENSAM), Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique (CNRS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université Claude Bernard Lyon 1 (UCBL), and Université de Lyon-Université Lumière - Lyon 2 (UL2)
Subjects: History, [ INFO ] Computer Science [cs], Content management system, 02 engineering and technology, Semantics, Digital records, 01 natural sciences, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], World Wide Web, ACM: H.: Information Systems, Cultural diversity, 3D Modeling, 0202 electrical engineering, electronic engineering, information engineering, [INFO]Computer Science [cs], [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Digital preservation, CEPROQHA project, Digitization, ComputingMilieux_MISCELLANEOUS, Digital heritage, 010401 analytical chemistry, ACM : H.: Information Systems, 020207 software engineering, 0104 chemical sciences, Cultural heritage, Semantic enrichment, Humanity
Abstract: The humanity has always learned from the previous experiences for many reasons. The national heritage proves to be a great way to discover a nation's history. As a result, these priceless cultural items have a special attention. However, Since the wide adoption of new digital technologies, documenting, storing, and exhibiting cultural heritage assets became more affordable and reliable. These digital records are then used in several applications. Researchers saw the opportunity to use digital heritage recordings for long-term preservation. In this paper, we present the research progress in cultural heritage digital processing and preservation, highlighting the most impactful advances. Additionally, we present the CEPROQHA project which is based on a new approach aiming at achieving cost-effective acquisition and digital preservation for cultural heritage artifacts in Qatar. - 2017 IEEE. CEPROQHA3 is a cooperative research project between Qatar University and Brunel University, London, funded by the Qatar National Research Fund (QNRF) under the National Priorities Research Program(NPRP) 9th cycle. The project goal. ACKNOWLEDGEMENTS This publication was made possible by NPRP grant 9-181-1-036 from the Qatar National Research Fund (a member of Qatar Foundation). The statements made herein are solely the responsibility of the authors. Scopus
Published: 2018
Full Text: View/download PDF

38. Application of Graph Rewriting to Natural Language Processing

Author: Bonfante, Guillaume, Guillaume, Bruno, Perrier, Guy, Guillaume, Bruno, Christian Rétoré, Université de Lorraine ( UL ), Carbone (CARBONE), Department of Formal Methods (LORIA - FM), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Semantic Analysis of Natural Language (SEMAGRAMME), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)
Subjects: 060201 languages & linguistics, 030507 speech-language pathology & audiology, 03 medical and health sciences, TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES, [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], 0602 languages and literature, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], 06 humanities and the arts, 16. Peace & justice, 0305 other medical science, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: International audience; The paradigm of Graph Rewriting is used very little in the field of Natural Language Processing. But graphs are a natural way of representing the deep syntax and the semantics of natural languages. Deep syntax is an abstraction of syntactic dependencies towards semantics in the form of graphs and there is a compact way of representing the semantics in an underspecified logical framework also with graphs. Then, Graph Rewriting reconciles efficiency with linguistic readability for producing representations at some linguistic level by transformation of a neighbor level: from raw text to surface syntax, from surface syntax to deep syntax, from deep syntax to underspecified logical semantics and conversely.
Published: 2018

39. A corpus of German political speeches from the 21st century

Author: Barbaresi , Adrien, Barbaresi, Adrien, Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga, Berlin-Brandenburgische Akademie der Wissenschaften (BBAW), and Berlin-Brandenburgische Akademie der Wissenschaften ( BBAW )
Subjects: Keyword extraction, [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], [ SHS.LANGUE ] Humanities and Social Sciences/Linguistics, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [SHS.LANGUE]Humanities and Social Sciences/Linguistics, Web corpus construction, [ SHS.SCIPO ] Humanities and Social Sciences/Political science, [SHS.LANGUE] Humanities and Social Sciences/Linguistics, [SHS.SCIPO] Humanities and Social Sciences/Political science, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], [SHS.SCIPO]Humanities and Social Sciences/Political science, Visualization
Abstract: International audience; The present German political speeches corpus follows from a initial release which has been used in various research contexts. This article documents an updated and extended version: as 2017 marks the end of a legislative period, the corpus now includes the four highest ranked functions on federal state level. Besides providing a citable reference for this resource, the main contributions are (1) an extensive description of the corpus to be released and (2) the description of an interface to navigate through the texts, designed for researchers beyond the corpus and computational linguistics communities as well as for the general public. The corpus can be considered to be from the 21st century since most speeches have been written after 2001 and also because it includes a visualiza-tion interface providing synoptic overviews ordered chronologically, by speaker or by keyword as well as consequent accesses to the texts.
Published: 2018

40. A question-answering system in the legal domain: the case of naval regulatory texts

Author: Kafcah Emani , Cheikh, Haralambous , Yannis, Télécom Bretagne (devenu IMT Atlantique), Ex-Bibliothèque, Lab-STICC_IMTA_CID_DECIDE, Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC), Institut Mines-Télécom [Paris] (IMT)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-École Nationale d'Ingénieurs de Brest (ENIB)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL)-Institut Mines-Télécom [Paris] (IMT)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-École Nationale d'Ingénieurs de Brest (ENIB)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL), Département Informatique (IMT Atlantique - INFO), IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance ( Lab-STICC ), École Nationale d'Ingénieurs de Brest ( ENIB ) -Université de Bretagne Sud ( UBS ) -Université de Brest ( UBO ) -ENSTA Bretagne-Institut Mines-Télécom [Paris]-Centre National de la Recherche Scientifique ( CNRS ) -Université Bretagne Loire ( UBL ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ) -École Nationale d'Ingénieurs de Brest ( ENIB ) -Université de Bretagne Sud ( UBS ) -Université de Brest ( UBO ) -ENSTA Bretagne-Institut Mines-Télécom [Paris]-Centre National de la Recherche Scientifique ( CNRS ) -Université Bretagne Loire ( UBL ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ), Département Informatique ( INFO ), and IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique )
Subjects: ontologie légale, legal texts, [INFO.INFO-NI] Computer Science [cs]/Networking and Internet Architecture [cs.NI], Question-Answering system, [ INFO.INFO-NI ] Computer Science [cs]/Networking and Internet Architecture [cs.NI], rules, règles, navigation maritime, SPARQL, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], legal ontology, [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI], [ INFO.INFO-HC ] Computer Science [cs]/Human-Computer Interaction [cs.HC], [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], rules, SPARQL, Regulatory texts, système questions-réponses, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], Textes réglementaires, [INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC], textes juridiques, sea navigation
Abstract: We present the first steps of the REIZHMOR project, the goal of which is to model legal and regulatory texts on sea navigation. After a short presentation of the corpus, which consists of prefectoral decrees referenced in a volume of the \emph{Sailing Directions} of the Hydrographic and Oceanographic Service of French Navy, we describe the development of a Question-Answering system based on SPARQL queries to a knowledge base, giving particular attention to the specific difficulties of legal language., Nous présentons les premiers travaux du projet REIZHMOR dont le but est la modélisation de textes juridiques et réglementaires autour de la navigation maritime. Après une présentation du corpus, constitué par les arrêtés (inter)préfectoraux référencés dans un volume des Instructions nautiques du Shom (Service hydrographique et océanographique de la marine), nous décrivons l'élaboration d'un système de questions-réponses basé sur des requêtes SPARQL adressées à une base de connaissances, avec une attention particulière portée aux difficultés spécifiques du langage juridique.
Published: 2018

41. Building a syntactic-semantic interface for a semi-automatically generated TAG for Arabic

Author: Ben Khelil, Chérifa, Zribi, Chiraz, Duchier, Denys, Parmentier, Yannick, Laboratoire RIADI-GDL [Manouba], Ecole Nationale des Sciences de l'Informatique, Manouba, Tunisie, Laboratoire d'Informatique Fondamentale d'Orléans ( LIFO ), Université d'Orléans ( UO ) -Institut National des Sciences Appliquées - Centre Val de Loire ( INSA CVL ), Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ), Natural Language Processing : representations, inference and semantics ( SYNALP ), Department of Natural Language Processing & Knowledge Discovery ( LORIA - NLPKD ), Laboratoire Lorrain de Recherche en Informatique et ses Applications ( LORIA ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Université de Lorraine ( UL ) -Centre National de la Recherche Scientifique ( CNRS ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Université de Lorraine ( UL ) -Centre National de la Recherche Scientifique ( CNRS ) -Laboratoire Lorrain de Recherche en Informatique et ses Applications ( LORIA ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Université de Lorraine ( UL ) -Centre National de la Recherche Scientifique ( CNRS ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Université de Lorraine ( UL ) -Centre National de la Recherche Scientifique ( CNRS ), Laboratoire de recherche en Génie Logiciel, Applications distribuées, Systèmes décisionnels et Imagerie intelligente [Manouba] (RIADI), École Nationale des Sciences de l'Informatique [Manouba] (ENSI), Université de la Manouba [Tunisie] (UMA)-Université de la Manouba [Tunisie] (UMA), Laboratoire d'Informatique Fondamentale d'Orléans (LIFO), Université d'Orléans (UO)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA), Natural Language Processing : representations, inference and semantics (SYNALP), Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)
Subjects: ACM: I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE, TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES, Tree Adjoining Grammar (TAG), Arabic language, ACM : I.: Computing Methodologies/I.7: DOCUMENT AND TEXT PROCESSING, meta-grammar, syntax-semantic interface, ACM: I.: Computing Methodologies/I.7: DOCUMENT AND TEXT PROCESSING, ACM : I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], semantic role, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], semantic frame
Abstract: Extended version of a paper presented at ACIT 2017. Full text available at https://iajit.org/portal/PDF/Special%20Issue%202018,%20No.%203A/17414.pdf; International audience; Syntactic and semantic resources play an important role for various Natural Language Processing (NLP) tasks by providing information about the correct structural representations of the sentences and their meaning. To date, there is not a wide-coverage electronic grammar for the Arabic language. In this context, we present a new approach for building a tree adjoining grammar to represent the syntax and the semantic of modern standard Arabic. This grammar is produced semi-automatically with the XMG (eXtensible MetaGrammar) description language. First the syntax of Arabic is described using the defined Arab-XMG meta-grammar. Then semantic information is added by introducing semantic frame-based dimension into the meta-grammar. This is achieved by exploiting lexical resources such as Arabic VerbNet. Finally, the link between semantic and syntax is established using a syntax-semantic interface that allows the construction of sentence meaning through semantic role labeling. Experiments were performed to check grammar coverage as well as the syntactic-semantic analysis. The results showed that the generated grammar can cover the basic syntactic structures of Arabic sentences and the different phrasal structures with a precision rate of about 92%. Moreover, it confirms the effectiveness of the proposed approach as we were able to parse semantically a set of sentences and build their semantic representations with a precision rate of about 72%.
Published: 2018

42. Predicting Word Embeddings Variability

Author: Bénédicte Pierrejean, Ludovic Tanguy, Cognition, Langues, Langage, Ergonomie ( CLLE-ERSS ), École pratique des hautes études ( EPHE ) -Université Toulouse - Jean Jaurès ( UT2J ) -Université Bordeaux Montaigne-Centre National de la Recherche Scientifique ( CNRS ), Cognition, Langues, Langage, Ergonomie (CLLE-ERSS), Université Bordeaux Montaigne-École pratique des hautes études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Université Toulouse - Jean Jaurès (UT2J)-Centre National de la Recherche Scientifique (CNRS), Tanguy, Ludovic, École pratique des hautes études (EPHE), and Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Université Toulouse - Jean Jaurès (UT2J)-Université Bordeaux Montaigne-Centre National de la Recherche Scientifique (CNRS)
Subjects: Computer science, Stability (learning theory), 02 engineering and technology, Space (commercial competition), 050105 experimental psychology, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], 0202 electrical engineering, electronic engineering, information engineering, 0501 psychology and cognitive sciences, Word2vec, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [SHS.LANGUE]Humanities and Social Sciences/Linguistics, Reliability (statistics), Hyperparameter, business.industry, 05 social sciences, Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing), Pattern recognition, [SHS.LANGUE] Humanities and Social Sciences/Linguistics, Variation (linguistics), [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], [ SHS.LANGUE ] Humanities and Social Sciences/Linguistics, Embedding, 020201 artificial intelligence & image processing, Artificial intelligence, business, Computer Science::Formal Languages and Automata Theory, Word (computer architecture)
Abstract: International audience; Neural word embeddings models (such as those built with word2vec) are known to have stability problems: when retraining a model with the exact same hyperparameters, words neighborhoods may change. We propose a method to estimate such variation, based on the overlap of neighbors of a given word in two models trained with identical hyperparam-eters. We show that this inherent variation is not negligible, and that it does not affect every word in the same way. We examine the influence of several features that are intrinsic to a word, corpus or embedding model and provide a methodology that can predict the variability (and as such, reliability) of a word representation in a semantic vector space.
Published: 2018

43. Boosting a Rule-Based Chatbot Using Statistics and User Satisfaction Ratings

Author: Vladislav Maraev, Octavia Efraim, João António Rodrigues, Linguistique, Ingénierie, Didactique des Langues ( LIDILE ), Université de Rennes 2 ( UR2 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ), Linguistique, Ingénierie, Didactique des Langues (LIDILE), Université de Rennes 2 (UR2), and Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)
Subjects: Boosting (machine learning), Artificial neural network, business.industry, Computer science, User satisfaction, Rule-based system, ACM: I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.7: Natural Language Processing/I.2.7.3: Language parsing and understanding, 02 engineering and technology, Machine learning, computer.software_genre, Convolutional neural network, Chatbot, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], ACM: I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.6: Learning/I.2.6.2: Connectionism and neural nets, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], 020201 artificial intelligence & image processing, Artificial intelligence, ACM : I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.6: Learning/I.2.6.2: Connectionism and neural nets, business, computer, ACM : I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.7: Natural Language Processing/I.2.7.3: Language parsing and understanding
Abstract: International audience; Using data from user-chatbot conversations where users have rated the answers as good or bad, we propose a more efficient alternative to a chatbot's keyword-based answer retrieval heuristic. We test two neural network approaches to the near-duplicate question detection task as a first step towards a better answer retrieval method. A convolutional neural network architecture gives promising results on this difficult task.
Published: 2017
Full Text: View/download PDF

44. A structural benchmark for logical argumentation frameworks

Author: Bruno Yun, Madalina Croitoru, Srdjan Vesic, Rallou Thomopoulos, Pierre Bisquert, Graphs for Inferences on Knowledge (GRAPHIK), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Centre de Recherche en Informatique de Lens (CRIL), Université d'Artois (UA)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Inria Sophia Antipolis - Méditerranée (CRISAM), Centre National de la Recherche Scientifique (CNRS)-Université d'Artois (UA), Graphs for Inferences on Knowledge ( GRAPHIK ), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier ( LIRMM ), Université de Montpellier ( UM ) -Centre National de la Recherche Scientifique ( CNRS ) -Université de Montpellier ( UM ) -Centre National de la Recherche Scientifique ( CNRS ) -Inria Sophia Antipolis - Méditerranée ( CRISAM ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), Centre de Recherche en Informatique de Lens ( CRIL ), and Université d'Artois ( UA ) -Centre National de la Recherche Scientifique ( CNRS )
Subjects: Generator (computer programming), Programming language, Computer science, Suite, 02 engineering and technology, Computational argumentation, computer.software_genre, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Argumentation theory, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Benchmark (computing), Computer Science::Programming Languages, 020201 artificial intelligence & image processing, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Semantic Web, computer
Abstract: International audience; This paper proposes a practically-oriented benchmark suite for computational argumentation. We instantiate abstract argumentation frameworks with existential rules, a language widely used in Semantic Web applications and provide a generator of such instantiated graphs. We analyse performance of argu-mentation solvers on these benchmarks.
Published: 2017
Full Text: View/download PDF

45. Using Spatio-temporal Trajectories to Monitor Construction Sites for Safety Management

Author: Muhammad Arslan, Christophe Cruz, Ana-Maria Roxin, Dominique Ginhac, Laboratoire Electronique, Informatique et Image ( Le2i ), Université de Bourgogne ( UB ) -AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique ( CNRS ), Laboratoire Systèmes et Transports ( SET ), Université de Technologie de Belfort-Montbeliard ( UTBM ) -Institut de Recherche sur les Transports, l'Energie et la Société - IRTES, Laboratoire Electronique, Informatique et Image [UMR6306] (Le2i), Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Arts et Métiers (ENSAM), Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement, Laboratoire d'Informatique de Bourgogne [Dijon] (LIB), Université de Bourgogne (UB), Université de Bourgogne (UB)-École Nationale Supérieure d'Arts et Métiers (ENSAM), and HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique (CNRS)
Subjects: Data processing, Scope (project management), Computer science, business.industry, [INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS], [INFO.INFO-LO]Computer Science [cs]/Logic in Computer Science [cs.LO], 02 engineering and technology, Track (rail transport), Data science, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Trajectory, Global Positioning System, 020201 artificial intelligence & image processing, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [ INFO.INFO-LO ] Computer Science [cs]/Logic in Computer Science [cs.LO], Mobile telephony, Safety management systems, Raw data, business, ComputingMilieux_MISCELLANEOUS, [ INFO.INFO-DS ] Computer Science [cs]/Data Structures and Algorithms [cs.DS]
Abstract: Working on a construction site is always risky because of its dynamic nature. Despite numerous efforts to reduce fatalities on construction sites, fatal accidents continue to occur. The advancements in location acquisition and mobile communication techniques offer various means to monitor construction sites using mobility data. Information derived from such data offers tremendous opportunities to track and analyze the mobility of moving objects, that can contributes to improve safety management systems. However, such systems requires preprocessed positioning data of moving objects as raw data captured from location acquisition devices such as Global Positioning System (GPS) device is generally available as discrete points and do not hold enough information to understand the mobility. In this article, we have conducted a review of applications that use mobility data known as trajectories. After a detailed literature review, an application of trajectories carrying spatio-temporal information for worker safety on construction sites is discussed. The application collects GPS data and reconstructs workers' trajectories using different data processing algorithms. Once trajectory data is cleaned and processed, it can further be enriched with semantic and contextual information to enable the desired interpretation of workers' movements on construction sites and ultimately attempts to improve work zone safety by reducing fatalities. However, the scope of this paper is kept limited to data processing of GPS trajectories.
Published: 2017
Full Text: View/download PDF

46. Études et développement de diagrammes de décision linéaires

Author: Ressouche , Annie, Gaffé , Daniel, Havayarimana , Dorine, Spatio-Temporal Activity Recognition Systems ( STARS ), Inria Sophia Antipolis - Méditerranée ( CRISAM ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), Laboratoire d'Electronique, Antennes et Télécommunications ( LEAT ), Centre National de la Recherche Scientifique ( CNRS ) -Université Nice Sophia Antipolis ( UNS ), Université Côte d'Azur ( UCA ) -Université Côte d'Azur ( UCA ), Université Nice Sophia Antipolis ( UNS ), Université Côte d'Azur ( UCA ), UNSA, Annie Ressouche, Daniel Gaffé, Spatio-Temporal Activity Recognition Systems (STARS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Laboratoire d'Electronique, Antennes et Télécommunications (LEAT), Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA), Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS), and Université Nice Sophia Antipolis (... - 2019) (UNS)
Subjects: [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: National audience; Model verification, more commonly known as Model Checking, is a concept basedon an automatic formal verification approach of temporal properties on reactive systems.INRIA in collaboration with LEAT developed CLEM, a modeling and propertyverification tool, based on a state representation in finite automata generated automaticallyusing binary decisions diagrams. From an evolutionary point of view, thework carried out during this internship was to develop the library of linear decisionsdiagrams, we focused on the implementation of new reduction methods in cases of"Imply High" and "Imply Low" case. The objective of this work is to develop theverification part of CLEM by replacing the representation of the fundamental valuesusing binary decisions diagrams(BDDs) with linear decisions diagrams(LDDs) whichwill allow us to represent the states by integer values instead of signals which arenot comparable among themselves. This new library, once implemented on CLEM,will make checks of finer models and, we hope, will make it more powerful.; La vérification de modèle, plus communément appelé Model Checking, est un conceptbasé sur une approche automatique de vérification formelles des propriétés temporellessur des systèmes réactifs. INRIA en collaboration avec le LEAT ont développéCLEM, un outil de modélisation et de vérification de propriétés, s’appuyant sur unereprésentation d’état en automates finis générés automatiquement et représentés pardes Diagrammes de Décisions Binaires. Dans une optique d’évolution, le travaileffectué durant ce stage a été de développer la bibliothèque de diagramme de décisionlinéaire, nous nous sommes concentrés sur l’inclusion de nouvelles méthodes deréduction dans les cas d’implication forte et faible. L’objectif de ce travail est de développerla partie vérification de CLEM en remplaçant la représentation actuelle desvaleurs fondamentales qui utilisent des diagrammes de décisions binaires(BDDs) parles diagrammes de décisions linéaires(LDDs) ce qui nous permettrait de représenterles états par des valeurs entières et non par des signaux non comparables entre eux.Cette nouvelle bibliothèque de LDDs, une fois implémentée sur CLEM, permettrade faire des vérifications de modèles plus fines et, potentiellement, le rendra plusperformant.
Published: 2017

47. Paris and Stanford at EPE 2017: Downstream Evaluation of Graph-based Dependency Representations

Author: Schuster, Sebastian, Villemonte de La Clergerie, Éric, Candito, Marie, Sagot, Benoît, Manning, Christopher, Seddah, Djamé, Department of Linguistics [Stanford], Stanford University, Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Laboratoire de Linguistique Formelle (LLF UMR7110), Université Paris Diderot - Paris 7 (UPD7)-Centre National de la Recherche Scientifique (CNRS), Computer Science Department [Stanford], Université Paris-Sorbonne (UP4), Goodan Family Graduate Fellowship, ANR-16-CE33-0021,PARSITI,Analyser l'impossible, Traduire l'improbable(2016), ANR-15-CE38-0011,SoSweet,Une sociolinguistique de Twitter : liens sociaux et variations linguistiques(2015), ANR-11-IDEX-0005,EFL,Empirical Foundations of Linguistics : data, methods, models(2011), Stanford University [Stanford], Centre National de la Recherche Scientifique (CNRS)-Université Paris Diderot - Paris 7 (UPD7), Department of Computer Science [Stanford], ANR-11-IDEX-0005-02/10-LABX-0083,EFL,Empirical Foundations of Linguistics : data, methods, models(2011), Automatic Language Modelling and ANAlysis & Computational Humanities ( ALMAnaCH ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), Laboratoire de Linguistique Formelle ( LLF ), Université Paris Diderot - Paris 7 ( UPD7 ) -Centre National de la Recherche Scientifique ( CNRS ), Université Paris-Sorbonne ( UP4 ), ANR-16-CE33-0021,Parsiti,Parsing the Improbable : Translating the Improbable, ANR-15-CE38-0011-03,SoSweet,A Sociolinguistics of Twitter: Social Networks and Linguistic Variations, ANR-11-IDEX-0005-02/10-LABX-0083,EFL,Empirical Foundations of Linguistics : data, methods, models ( 2011 ), and ANR-11-IDEX-0005,USPC,Université Sorbonne Paris Cité(2011)
Subjects: [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: International audience; We describe the STANFORD-PARIS and PARIS-STANFORD submissions to the 2017 Extrinsic Parser Evaluation (EPE) Shared Task. The purpose of this shared task was to evaluate dependency graphs on three downstream tasks. Through our submissions, we evaluated the usability of several representations derived from English Universal Dependencies (UD), as well as the Stanford Dependencies (SD), Predicate Argument Structure (PAS), and DM representations. We further compared two parsing strategies: Directly parsing to graph-based dependency representations and a two-stage process of first parsing to surface syntax trees and then applying rule-based augmentations to obtain the final graphs. Overall, our systems performed very well and our submissions ranked first and third. In our analysis, we find that the two-stage parsing process leads to better downstream performance, and that enhanced UD, a graph-based representation, consistently outperforms basic UD, a strict surface syntax representation, suggesting an advantage of enriched representations for downstream tasks.
Published: 2017

48. Improving neural tagging with lexical information

Author: Sagot , Benoît, Martínez Alonso , Héctor, Automatic Language Modelling and ANAlysis & Computational Humanities ( ALMAnaCH ), Inria de Paris, Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), RAPID VerDI, ANR-15-CE38-0011-03,SoSweet,A Sociolinguistics of Twitter: Social Networks and Linguistic Variations, ANR-16-CE33-0021,Parsiti,Parsing the Improbable : Translating the Improbable, Sagot, Benoît, Une sociolinguistique de Twitter : liens sociaux et variations linguistiques - - SoSweet2015 - ANR-15-CE38-0011 - AAPG2015 - VALID, Analyser l'impossible, Traduire l'improbable - - PARSITI2016 - ANR-16-CE33-0021 - AAPG2016 - VALID, Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), ANR-15-CE38-0011,SoSweet,Une sociolinguistique de Twitter : liens sociaux et variations linguistiques(2015), and ANR-16-CE33-0021,PARSITI,Analyser l'impossible, Traduire l'improbable(2016)
Subjects: [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: International audience; Neural part-of-speech tagging has achieved competitive results with the incorporation of character-based and pre-trained word embeddings. In this paper, we show that a state-of-the-art bi-LSTM tagger can benefit from using information from morphosyntactic lexicons as additional input. The tagger, trained on several dozen languages, shows a consistent, average improvement when using lexical information, even when also using character-based embeddings, thus showing the complementarity of the different sources of lexical information. The improvements are particularly important for the smaller datasets.
Published: 2017

49. Extracting an Etymological Database from Wiktionary

Author: Sagot, Benoît, Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), ANR-16-CE38-0010,PROFITEROLE,Modélisation de l'évolution de la langue à partir de textes d'ancien français instrumentés(2016), Automatic Language Modelling and ANAlysis & Computational Humanities ( ALMAnaCH ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), ANR-16-CE38-0010,Profiterole,Modélisation de l'évolution de la langue à partir de textes d'ancien français instrumentés, Sagot, Benoît, and Modélisation de l'évolution de la langue à partir de textes d'ancien français instrumentés - - PROFITEROLE2016 - ANR-16-CE38-0010 - AAPG2016 - VALID
Subjects: [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], etymology, [ SHS.LANGUE ] Humanities and Social Sciences/Linguistics, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], Lexical resource development, Wiktionary, [SHS.LANGUE]Humanities and Social Sciences/Linguistics, [SHS.LANGUE] Humanities and Social Sciences/Linguistics, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract: International audience; Electronic lexical resources almost never contain etymological information. The availability of such information, if properly formalised, could open up the possibility of developing automatic tools targeted towards historical and comparative linguistics, as well as significantly improving the automatic processing of ancient languages. We describe here the process we implemented for extracting etymological data from the etymological notices found in Wiktionary. We have produced a multilingual database of nearly one million lexemes and a database of more than half a million etymological relations between lexemes.
Published: 2017

50. Speeding up corpus development for linguistic research: language documentation and acquisition in Romansh Tuatschin

Author: Géraldine Walther, Benoît Sagot, Institut für Vergleichende Sprachwissenschaft, University of Zürich [Zürich] ( UZH ), Automatic Language Modelling and ANAlysis & Computational Humanities ( ALMAnaCH ), Inria de Paris, Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ), Swiss National Science Foundation project number 159544 'The morphosyntax of agreement in Tuatschin: acquisition and contact', European Project : 654119,H2020 Pilier Excellent Science,H2020-INFRADEV-1-2014-1,PARTHENOS ( 2015 ), Universität Zürich [Zürich] = University of Zurich (UZH), Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), and European Project: 654119,H2020 Pilier Excellent Science,H2020-INFRADEV-1-2014-1,PARTHENOS(2015)
Subjects: Computer science, Context (language use), 02 engineering and technology, Language documentation, computer.software_genre, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Resource development, 0202 electrical engineering, electronic engineering, information engineering, [ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL], [SHS.LANGUE]Humanities and Social Sciences/Linguistics, Noisy data, Reliability (statistics), Romansh Tuatschin, Natural Language Processing, 060201 languages & linguistics, business.industry, Corpus annotation and tagging, 06 humanities and the arts, Language documentation methodology, Language acquisition, Variety (linguistics), Linguistics, 0602 languages and literature, [ SHS.LANGUE ] Humanities and Social Sciences/Linguistics, 020201 artificial intelligence & image processing, Noise (video), Artificial intelligence, business, computer, Natural language processing
Abstract: International audience; In this paper, we present ongoing work for developing language resources and basic NLP tools for an undocumented variety of Romansh, in the context of a language documentation and language acquisition project. Our tools are designed to improve the speed and reliability of corpus annotations for noisy data involving large amounts of code-switching, occurrences of child speech and orthographic noise. Being able to increase the efficiency of language resource development for language documentation and acquisition research also constitutes a step towards solving the data sparsity issues with which researchers have been struggling.
Published: 2017
Full Text: View/download PDF

Catalog

Books, media, physical & digital resources

See catalog results

Searchworks

Select search scope, currently: Articles Catalog books, media & more in Jio Institute collections Articles journal articles & other e-resources

Search

Search Constraints

Refine your results

Search Limiters

Topic

Publication Year Range

Language

Publication Type

Journal

Database

Publisher

234 results on '"[ INFO.INFO-CL ] Computer Science [cs]/Computation and Language [cs.CL]"'

Search Results

Catalog

Select search scope, currently: Articles

Catalog

books, media & more in Jio Institute collections

Articles

journal articles & other e-resources