Search

In this research, we evaluate different approaches for the automatic extraction of hypernym relations from English and Dutch technical text. The detected hypernym relations should enable us to semantically structure automatically obtained term lists from domain- and user-specific data. We investigated three different hypernymy extraction approaches for Dutch and English: a lexico-syntactic pattern-based approach, a distributional model and a morpho-syntactic method. To test the performance of the different approaches on domain-specific data, we collected and manually annotated English and Dutch data from two technical domains, viz. the dredging and financial domain. The experimental results show that especially the morpho-syntactic approach obtains good results for automatic hypernym extraction from technical and domain-specific texts.

This paper introduces the Aix Map Task corpus, a corpus of audio and video recordings of task-oriented dialogues. It was modelled afterthe original HCRC Map Task corpus. Lexical material was designed for the analysis of speech and prosody, as described in Astésanoet al. (2007). The design of the lexical material, the protocol and some basic quantitative features of the existing corpus are presented.The corpus was collected under two communicative conditions, one audio-only condition and one face-to-face condition. The recordingstook place in a studio and a sound attenuated booth respectively, with head-set microphones (and in the face-to-face condition with twovideo cameras). The recordings have been segmented into Inter-Pausal-Units and transcribed using transcription conventions containingactual productions and canonical forms of what was said. It is made publicly available online.

Both sentiment and event factuality are fundamental information levels for our understanding of events mentioned in news texts. Most research so far has focused on either modeling opinions or factuality. In this paper, we propose a model that combines the two for the extraction and interpretation of perspectives on events. By doing so, we can explain the way people perceive changes in (their belief of) the world as a function of their fears of changes to the bad or their hopes of changes to the good. This study seeks to examine the effectiveness of this approach by applying factuality annotations, based on FactBank, on top of the MPQA Corpus, a corpus containing news texts annotated for sentiments and other private states. Our findings suggest that this approach can be valuable for the understanding of perspectives, but that there is still some work to do on the refinement of the integration.

This paper presents the linguistic analysis tools and its infrastructure developed within the XLike project. The main goal of the implemented tools is to provide a set of functionalities for supporting some of the main objectives of XLike, such as enabling cross-lingual services for publishers, media monitoring or developing new business intelligence applications. The services cover seven major and minor languages: English, German, Spanish, Chinese, Catalan, Slovenian, and Croatian. These analyzers are provided as web services following a lightweight SOA architecture approach, and they are publically callable and are catalogued in META-SHARE

In this paper we present a Dutch and English dataset that can serve as a gold standard for evaluating text normalization approaches. With the combination of text messages, message board posts and tweets, these datasets represent a variety of user generated content. All data was manually normalized to their standard form using newly-developed guidelines. We perform automatic lexical normalization experiments on these datasets using statistical machine translation techniques. We focus on both the word and character level and find that we can improve the BLEU score with ca. 20% for both languages. In order for this user generated content data to be released publicly to the research community some issues first need to be resolved. These are discussed in closer detail by focussing on the current legislation and by investigating previous similar data collection projects. With this discussion we hope to shed some light on various difficulties researchers are facing when trying to share social media data.

We present the current state of development of the Croatian Dependency Treebank – with special empahsis on adapting the Prague Dependency Treebank formalism to Croatian language specifics – and illustrate its possible applications in an experiment with dependency parsing using MaltParser. The treebank currently contains approximately 2870 sentences, out of which the 2699 sentences and 66930 tokens were used in this experiment. Three linear-time projective algorithms implemented by the MaltParser system – Nivre eager, Nivre standard and stack projective – running on default settings were used in the experiment. The highest performing system, implementing the Nivre eager algorithm, scored (LAS 71.31 UAS 80.93 LA 83.87) within our experiment setup. The results obtained serve as an illustration of treebank’s usefulness in natural language processing research and as a baseline for further research in dependency parsing of Croatian.

How do people behave in their everyday information seeking tasks, which often involve Wikipedia? Are there systems which can help them, or do a similar job? In this paper we describe Págico, an evaluation contest with the main purpose of fostering research in these topics. We describe its motivation, the collection of documents created, the evaluation setup, the topics chosen and their choice, the par- ticipation, as well as the measures used for evaluation and the gathered resources. The task—between information retrieval and question answering—can be further described as answering questions related to Portuguese-speaking culture in the Portuguese Wikipedia, in a number of different themes and geographic and temporal angles. This initiative allowed us to create interesting datasets and perform some assessment of Wikipedia, while also improving a public-domain open-source system for further wikipedia-based evaluations. In the pa- per, we provide examples of questions, we report the results obtained by the participants, and provide some discussion on complex issues.

The domain of architecture, engineering and construction (AEC) has experienced significant improvements with the advent of building information modelling (BIM) applications, which allow AEC specialists to model all information concerning a building design into one three-dimensional building model. Much of these improvements are however generated by the mere availability of such an environment, whereas many more improvements were expected by achieving an appropriate interoperability of information. We are investigating why such an interoperability is not reached fully and consider the semantic web as an alternative approach to reach the targeted interoperability. In this paper, an AEC description framework based on semantic web technology is presented and compared to the BIM approach, after which we indicate how it might solve the issue of interoperability more appropriately. Our evaluation of this investigation indicates the semantic web approach as a valid alternative approach, although considerably more research is needed to show it capable of providing the targeted interoperability of information in the AEC domain.

International audience; In this paper we address the problem of defining standards for discourse-level text annotation. We propose the URS metamodel as a common formalism in which existing models and models-to-be could be (re)formulated. This meta-model should permit to create standard annotated corpora in a consistent way, i.e. allowing alignment of various discourse structures. We also present the annotation platform Glozz supporting the URS metamodel. The approach is illustrated by an on-going campaign devoted to both topical and rhetorical structure of texts.

In this paper we present the semantic analysis module in F-logic as a part of a Croatian spoken dialog system developed for a limited domain of weather forecasts. Semantic analysis is implemented as an information extraction technique using the F-logic formalism. F-logic (Frame Logic) is a logic formalism with a second order syntax and an object-oriented approach. Semantic knowledge is captured through semantic categories, a semantic dictionary and output frames represented in F-logic. The developed semantic analysis is conducted in three phases. In the first phase the main semantic context for the input text is determined. In the second phase semantic units are analysed and knowledge slots in the database are filled. Since some slots of input data are missing in the third phase, incomplete data are updated with missing values. The semantic analysis is evaluated with 3 months period weather data in terms of frame rates and slot error rates. The rules for semantic analysis are defined in the F-logic language and implemented using the FLORA-2 system.

Digital media facilitates tight integration of multi-modal information and networking allows this richly textured knowledge to be shared. We present the system we have developed in the MIAKT (Medical Imaging with Advanced Knowledge Technologies) project that provides knowledge management, and facilities for semantic annotations on mammographic images in the context of clinical and histopathological information. This paper also describes the novel generic architecture we have built on semantic web technologies to facilitate the annotation of images with ontological concepts, and storage thereof, in any domain. Functionality of a specific domain application is provided through web-resources, which are called through a task invocation system which abstracts the actual service implementation from the client application implementation.

In this article, we lay out the basic ideas and principles of the project Framing Situations in the Dutch Language. We provide our first results of data acquisition, together with the first data release. We introduce the notion of cross-lingual referential corpora. These corpora consist of texts that make reference to exactly the same incidents. The referential grounding allows us to analyze the framing of these incidents in different languages and across different texts. During the project, we will use the automatically generated data to study linguistic framing as a phenomenon, build framing resources such as lexicons and corpora. We expect to capture larger variation in framing compared to traditional approaches for building such resources. Our first data release, which contains structured data about a large number of incidents and reference texts, can be found at http://dutchframenet.nl/data-releases/.

Research from communication science has shown that stereotypical ideas are often reflected in language use. Media coverage of different groups in society influences the perception people have about these groups and even increases distrust and polarization among different groups. Investigating the forms of (especially subtle) stereotyping can raise awareness to journalists and help prevent reinforcing oppositions between groups in society. Conducting large-scale, deep investigations to determine whether we are faced with stereotyping is time-consuming and costly. We propose to tackle this challenges through the means of microportraits: an impression of a target group or individual conveyed in a single text. We introduce the first system implementation for Dutch and show that microportraits allow social scientists to explore various dimensions of stereotyping. We explore the possibilities provided by microportraits by investigating stereotyping of Muslims in the Dutch media. Our (preliminary) results show that microportraits provide more detailed insights into stereotyping compared to more basic models such as word clouds.

In this work we address the processing of negation in Spanish. We first present a machine learning system that processes negation in Spanish. Specifically, we focus on two tasks: i) negation cue detection and ii) scope identification. The corpus used in the experimental framework is the SFU ReviewSP-NEG. The results for cue detection outperform state-of-the-art results, whereas for scope detection this is the first system that performs the task for Spanish. Moreover, we provide a qualitative error analysis aimed at understanding the limitations of the system and showing which negation cues and scopes are straightforward to predict automatically, and which ones are challenging.

This article presents the current outcomes of the CURLICAT CEF Telecom project, which aims to collect and deeply annotate a set of large corpora from selected domains. The CURLICAT corpus includes 7 monolingual corpora (Bulgarian, Croatian, Hungarian, Polish, Romanian, Slovak and Slovenian) containing selected samples from respective national corpora. These corpora are automatically tokenized, lemmatized and morphologically analysed and the named entities annotated. The annotations are uniformly provided for each language specific corpus while the common metadata schema is harmonised across the languages. Additionally, the corpora are annotated for IATE terms in all languages. The file format is CoNLL-U Plus format, containing the ten columns specific to the CoNLL-U format and three extra columns specific to our corpora as defined by Varádi et al. (2020). The CURLICAT corpora represent a rich and valuable source not just for training NMT models, but also for further studies and developments in machine learning, cross- lingual terminological data extraction and classification.

This paper presents FISKMÖ, a project that focuses on the development of resources and tools for cross-linguistic research and machine translation between Finnish and Swedish. The goal of the project is the compilation of a massive parallel corpus out of translated material collected from web sources, public and private organisations and language service providers in Finland with its two official languages. The project also aims at the development of open and freely accessible translation services for those two languages for the general purpose and for domain-specific use. We have released new data sets with over 3 million translation units, a benchmark test set for MT development, pre-trained neural MT models with high coverage and competitive performance and a self-contained MT plugin for a popular CAT tool. The latter enables offline translation without dependencies on external services making it possible to work with highly sensitive data without compromising security concerns. In this paper, we investigate paraphrase generation in the colloquial domain. We use state-of-the-art neural machine translation models trained on the Opusparcus corpus to generate paraphrases in six languages: German, English, Finnish, French, Russian, and Swedish. We perform experiments to understand how data selection and filtering for diverse paraphrase pairs affects the generated paraphrases. We compare two different model architectures, an RNN and a Transformer model, and find that the Transformer does not generally outperform the RNN. We also conduct human evaluation on five of the six languages and compare the results to the automatic evaluation metrics BLEU and the recently proposed BERTScore. The results advance our understanding of the trade-offs between the quality and novelty of generated paraphrases, affected by the data selection method. In addition, our comparison of the evaluation methods shows that while BLEU correlates well with human judgments at the corpus level, BERTScore outperforms BLEU in both corpus and sentence-level evaluation.

This paper describes the building of the first Spanish-Croatian unidirectional parallel corpus, which has been constructed at the Faculty of Humanities and Social Sciences of the University of Zagreb. The corpus is comprised of eleven Spanish novels and their translations to Croatian done by six different professional translators. All the texts were published between 1999 and 2012. The corpus has more than 2 Mw, with approximately 1 Mw for each language. It was automatically sentence segmented and aligned, as well as manually post-corrected, and contains 71, 778 translation units. In order to protect the copyright and to make the corpus available under permissive CC-BY licence, the aligned translation units are shuffled. This limits the usability of the corpus for research of language units at sentence and lower language levels only. There are two versions of the corpus in TMX format that will be available for download through META-SHARE and CLARIN ERIC infrastructure. The former contains plain TMX, while the latter is lemmatised and POS-tagged and stored in the aTMX format.

In this work we present a corpus for the evaluation of sensitive information detection approaches that addresses the need for real world sensitive information for empirical studies. Our sentence corpus contains different notions of complex sensitive information that correspond to different aspects of concern in a current trial of the Monsanto company. This paper describes the annotations process, where we both employ human annotators and furthermore create automatically inferred labels regarding technical, legal and informal communication within and with employees of Monsanto, drawing on a classification of documents by lawyers involved in the Monsanto court case. We release corpus of high quality sentences and parse trees with these two types of labels on sentence level. We characterize the sensitive information via several representative sensitive information detection models, in particular both keyword-based (n-gram) approaches and recent deep learning models, namely, recurrent neural networks (LSTM) and recursive neural networks (RecNN). Data and code are made publicly available.

Sentiment classification over Twitter is usually affected by the noisy nature (abbreviations, irregular forms) of tweets data. A popular procedure to reduce the noise of textual data is to remove stopwords by using pre-compiled stopword lists or more sophisticated methods for dynamic stopword identification. However, the effectiveness of removing stopwords in the context of Twitter sentiment classification has been debated in the last few years. In this paper we investigate whether removing stopwords helps or hampers the effectiveness of Twitter sentiment classification methods. To this end, we apply six different stopword identification methods to Twitter data from six different datasets and observe how removing stopwords affects two well-known supervised sentiment classification methods. We assess the impact of removing stopwords by observing fluctuations on the level of data sparsity, the size of the classifier’s feature space and its classification performance. Our results show that using pre-compiled lists of stopwords negatively impacts the performance of Twitter sentiment classification approaches. On the other hand, the dynamic generation of stopword lists, by removing those infrequent terms appearing only once in the corpus, appears to be the optimal method to maintaining a high classification performance while reducing the data sparsity and substantially shrinking the feature space.

This article presents the results of the evaluation campaign of language tools available for fifteen EU-official under-resourced languages. The evaluation was conducted within the MSC ITN CLEOPATRA action that aims at building the cross-lingual event- centric knowledge processing on top of the application of linguistic processing chains (LPCs) for at least 24 EU-official languages. In this campaign, we concentrated on three existing NLP platforms (Stanford CoreNLP, NLP Cube, UDPipe) that all provide models for under-resourced languages and in this first run we covered 15 under- resourced languages for which the models were available. We present the design of the evaluation campaign and present the results as well as discuss them. We considered the difference between reported and our tested results within a single percentage point as being within the limits of acceptable tolerance and thus consider this result as reproducible. However, for a number of languages, the results are below what was reported in the literature, and in some cases, our testing results are even better than the ones reported previously. Particularly problematic was the evaluation of NERC systems. One of the reasons is the absence of universally or cross-lingually applicable named entities classification scheme that would serve the NERC task in different languages analogous to the Universal Dependency scheme in parsing task. To build such a scheme has become one of our the future research directions.

We use synchronized 120 fps motion capture and 50 fps eye tracking data from two native signers to investigate the temporal order in which the dominant hand, the head, the chest and the eyes start producing overt constructed action from regular narration in seven short Finnish Sign Language stories. From the material, we derive a sample of ten instances of regular narration to overt constructed action transfers in ELAN which we then further process and analyze in Matlab. The results indicate that the temporal order of articulators shows both contextual and individual variation but that there are also repeated patterns which are similar across all the analyzed sequences and signers. Most notably, when the discourse strategy changes from regular narration to overt constructed action, the head and the eyes tend to take the leading role, and the chest and the dominant hand tend to start acting last. Consequences of the findings are discussed. peerReviewed

The recent construction of large linguistic treebanks for spoken and written Dutch (e.g. CGN, LASSY, Alpino) has created new and exciting opportunities for the empirical investigation of Dutch syntax and semantics. However, the exploitation of those treebanks requires knowledge of specific data structures and query languages such as XPath. Linguists who are unfamiliar with formal languages are often reluctant towards learning such a language. In order to make treebank querying more attractive for non-technical users we developed GrETEL (Greedy Extraction of Trees for Empirical Linguistics), a query engine in which linguists can use natural language examples as a starting point for searching the Lassy treebank without knowledge about tree representations nor formal query languages. By allowing linguists to search for similar constructions as the example they provide, we hope to bridge the gap between traditional and computational linguistics. Two case studies are conducted to provide a concrete demonstration of the tool. The architecture of the tool is optimised for searching the LASSY treebank, but the approach can be adapted to other treebank lay-outs. ispartof: pages:3161-3167 ispartof: Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC 2012) pages:3161-3167 ispartof: International Conference on Language Resources and Evaluation (LREC) location:Istanbul date:21 May - 27 May 2012 status: published

Named entity recognition (NER) is a knowledge-intensive information extraction task that is used for recognizing textual mentions of entities that belong to a predefined set of categories, such as locations, organizations and time expressions. NER is a challenging, difficult, yet essential preprocessing technology for many natural language processing applications, and particularly crucial for language understanding. NER has been actively explored in academia and in industry especially during the last years due to the advent of social media data. This paper describes the conversion, modeling and adaptation of a Swedish NER system from a hybrid environment, with integrated functionality from various processing components, to the Helsinki Finite-State Transducer Technology (HFST) platform. This new HFST-based NER (HFST-SweNER) is a full-fledged open source implementation that supports a variety of generic named entity types and consists of multiple, reusable resource layers, e.g., various n-gram-based named entity lists (gazetteers).

The paper presents a procedure for generating prefixed verbs in Croatian comprising combinations of one, two or three prefixes. The result of this generation process is a pool of derivationally valid prefixed verbs, although not necessarily occuring in corpora. The statistics of occurences of generated verbs in Croatian National Corpus has been calculated. Further usage of such language resource with generated potential verbs is also suggested, namely, enrichment of Croatian Morphological Lexicon, Croatian Wordnet and CROVALLEX.

This paper presents the German Twitter section of a large (2 billion word) bilingual Social Media corpus for Hate Speech research, discussing the compilation, pseudonymization and grammatical annotation of the corpus, as well as special linguistic features and peculiarities encountered in the data. Among other things, compounding, accidental and intentional orthographic variation, gendering and the use of emoticons/emojis are addressed in a genre-specific fashion. We present the different layers of linguistic annotation (morphosyntactic, dependencies and semantic types) and explain how a general parser (GerGram) can be made to work on Social Media data, pointing out necessary adaptations and extensions. In an evaluation run on a random cross-section of tweets, the modified parser achieved F-scores of 97% for morphology (fine-grained POS) and 92% for syntax (labeled attachment score). Predictably, performance was twice as good in tweets with standard orthography than in tweets with spelling/casing irregularities or lack of sentence separation, the effect being more marked for morphology than for syntax.

Following decades of massive digitization, an unprecedented amount of historical document facsimiles can now be retrieved and accessed via cultural heritage online portals. If this represents a huge step forward in terms of preservation and accessibility, the next fundamental challenge-- and real promise of digitization-- is to exploit the contents of these digital assets, and therefore to adapt and develop appropriate language technologies to search and retrieve information from this `Big Data of the Past'. Yet, the application of text processing tools on historical documents in general, and historical newspapers in particular, poses new challenges, and crucially requires appropriate language resources. In this context, this paper presents a collection of historical newspaper data sets composed of text and image resources, curated and published within the context of the `impresso - Media Monitoring of the Past' project. With corpora, benchmarks, semantic annotations and language models in French, German and Luxembourgish covering ca. 200 years, the objective of the impresso resource collection is to contribute to historical language resources, and thereby strengthen the robustness of approaches to non-standard inputs and foster efficient processing of historical documents.

The limited availability of in-domain training data is a major issue in the training of application-specific neural machine translation models. Professional outsourcing of bilingual data collections is costly and often not feasible. In this paper we analyze the influence of using crowdsourcing as a scalable way to obtain translations of target in-domain data having in mind that the translations can be of a lower quality. We apply crowdsourcing with carefully designed quality controls to create parallel corpora for the educational domain by collecting translations of texts from MOOCs from English to eleven languages, which we then use to fine-tune neural machine translation models previously trained on general-domain data. The results from our research indicate that crowdsourced data collected with proper quality controls consistently yields performance gains over general-domain baseline systems, and systems fine-tuned with pre-existing in-domain corpora.

Topological Data Analysis (TDA) focuses on the inherent shape of (spatial) data. As such, it may provide useful methods to explore spatial representations of linguistic data (embeddings) which have become central in NLP. In this paper we aim to introduce TDA to researchers in language technology. We use TDA to represent document structure as so-called story trees. Story trees are hierarchical representations created from semantic vector representations of sentences via persistent homology. They can be used to identify and clearly visualize prominent components of a story line. We showcase their potential by using story trees to create extractive summaries for news stories.

12th Edition of its Language Resources and Evaluation Conference was cancelled due to Covid 19 pandemic. This paper introduces OpusTools, a package for downloading and processing parallel corpora included in the OPUS corpus collection. The package implements tools for accessing compressed data in their archived release format and make it possible to easily convert between common formats. OpusTools also includes tools for language identification and data filtering as well as tools for importing data from various sources into the OPUS format. We show the use of these tools in parallel corpus creation and data diagnostics. The latter is especially useful for the identification of potential problems and errors in the extensive data set. Using these tools, we can now monitor the validity of data sets and improve the overall quality and consitency of the data collection.

In the present paper, we describe a large corpus of eye movement data, collected during natural reading of a human translation and a machine translation of a full novel. This data set, called GECO-MT (Ghent Eye-tracking Corpus of Machine Translation) expands upon an earlier corpus called GECO (Ghent Eye-tracking Corpus) by Cop et al. (2017). The eye movement data in GECO-MT will be used in future research to investigate the effect of machine translation on the reading process and the effects of various error types on reading. In this article, we describe in detail the materials and data collection procedure of GECO-MT. Extensive information on the language proficiency of our participants is given, as well as a comparison with the participants of the original GECO. We investigate the distribution of a selection of important eye movement variables and explore the possibilities for future analyses of the data. GECO-MT is freely available at https://www.lt3.ugent.be/resources/geco-mt.

In this paper we present S-pot, a benchmark setting for evaluating the performance of automatic spotting of signs in continuous sign language videos. The benchmark includes 5539 video files of Finnish Sign Language, ground truth sign spotting results, a tool for assessing the spottings against the ground truth, and a repository for storing information on the results. In addition we will make our sign detection system and results made with it publicly available as a baseline for comparison and further developments. peerReviewed

We present a software toolkit called SLMotion which provides a framework for automatic and semiautomatic analysis, feature extraction and annotation of individual sign language videos, and which can easily be adapted to batch processing of entire sign language corpora. The program follows a modular design, and exposes a Numpy-compatible Python application programming interface that makes it easy and convenient to extend its functionality through scripting. The program includes support for exporting the annotations in ELAN format. The program is released as free software, and is available for GNU/Linux and MacOS platforms. peerReviewed

This paper reports on an approach and experiments to automatically build a cross-lingual multi-word entity resource. Starting from a collection of millions of acronym/expansion pairs for 22 languages where expansion variants were grouped into monolingual clusters, we experiment with several aggregation strategies to link these clusters across languages. Aggregation strategies make use of string similarity distances and translation probabilities and they are based on vector space and graph representations. The accuracy of the approach is evaluated against Wikipedia's redirection and cross-lingual linking tables. The resulting multi-word entity resource contains 64,000 multi-word entities with unique identifiers and their 600,000 multilingual lexical variants. We intend to make this new resource publicly available.