Search

Your search keyword '"Roe, Glenn"' showing total 112 results
Start Over Author "Roe, Glenn"
112 results on '"Roe, Glenn"'

8. Mapping spatial named entities from noisy OCR output: Epimetheus from OCR to map

Author

Koudoro-Parfait, Caroline, Alrahabi, Motasem, Dupont, Yoann, Lejeune, Gaël, Roe, Glenn, Scholger, Walter, Vogeler, Georg, Tasovac, Toma, Baillot, Anne, Raunig, Elisabeth, Scholger, Martina, Steiner, Elisabeth, Centre for Information Modelling, and Helling, Patrick

Subjects
Paper, spatial & spatio-temporal analysis, Statistics, Geography and geo-humanities, optical character recognition and handwriting recognition, Named Entity Recognition, Short Presentation, Literary studies, Cluster, Map, FOS: Mathematics, modeling and visualization, natural language processing, artificial intelligence and machine learning, Optical character recognition
Abstract

This contribution presents the difficulties encountered and methods to overcome them when using ready-to-use tools for the elaboration of a processing chain going from OCR to NER and then to the cartographic representation of spaces mentioned in literary texts.

Published
2023
Full Text
View/download PDF

9. Pandore: a toolbox for digital humanities text-based workflows

Author

Alrahabi, Motasem, Fedchenko, Valentina, Petkovic, Ljudmila, Roe, Glenn, Scholger, Walter, Vogeler, Georg, Tasovac, Toma, Baillot, Anne, Raunig, Elisabeth, Scholger, Martina, Steiner, Elisabeth, Centre for Information Modelling, and Helling, Patrick

Subjects
Paper, OCR/HTR, Named Entities Recognition, Mapping, text mining and analysis, Humanities computing, Text annotation, optical character recognition and handwriting recognition, Poster, natural language processing, Toolbox, artificial intelligence and machine learning
Abstract

We present Pandore, an online toolbox for pre- and post-processing of textual data. This freely accessible platform allows humanities students and researchers, with little or no prior knowledge of computer programming, to perform a series of important and recurrent tasks crucial for the editing, enrichment and mining of digital texts.

Published
2023
Full Text
View/download PDF

10. Using text summarization models to improve digital reading of scientific papers

Author

Mastrobattista, Ludovica, Alrahabi, Motasem, Fedchenko, Valentina, Jomaa, Oussama, Gawley, James, Cordova, Johanna, Roe, Glenn, Scholger, Walter, Vogeler, Georg, Tasovac, Toma, Baillot, Anne, Raunig, Elisabeth, Scholger, Martina, Steiner, Elisabeth, Centre for Information Modelling, and Helling, Patrick

Subjects
Paper, keyword extraction, Humanities computing, qualitative evaluation, text summarization, Interface design, Poster, digital reading, and analysis, artificial intelligence and machine learning, development
Abstract

This paper presents an evaluation and comparison of three state-of-the-art models for text summarization, and proposes a new digital reading interface designed for neophyte users to exploit these models, as well as automatic keyword extraction, with little or no programming experience.

Published
2023
Full Text
View/download PDF

11. Enlightenment Inflluencers: Networks of Text Reuse in 18th-century France

Author

Roe, Glenn, Fedchenko, Valentina, Nicolosi, Dario, Scholger, Walter, Vogeler, Georg, Tasovac, Toma, Baillot, Anne, Raunig, Elisabeth, Scholger, Martina, Steiner, Elisabeth, Centre for Information Modelling, and Helling, Patrick

Subjects
Paper, influence, History, Long Presentation, network analysis and graphs theory and application, FOS: Philosophy, ethics and religion, intertextuality, Philosophy, cultural analytics, Literary studies, text mining and analysis, text reuse, enlightenment, network analysis
Abstract

The ERC-funded ModERN project is investigating 18th-century authorship practices using data-rich computational techniques to examine the digital archive of the Enlightenment period. This paper explores the use of new large-scale text reuse detection and network analysis to identify intertextual 'influencers' in a large heterogeneous collection of 18th-century French texts.

Published
2023
Full Text
View/download PDF

12. Circulation du discours médical de Jean-Martin Charcot

Author

Petkovic, Ljudmila, Alrahabi, Motasem, Roe, Glenn, Sorbonne Université (SU), Observatoire des textes, des idées et des corpus (ObTIC), Bibliothèque nationale de France (BnF)-Centre d’étude de la langue et des littératures françaises (CELLF), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)- Sorbonne Center for Artificial Intelligence (SCAI), Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Université de Technologie de Compiègne (UTC)-Institut National de Recherche en Informatique et en Automatique (Inria)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut Européen d'administration des Affaires (INSEAD)-Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Université de Technologie de Compiègne (UTC)-Institut National de Recherche en Informatique et en Automatique (Inria)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut Européen d'administration des Affaires (INSEAD), and Association francophone des humanités numériques

Subjects
[SHS.HISPHILSO]Humanities and Social Sciences/History, Philosophy and Sociology of Sciences, [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, History of medicine, Histoire de la médecine, Concepts circulation, Circulation de concepts, Jean-Martin Charcot
Abstract

International audience; Cette proposition de communication se veut une première réflexion liée à la mesure du degré d'intertextualité entre Jean-Martin Charcot (1825-1893) et son réseau scientifique et artistique au prisme des humanités numériques. L'approche consiste à comparer les textes écrits par Charcot avec ceux de ses collaborateurs et successeurs, via les concepts-clés liés à son discours scientifique. Les expériences menées sur la circulation des concepts d'un corpus à l'autre se base sur les mesures TF-IDF, BM-25 et BERT, et les résultats obtenus semblent probants. Au-delà du cas de Charcot, ce travail vise à établir un protocole permettant d'appréhender la circulation de concepts de manière automatisée.

Published
2023

13. Impact of automatic OCR/HTR correction on named entity recognition in noisy corpora

Author

Petkovic, Ljudmila, Alrahabi, Motasem, Roe, Glenn, Sorbonne Université (SU), Observatoire des textes, des idées et des corpus (ObTIC), Bibliothèque nationale de France (BnF)-Centre d’étude de la langue et des littératures françaises (CELLF), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)- Sorbonne Center for Artificial Intelligence (SCAI), Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Université de Technologie de Compiègne (UTC)-Institut National de Recherche en Informatique et en Automatique (Inria)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut Européen d'administration des Affaires (INSEAD)-Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Université de Technologie de Compiègne (UTC)-Institut National de Recherche en Informatique et en Automatique (Inria)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut Européen d'administration des Affaires (INSEAD), Centre d’étude de la langue et des littératures françaises (CELLF), and Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, OCR, traitement automatique des langues, Automatic Spelling Correction, reconnaissance d’entités nommées, documents d’archives numérisées, Digitized Archival Documents, [SCCO.LING]Cognitive science/Linguistics, Named Entity Recognition, Natural Language Processing, correction d'orthographe automatique
Abstract

International audience; We present an experiment conducted on the automatic spelling correction of texts resulting from optical character recognition (OCR), with the objective of measuring the impact of corrections on an information extraction task. Using a sample of OCRed digitized archival documents, we applied a named entity recognition system before and after orthographic correction. The results obtained showed that the spelling checker improves certain automatic natural language processing tasks. An extension of the proposed approach by re-training on a larger corpus is also presented to further optimize the results obtained.; Nous présentons une expérience menée sur la correction d’orthographe automatique de textes issus de la reconnaissance optique des caractères (OCR), dans l’objectif de mesurer l’impact de la correction sur une tâche d’extraction d’informations. À partir d'un échantillon de documents d’archives numérisées (océrisées), nous avons appliqué un système de reconnaissance d’entités nommées avant et après une correction d’orthographe. Les résultats obtenus ont montré que le correcteur orthographique permet d’améliorer certaines tâches du traitement automatique du langage naturel. Une extension de l’approche proposée par un ré-entraînement sur un plus grand corpus est également présentée pour optimiser davantage les résultats obtenus.

Published
2022
Full Text
View/download PDF

14. Literature Students Confronted with Digital Humanities: A Classroom Experiment

Author

Alrahabi, Motasem, Roe, Glenn, Bordry, Marguerite, Koskas, Camille, Gawley, James, Observatoire des textes, des idées et des corpus (ObTIC), Bibliothèque nationale de France (BnF)-Centre d’étude de la langue et des littératures françaises (CELLF), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)- Sorbonne Center for Artificial Intelligence (SCAI), Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Université de Technologie de Compiègne (UTC)-Institut National de Recherche en Informatique et en Automatique (Inria)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut Européen d'administration des Affaires (INSEAD)-Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Université de Technologie de Compiègne (UTC)-Institut National de Recherche en Informatique et en Automatique (Inria)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut Européen d'administration des Affaires (INSEAD), Centre d’étude de la langue et des littératures françaises (CELLF), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Équipe Littérature et Culture italiennes (ELCI), and Sorbonne Université (SU)

Subjects
[SHS]Humanities and Social Sciences
Abstract

International audience; This paper presents an experiment in digital humanities pedagogy enacted as part of a Master course at Sorbonne Université for students of French literature and language with little to no digital research experience. For the final evaluation, students worked in groups on projects that allowed them to deploy the skills and expertise acquired during the course. Students evaluated concretely the potential benefits of digital humanities methods for their own studies, either in the form of a critical reflection on a subject related to digital approaches to literary research, or through the conception and execution of a research project using digital tools and corpora of their choosing. The authors supervised this work as tutors, providing support through the different stages of each project’s elaboration. Based on these interactions, as well as course feedback in the form of a survey, this paper presents reflections on the challenges of teaching digital humanities methods to beginners, and on the potential that these methods hold for transforming traditional university curricula.; Nous présentons une expérience pédagogique menée dans le cadre d’un cours d’humanités numériques au sein d’un master de lettres dispensé à Sorbonne Université. À l’issue de cet enseignement, les étudiants inscrits, dépourvus de connaissances préalables en matière d’humanités numériques, sont invités à construire un projet qui mobilise les connaissances acquises lors du cours et qui les amène à évaluer concrètement les bénéfices de cette expérience pour leurs propres travaux. Il s’agit soit de mener une réflexion théorique et critique sur un sujet en lien avec l’apprentissage des humanités numériques pour les lettres et sciences humaines, soit de concevoir un scénario de fouille de corpus littéraires mobilisant des outils numériques. Nous avons encadré ces travaux en tant qu’enseignants et tuteurs, en suivant les différentes étapes de leur déroulement. À partir de ce retour d’expérience, nous proposons une réflexion sur les modalités de l’enseignement des humanités numériques à un public de néophytes et sur les apports des nouveaux outils numériques pour des étudiants issus de parcours traditionnels.

Published
2022
Full Text
View/download PDF

19. Spatial Named Entity Recognition in Literary Texts

Author

Koudoro-Parfait, Caroline, Lejeune, Gaël, Roe, Glenn, Sorbonne Université (SU), Sens, Texte, Informatique, Histoire (STIH), Sorbonne Center for Artificial Intelligence (SCAI), Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Université de Technologie de Compiègne (UTC)-Institut National de Recherche en Informatique et en Automatique (Inria)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut Européen d'administration des Affaires (INSEAD), Observatoire des textes, des idées et des corpus (ObTIC), Bibliothèque nationale de France (BnF)-Centre d’étude de la langue et des littératures françaises (CELLF), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)- Sorbonne Center for Artificial Intelligence (SCAI), Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Université de Technologie de Compiègne (UTC)-Institut National de Recherche en Informatique et en Automatique (Inria)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut Européen d'administration des Affaires (INSEAD)-Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Université de Technologie de Compiègne (UTC)-Institut National de Recherche en Informatique et en Automatique (Inria)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut Européen d'administration des Affaires (INSEAD), Université Paris-Sorbonne (UP4), Centre d’étude de la langue et des littératures françaises (CELLF), and Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Digital Humanities, Optical Character Recognition, [SHS.LITT]Humanities and Social Sciences/Literature, Natural language Processing, Noise, Evaluation, Named Entity Recognition, Users, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract

Exploring text collections through named entities remains a very common need for scholars. Despite the recent advances of Named Entity Recognition (NER) systems, more efficient and easier to use, the task remains problematic when the data is not born digital and thus more prone to Optical Character Recognition errors. In this paper, we investigate the real influence of noise on the extraction of locations in a collection of ten books in French exhibiting different levels of difficulties for NER systems (digitization quality, complexity of layout, variation in language). We compare the results of various systems on the "clean" version of the documents and on different OCRed versions. We show that NER systems do not yield many more errors in noisy documents, most of the errors being already there on a reference version, and in some cases NER performs better on noisy versions. According to our results, the main problem is rare entities (especially hapax) which are more likely to disappear from of the output.

Published
2021
Full Text
View/download PDF

20. The Book of Abstracts for What's Past is Prologue: The NewsEye International Conference

Author

Kanner, Antti, Mäkelä, Eetu, Marjanen, Jani, Tolonen, Mikko, Oberbichler, Sarah, Duong, Quan, Pivovarova, Lidia, Ali, Dilawar, Verstockt, Steven, Ollion, Étienne, Shen, Rubing, Arnold, Matthias, Brown, David, Adam, Raven, Balasubramanian, Saranya, Charvat, Vera Maria, Füllsack, Manfred, Kleinert, Jörn, Misera, Hanna, Pantelic, Nenad, Sonnberger, Jakob, Vogelor, Georg, De Mulder, Alessandra, Kokko, Heikki, Resch, Claudia, Schlögl, Matthias, Rastinger, Nina C., Kampkaspar, Dario, Cuper, Mirjam, Alrahabi, Motasem, Lejeune, Gaël, Parfait, Caroline, Roe, Glenn, Birkholz, Julie M., Chambers, Sally, Hradiš, Michal, Smrz, Pavel, Vidal-Gorène, Chahan, Papastomkou, Sofia, Parr, Jessica, Quiroga, Riva, Sturgeon, Donald, Lee, Ben, Yarasavage, Nathan, Chagué, Alix, Chiffoleau, Floriane, Babitsky, Timlynn, Salmons, Jim, Hyman, James, Lomazow, Steven, and Maunoury, Amanda

Subjects
Digital Humanities, Horizon 2020, Data Science, Computer Science, International Conference, Cultural Heritage
Abstract

This publication presents the abstracts of What’s Past is Prologue: The NewsEye International Conference organised by the consortium of the EU Horizon 2020 research and innovation programme project NewsEye: A Digital Investigator for Historical Newspapers. This conference, which was held online on the 16th and 17th of March 2021, featured four keynote speakers and over thirty presenters hailing from eleven countries. Spanning from May 2018 to January 2022, NewsEye is a research project advancing the state of the art and introducing new concepts, methods and tools for digital humanities by providing enhanced access to historical newspapers for a wide range of users. Hence, the conference theme Towards a future of interdisciplinary collaboration between Cultural Heritage, Digital Humanities, Computer Science and Data Science reflects certain aspects of the NewsEye project itself. The NewsEye consortium is composed of three national libraries and eight research groups based in Austria, Finland, France and Germany, which have each contributed specialised knowledge in the aforementioned subjects.

Published
2021
Full Text
View/download PDF

30. Digitizing Enlightenment: Digital Humanities and the Transformation of Eighteenth-Century Studies

Author

Roe, Glenn, Burrows, Simon, Centre d’étude de la langue et des littératures françaises (CELLF), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Western Sydney University, and Oxford University Studies in the Enlightenment

Subjects
[SHS.LITT]Humanities and Social Sciences/Literature, [SHS.HIST]Humanities and Social Sciences/History, ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Published
2020

35. Pour une esthétique herméneutique. Du Dictionnaire historique et critique de Bayle à l’Encyclopédie

Author

Morrissey, Robert and Roe, Glenn

Abstract

This paper explores tensions at work in the great 18th-century Encyclopédie of Diderot and d'Alembert between, on the one hand, the need for abridgement and summary in order to manage the early modern abundance of knowledge; and, on the other, the critical spirit of copious polyphony that animates the encyclopaedic project. These tensions are the legacy of the dictionary conflicts of the late 17th century, but are also very much at work in the digital age. In the Encyclopédie they lead to the elaboration of a new interactive aesthetic that we have designated “hermeneutical aesthetics”. With the help of computational approaches developed in the digital humanities, the paper analyses the fragile equilibrium between abundance and criticism that the encyclopédistes sought to establish and maintain with varying degrees of success. Once uncovered, it becomes clear that the playful instability at the core of this aesthetic underscores the relevance of the Encyclopédie in dealing with the digital abundance of our own age.

Published
2019

36. Text mining Mill: Computationally detecting influence in the writings of John Stuart Mill from library records.

Author

O'Neill, Helen, Welsh, Anne, Smith, David A., Roe, Glenn, and Terras, Melissa

Subjects
LIBRARY circulation & loans, BOOK donations, NATURAL language processing, DIGITAL libraries, SCHOOL libraries, TEXTBOOKS
Abstract

How can computational methods illuminate the relationship between a leading intellectual, and their lifetime library membership? We report here on an international collaboration that explored the interrelation between the reading record and the publications of the British philosopher and economist John Stuart Mill, focusing on his relationship with the London Library, an independent lending library of which Mill was a member for 32 years. Building on detailed archival research of the London Library's lending and book donation records, a digital library of texts borrowed, and publications produced was assembled, which enabled natural language processing approaches to detect textual reuse and similarity, establishing the relationship between Mill and the Library. Text mining the books Mill borrowed and donated against his published outputs demonstrates that the collections of the London Library influenced his thought, transferred into his published oeuvre, and featured in his role as political commentator and public moralist. We reconceive archival library issue registers as data for triangulating against the growing body of digitized historical texts and the output of leading intellectual figures. We acknowledge, however, that this approach is dependent on the resources and permissions to transcribe extant library registers, and on access to previously digitized sources. Related copyright and privacy restrictions mean our approach is most likely to succeed for other leading eighteenth- and nineteenth-century figures. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

37. Les syntagmes prépositionnels à l’initiale de phrase dans L’Encyclopédie ou Dictionnaire raisonné des sciences, des arts et des métiers

Author

Vigier, Denis, Roe, Glenn, Gladstone, Clovis, Vigier, Denis, Interactions, Corpus, Apprentissages, Représentations (ICAR), École normale supérieure de Lyon (ENS de Lyon)-Université Lumière - Lyon 2 (UL2)-INRP-Ecole Normale Supérieure Lettres et Sciences Humaines (ENS LSH)-Centre National de la Recherche Scientifique (CNRS), and Australian National University (ANU)

Subjects
[SHS.LANGUE]Humanities and Social Sciences/Linguistics, [SHS.LANGUE] Humanities and Social Sciences/Linguistics, ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Published
2018

38. Text mining Mill: Computationally detecting influence in the writings of John Stuart Mill from library records

Author

O’Neill, Helen, Welsh, Anne, Smith, David A., Roe, Glenn, and Terras, Melissa

Abstract

How can computational methods illuminate the relationship between a leading intellectual, and their lifetime library membership? We report here on an international collaboration that explored the interrelation between the reading record and the publications of the British philosopher and economist John Stuart Mill, focusing on his relationship with the London Library, an independent lending library of which Mill was a member for 32 years. Building on detailed archival research of the London Library’s lending and book donation records, a digital library of texts borrowed, and publications produced was assembled, which enabled natural language processing approaches to detect textual reuse and similarity, establishing the relationship between Mill and the Library. Text mining the books Mill borrowed and donated against his published outputs demonstrates that the collections of the London Library influenced his thought, transferred into his published oeuvre, and featured in his role as political commentator and public moralist. We reconceive archival library issue registers as data for triangulating against the growing body of digitized historical texts and the output of leading intellectual figures. We acknowledge, however, that this approach is dependent on the resources and permissions to transcribe extant library registers, and on access to previously digitized sources. Related copyright and privacy restrictions mean our approach is most likely to succeed for other leading eighteenth- and nineteenth-century figures.

Published
2021
Full Text
View/download PDF

39. Constructive Visual Analytics for Text Similarity Detection

Author

Abdul-Rahman, A., Roe, Glenn, Olsen, M., Gladstone, C., Whaling, R., Cronk, N., Morrissey, R., Chen, M., Centre d’étude de la langue et des littératures françaises (CELLF), and Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], ComputingMilieux_MISCELLANEOUS
Abstract

Detecting similarity between texts is a frequently encountered text mining task. Because the measurement of similarity is typically composed of a number of metrics, and some measures are sensitive to subjective interpretation, a generic detector obtained using machine learning often has difficulties balancing the roles of different metrics according to the semantic context exhibited in a specific collection of texts. In order to facilitate human interaction in a visual analytics process for text similarity detection, we first map the problem of pairwise sequence comparison to that of image processing, allowing patterns of similarity to be visualized as a 2D pixelmap. We then devise a visual interface to enable users to construct and experiment with different detectors using primitive metrics, in a way similar to constructing an image processing pipeline. We deployed this new approach for the identification of commonplaces in 18th-century literary and print culture. Domain experts were then able to make use of the prototype system to derive new scholarly discoveries and generate new hypotheses.

Published
2017
Full Text
View/download PDF

45. Visualizing Text Alignments: Image Processing Techniques for Locating 18th-Century Commonplaces

Author

Roe, Glenn, Abdul-Rahman, Alfie, Chen, Min, Gladstone, Clovis, Morrissey, Robert, Olsen, Mark, Roe, Glenn, Abdul-Rahman, Alfie, Chen, Min, Gladstone, Clovis, Morrissey, Robert, and Olsen, Mark

Abstract

This paper examines the use of 'visual analytic' techniques to scrutinise and refine current approaches and algorithms for the identification of text reuse and alignment. In particular, we compare text alignment approaches using the ViTA (Visualization for Text Alignment) system we have developed in the context of a Digging into Data project that seeks to identify 18th century commonplaces in large-scale historical datasets. By leveraging the flexibility of image processing techniques to visualize text alignments in a variety of ways and using multiple parameters, we can improve upon current alignment algorithms in an iterative and integrated process of automated text mining, multivariate visualization, and human-computer interaction

Published
2015

46. To Quote or not to Quote: Citation Strategies in the Encyclopédie

Author

ROE, Glenn, EDELSTEIN, Dan, MORRISSEY, Robert, Centre d’étude de la langue et des littératures françaises (CELLF), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Stanford University, and University of Chicago

Subjects
[SHS.LITT]Humanities and Social Sciences/Literature, [SHS.HIST]Humanities and Social Sciences/History, ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Published
2013
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results