[ Home ] – [ Research ] – [ Teaching ] – [ Misc ]


Texte, Discours et Document

Objectifs

L'objectif initial de cette page est d'offrir d'une part des pointeurs vers les ressources ayant trait aux travaux sur la compréhension et l'analyse automatique des “Texte, Discours et Document”, et d'autre part d'assurer un service de veille sur ces pointeurs ; l'idée étant de se tenir au courant de ce qui se fait au niveau national et international et de se positionner par rapport aux thématiques et aux différentes disciplines.

Le terme de ressource se veut large et non spécifié, parmi nos premières idées la page comptera un calendrier d'évènements à venir et passé (appel à communication, parution, …), les pages web des collègues, une bibliographie, les revues du domaine… Ces ressources ne sont pas limitées au web et pourront de plus croiser le regard de plusieurs disciplines comme le Traitement Automatique des Langues, la Linguistique, la Psycho-linguistique, l'Ingénierie du Document… Ce projet pourra évoluer et constituer plus tard un dépôt de ressources et un lieu de discussion, en prenant par exemple la forme wiki et en accueillant des fiches de lecture, des commentaires sur les articles, un forum sur les questions de fond, un glossaire du domaine… Cette page ne concerne pas le champ de recherche en Sciences Humaines et Sociales sur l'analyse critique du discours.

Nous croyons beaucoup en la force collaborative et en l'initiative de chacun. Nous tâcherons de mettre à jour cette page “régulièrement” et toutes suggestions de correction ou de rajout seront les bienvenues.

News (CFP, Seminar, Publication, Job...)

Forthcoming events

Journals

D&D is the first international journal dedicated exclusively to work that deals with language “beyond the single sentence”, in discourse (i.e., text, monologue) and dialogue. The journal adopts an interdisciplinary perspective, accepting work from Linguistics, Computer Science, Psychology, Sociology, Philosophy, and other associated fields with an interest in formally, technically, empirically or experimentally rigorous approaches.

Discours is an international and interdisciplinary e-journal, which publishes non-thematic issues twice a year, and occasional special issues. The journal focuses on the following topics: discourse structure, cohesion, co-reference, linearization, indexation, information structure, word order, segmentation markers, integration markers, discourse relations, cognitive processes involved in discourse comprehension and production, and other related topics. It is intended as a forum for exchanging and comparing data, analyses and opinions for all linguists, psycholinguists and computer linguists working in fields involving the description, comprehension, formalization and processing of text organization. One of the specific features of the journal is to make available online materials or programmes developed for research projects presented in the journal, which may be useful for the research community, such as annotated corpora, coding tables and software tools.

Portals

People working at...

Team

Projects

  • AnnoDis (Annotation Discursive un corpus de référence annoté discursivement outils d'annotation et d'exploitation de corpus annotés )

Tools

Corpus

  • Penn Discourse Treebank Version 2.0 The goal of the project is to annotate the 1 million word Wall Street Journal corpus in Treebank-2 (LDC95T7) with discourse relations holding between the eventualities and propositions mentioned in text, which serve as the arguments to the relation.
  • RST Discourse Treebank RST Discourse Treebank contains a selection of 385 Wall Street Journal articles from the Penn Treebank which have been annotated with discourse structure in the framework of Rhetorical Structure Theory (RST). In addition, the corpus includes a number of humanly-generated extracts and abstracts associated with the original documents.
  • Discourse Graphbank As Florian Wolf's Ph.D thesis, the Discourse Treebank aimed to define a descriptively adequate data structure for representing discourse coherence structures. This project also investigated the impact of discourse coherence structures on other linguistic processes and natural language applications (e.g. anaphor resolution,summarization, information retrieval), and developed and tested discourse parsing algorithms.

Knowlegde resources

References

  • Donia Scott and Hans Kamp, Discourse modeling, In Survey of the State of the Art in Human Language Technology, Chapter 6, Edited by Hans Uszkoreit, 1996

Archives

Submission deadline When Type What Comment

HS Out of interest (Hors sujet)

 
research/discours_etc.txt · Last modified: 2010/05/13 12:35 (external edit)
 
Recent changes RSS feed Creative Commons License Donate Powered by PHP Valid XHTML 1.0 Valid CSS Driven by DokuWiki