Université Paris-Diderot - Cursus de Linguistique Informatique

Ressources pour le TAL, en particulier pour les projets de L3 et M1 LI.

Ressources générales

Natural Language Toolkit
The Penn Lambda Calculator
Un concordancier bien pratique
Une liste d'outils pour faire de la linguistique de corpus
Bibliographie en ligne d'études linguistiques portant sur des unités lexicales du français, compilée par Patrick Dendale et collaborateurs (Universiteit Antwerpen)

An annotated corpus for the analysis of VP ellipsis.
LEOPAR is an Open Source natural language parser. It is based on Interaction Grammars and produces deep syntactic structures for grammatical sentences.

le tagger Melt
Gérer de grosses matrices creuses ("sparse") en Python: package scipy. doc notamment cf l'utilisation du format MatrixMarket pour stocker un graphe.

TextGraphs-4: Graph-based Methods for Natural Language Processing, ACL IJCNLP workshop (2009), http://www.textgraphs.org/ws09/index.html
Philippe Muller, Nabil Hathout, and Bruno Gaume. Synonym extraction using a semantic distance on a dictionary. In D. Boguraev and R. Mihalcea, editors, Proceedings of the HLT/NAACL workshop Textgraphs, New York, NY, 2006. Association for Computational Linguistics.
B. Gaume, N. Hathout, and P. Muller. Word sense disambiguation using a dictionary for sense similarity measure. In Proceedings of Coling 2004, volume II, pages 1194-1200, Genève, 2004, Association for Computational Linguistics.
Rada Mihalcea, Paul Tarau and Elizabeth Figa, PageRank on Semantic Networks, with application to Word Sense Disambiguation, in Proceedings of The 20st International Conference on Computational Linguistics (COLING 2004), 2004. http://www.cs.unt.edu/~rada/papers/mihalcea.coling04.pdf
Véronis, J. (2004). Hyperlex : lexical cartography for information retrieval. Computer, Speech and Language, 18 (3), 223-252.