Techniques d'apprentissage supervisé pour l'extraction d'événements TimeML en anglais et français

Béatrice Arnulphy 1, 2 Vincent Claveau 2 Xavier Tannier 1 Anne Vilnat 1
2 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Identifying events from texts is an information extraction task necessary for many NLP applications. Through the TimeML specifications and TempEval challenges, it has received some attention in the last years, yet, no reference result is available for French. In this paper, we try to fill this gap by proposing several event extraction systems, combining for instance Conditional Random Fields, language modeling and k-nearest-neighbors. These systems are evaluated on French corpora and compared with state-of-the-art methods on English. The very good results obtained on both languages validate our whole approach.
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01027563
Contributor : Vincent Claveau <>
Submitted on : Tuesday, July 22, 2014 - 11:36:39 AM
Last modification on : Monday, September 16, 2019 - 11:36:22 AM
Long-term archiving on : Tuesday, November 25, 2014 - 10:36:40 AM

File

CORIA_event.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01027563, version 1

Citation

Béatrice Arnulphy, Vincent Claveau, Xavier Tannier, Anne Vilnat. Techniques d'apprentissage supervisé pour l'extraction d'événements TimeML en anglais et français. Conférence en recherche d'information et applications, CORIA 2014, Mar 2014, Nancy, France. 16 p. ⟨hal-01027563⟩

Share

Metrics

Record views

513

Files downloads

472