Supervised Machine Learning Techniques to Detect TimeML Events in French and English

Béatrice Arnulphy 1 Vincent Claveau 2 Xavier Tannier 3 Anne Vilnat 3
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
2 LinkMedia - Creating and exploiting explicit links between multimedia fragments
IRISA-D6 - MEDIA ET INTERACTIONS, 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.
Liste complète des métadonnées

Cited literature [25 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01226541
Contributor : Vincent Claveau <>
Submitted on : Monday, November 9, 2015 - 5:47:19 PM
Last modification on : Wednesday, April 10, 2019 - 10:32:01 AM
Document(s) archivé(s) le : Wednesday, February 10, 2016 - 10:50:26 AM

File

NLDB_event.pdf
Files produced by the author(s)

Identifiers

Citation

Béatrice Arnulphy, Vincent Claveau, Xavier Tannier, Anne Vilnat. Supervised Machine Learning Techniques to Detect TimeML Events in French and English. 20thInternational Conference on Applications of Natural Language to Information Systems, NLDB 2015, Jun 2015, Passau, Germany. ⟨10.1007/978-3-319-19581-0_2⟩. ⟨hal-01226541⟩

Share

Metrics

Record views

682

Files downloads

323