Automatic Extraction of Time Expressions Across Domains in French Narratives

Abstract : The prevalence of temporal references across all types of natural language utterances makes temporal analysis a key issue in Natural Language Processing. This work adresses three research questions: 1/is temporal expression recognition specific to a particular domain? 2/if so, can we characterize domain specificity? and 3/how can subdomain specificity be integrated in a single tool for unified temporal expression extraction? Herein, we assess temporal expression recognition from documents written in French covering three domains. We present a new corpus of clinical narratives annotated for temporal expressions , and also use existing corpora in the newswire and historical domains. We show that temporal expressions can be extracted with high performance across domains (best F-measure 0.96 obtained with a CRF model on clinical narratives). We argue that domain adaptation for the extraction of temporal expressions can be done with limited efforts and should cover pre-processing as well as temporal specific tasks.
Type de document :
Communication dans un congrès
Conference on Empirical Methods in Natural Language Processing (EMNLP 2015), Sep 2015, Lisbonne, Portugal. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing,, pp.492-498, 2015
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01222642
Contributeur : Mike Donald Tapi Nzali <>
Soumis le : mercredi 6 septembre 2017 - 20:51:58
Dernière modification le : jeudi 12 juillet 2018 - 13:20:03
Document(s) archivé(s) le : mercredi 10 janvier 2018 - 10:33:09

Fichier

tapinzaliEMNLPshort2015_final....
Fichiers produits par l'(les) auteur(s)

Licence


Copyright (Tous droits réservés)

Identifiants

  • HAL Id : hal-01222642, version 1

Citation

Mike Donald Tapi Nzali, Xavier Tannier, Aurélie Névéol. Automatic Extraction of Time Expressions Across Domains in French Narratives. Conference on Empirical Methods in Natural Language Processing (EMNLP 2015), Sep 2015, Lisbonne, Portugal. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing,, pp.492-498, 2015. 〈hal-01222642〉

Partager

Métriques

Consultations de la notice

119

Téléchargements de fichiers

38