The importance of character-level information in an event detection model - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

The importance of character-level information in an event detection model

Résumé

This paper tackles the task of event detection that aims at identifying and categorizing event mentions in texts. One of the difficulties of this task is the problem of event mentions corresponding to misspelled, custom, or out-of-vocabulary words. To analyze the impact of character-level features, we propose to integrate character embeddings, that can capture morphological and shape information about words, to a convolutional model for event detection. More precisely, we evaluate two strategies for performing such integration and show that a late fusion approach outperforms both an early fusion approach and models integrating character or subword information such as ELMo or BERT.
Fichier principal
Vignette du fichier
boros-nldb-21-author_version.pdf (482.27 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

cea-04363097 , version 1 (24-12-2023)

Identifiants

Citer

Emanuela Boros, Romaric Besancon, Olivier Ferret, Brigitte Grau. The importance of character-level information in an event detection model. 26th International Conference on Applications of Natural Language to Information Systems (NLDB 2021), Jun 2021, Saarbrücken, Germany. pp.119-131, ⟨10.1007/978-3-030-80599-9_11⟩. ⟨cea-04363097⟩
36 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More