Improving neural tagging with lexical information

Abstract : Neural part-of-speech tagging has achieved competitive results with the incorporation of character-based and pre-trained word embeddings. In this paper, we show that a state-of-the-art bi-LSTM tagger can benefit from using information from morphosyntactic lexicons as additional input. The tagger, trained on several dozen languages, shows a consistent, average improvement when using lexical information, even when also using character-based embeddings, thus showing the complementarity of the different sources of lexical information. The improvements are particularly important for the smaller datasets.
Type de document :
Communication dans un congrès
15th International Conference on Parsing Technologies, Sep 2017, Pisa, Italy. pp.25-31, 2017, 〈http://compling.ucdavis.edu/iwpt2017/〉
Liste complète des métadonnées

Littérature citée [35 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01592055
Contributeur : Benoît Sagot <>
Soumis le : lundi 23 octobre 2017 - 15:15:39
Dernière modification le : mardi 24 octobre 2017 - 11:14:40

Fichier

iwpt17 (1).pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01592055, version 1

Collections

Citation

Benoît Sagot, Héctor Martínez Alonso. Improving neural tagging with lexical information. 15th International Conference on Parsing Technologies, Sep 2017, Pisa, Italy. pp.25-31, 2017, 〈http://compling.ucdavis.edu/iwpt2017/〉. 〈hal-01592055〉

Partager

Métriques

Consultations de la notice

36

Téléchargements de fichiers

8