Improving neural tagging with lexical information - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

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.
Fichier principal
Vignette du fichier
iwpt17 (1).pdf (353.77 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01592055 , version 1 (23-10-2017)

Identifiers

  • HAL Id : hal-01592055 , version 1

Cite

Benoît Sagot, Héctor Martínez Alonso. Improving neural tagging with lexical information. 15th International Conference on Parsing Technologies, Sep 2017, Pisa, Italy. pp.25-31. ⟨hal-01592055⟩

Collections

INRIA INRIA2 ANR
150 View
146 Download

Share

Gmail Facebook X LinkedIn More