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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [31 references]  Display  Hide  Download

https://hal.inria.fr/hal-01592055
Contributor : Benoît Sagot <>
Submitted on : Monday, October 23, 2017 - 3:15:39 PM
Last modification on : Saturday, June 9, 2018 - 10:30:06 AM
Document(s) archivé(s) le : Wednesday, January 24, 2018 - 12:14:36 PM

File

iwpt17 (1).pdf
Files produced by the author(s)

Identifiers

  • 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. ⟨hal-01592055⟩

Share

Metrics

Record views

193

Files downloads

111