Skip to Main content Skip to Navigation
Journal articles

Approche supervisée à base de cellules LSTM bidirectionnelles pour la désambiguïsation lexicale

Abstract : In Word Sense Disambiguation, there are still few usages of neural networks. This direction is very promising however, the results obtained by these first systems being systematically in the top of the evaluation campaigns, with a scope for improvement which seems still large. We present in this paper a new architecture based on neural networks for Word Sense Disambiguation. Our system is at the same time less difficult to train than existing neural networks , and it obtains state of the art results on most evaluation tasks in English. The focus is on the reproducibility of our system and our results, through the use of a word embeddings model, training corpora and evaluation corpora freely accessible.
Document type :
Journal articles
Complete list of metadatas

Cited literature [48 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02010901
Contributor : Benjamin Lecouteux <>
Submitted on : Thursday, February 7, 2019 - 3:19:20 PM
Last modification on : Friday, July 3, 2020 - 4:50:13 PM
Document(s) archivé(s) le : Wednesday, May 8, 2019 - 3:02:40 PM

File

Revue_TAL_59_1_versionlongue_2...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02010901, version 1

Collections

Citation

Loïc Vial, Benjamin Lecouteux, Didier Schwab. Approche supervisée à base de cellules LSTM bidirectionnelles pour la désambiguïsation lexicale. Traitement Automatique des Langues, ATALA, 2019. ⟨hal-02010901⟩

Share

Metrics

Record views

133

Files downloads

178