Modal sense classification with task-specific context embeddings

Bo Li 1 Mathieu Dehouck 2, 1 Pascal Denis 1
1 MAGNET - Machine Learning in Information Networks
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : Sense disambiguation of modal constructions is a crucial part of natural language understanding. Framed as a supervised learning task, this problem heavily depends on an adequate feature representation of the modal verb context. Inspired by recent work on general word sense disambiguation, we propose a simple approach of modal sense classification in which standard shallow features are enhanced with task-specific context embedding features. Comprehensive experiments show that these enriched contextual representations fed into a simple SVM model lead to significant classification gains over shallow feature sets.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download
Contributor : Mathieu Dehouck <>
Submitted on : Wednesday, May 29, 2019 - 3:33:55 PM
Last modification on : Wednesday, June 5, 2019 - 1:17:13 AM


Files produced by the author(s)


  • HAL Id : hal-02143762, version 1


Bo Li, Mathieu Dehouck, Pascal Denis. Modal sense classification with task-specific context embeddings. ESANN 2019 - 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2019, Bruges, Belgium. ⟨hal-02143762⟩



Record views


Files downloads