Word Sense Disambiguation using a Bidirectional LSTM

Mikael Kågebäck, Hans Salomonsson


Abstract
In this paper we present a clean, yet effective, model for word sense disambiguation. Our approach leverage a bidirectional long short-term memory network which is shared between all words. This enables the model to share statistical strength and to scale well with vocabulary size. The model is trained end-to-end, directly from the raw text to sense labels, and makes effective use of word order. We evaluate our approach on two standard datasets, using identical hyperparameter settings, which are in turn tuned on a third set of held out data. We employ no external resources (e.g. knowledge graphs, part-of-speech tagging, etc), language specific features, or hand crafted rules, but still achieve statistically equivalent results to the best state-of-the-art systems, that employ no such limitations.
Anthology ID:
W16-5307
Volume:
Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex - V)
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Michael Zock, Alessandro Lenci, Stefan Evert
Venue:
CogALex
SIG:
SIGLEX
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
51–56
Language:
URL:
https://aclanthology.org/W16-5307
DOI:
Bibkey:
Cite (ACL):
Mikael Kågebäck and Hans Salomonsson. 2016. Word Sense Disambiguation using a Bidirectional LSTM. In Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex - V), pages 51–56, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Word Sense Disambiguation using a Bidirectional LSTM (Kågebäck & Salomonsson, CogALex 2016)
Copy Citation:
PDF:
https://aclanthology.org/W16-5307.pdf
Code
 salomons/wsd