Word Sense Disambiguation using a Bidirectional LSTM
Paper in proceeding, 2016

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.

Author

Mikael Kågebäck

Chalmers, Computer Science and Engineering (Chalmers), Computing Science (Chalmers)

Hans Salomonsson

Chalmers, Computer Science and Engineering (Chalmers)

5th Workshop on Cognitive Aspects of the Lexicon (CogALex-V) at the 26th International Conference on Computational Linguistics (COLING 2016)

Subject Categories

Computer and Information Science

More information

Created

10/7/2017