Word Sense Disambiguation using a Bidirectional LSTM
arXiv:1606.03568
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.
Cited by in corpus (6)
- GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge
- Incorporating Glosses into Neural Word Sense Disambiguation
- A Novel Neural Sequence Model with Multiple Attentions for Word Sense Disambiguation
- Handling Homographs in Neural Machine Translation
- Fixed-Size Ordinally Forgetting Encoding Based Word Sense Disambiguation
- Token Drop mechanism for Neural Machine Translation