SensPick: Sense Picking for Word Sense Disambiguation

TL;DR

SensPick is a neural network model that combines context and gloss information for word sense disambiguation, achieving competitive results by modeling semantic relationships more effectively.

Contribution

This paper introduces SensPick, a stacked bidirectional LSTM model that leverages both context and gloss data for improved WSD performance.

Findings

Outperforms traditional and state-of-the-art models on benchmark datasets.

Achieves a 3.5% relative improvement in F-1 score.

Incorporating semantic relationships enhances WSD accuracy.

Abstract

Word sense disambiguation (WSD) methods identify the most suitable meaning of a word with respect to the usage of that word in a specific context. Neural network-based WSD approaches rely on a sense-annotated corpus since they do not utilize lexical resources. In this study, we utilize both context and related gloss information of a target word to model the semantic relationship between the word and the set of glosses. We propose SensPick, a type of stacked bidirectional Long Short Term Memory (LSTM) network to perform the WSD task. The experimental evaluation demonstrates that SensPick outperforms traditional and state-of-the-art models on most of the benchmark datasets with a relative improvement of 3.5% in F-1 score. While the improvement is not significant, incorporating semantic relationships brings SensPick in the leading position compared to others.