SensPick: Sense Picking for Word Sense Disambiguation
This is an incremental improvement for natural language processing tasks, specifically enhancing word sense disambiguation accuracy.
The paper tackled word sense disambiguation by proposing SensPick, a stacked bidirectional LSTM network that uses context and gloss information, resulting in a 3.5% relative improvement in F-1 score over state-of-the-art models on most benchmarks.
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.