Semi-supervised Word Sense Disambiguation with Neural Models

TL;DR

This paper introduces a semi-supervised neural approach using LSTM models for word sense disambiguation, effectively capturing sequential information and achieving state-of-the-art results, especially for verbs.

Contribution

It presents a novel semi-supervised LSTM-based method that leverages sequence information for WSD, improving over previous vector averaging techniques.

Findings

Achieved state-of-the-art results on WSD benchmarks.

Particularly improved disambiguation accuracy for verbs.

Demonstrated effectiveness of semi-supervised learning in low-resource settings.

Abstract

Determining the intended sense of words in text - word sense disambiguation (WSD) - is a long standing problem in natural language processing. Recently, researchers have shown promising results using word vectors extracted from a neural network language model as features in WSD algorithms. However, a simple average or concatenation of word vectors for each word in a text loses the sequential and syntactic information of the text. In this paper, we study WSD with a sequence learning neural net, LSTM, to better capture the sequential and syntactic patterns of the text. To alleviate the lack of training data in all-words WSD, we employ the same LSTM in a semi-supervised label propagation classifier. We demonstrate state-of-the-art results, especially on verbs.