Decomposing Word Embedding with the Capsule Network

TL;DR

This paper introduces CapsDecE2S, a capsule network-based method for decomposing unsupervised word embeddings into context-specific sense embeddings, achieving state-of-the-art results in word sense disambiguation tasks.

Contribution

The paper presents a novel capsule network approach to decompose word embeddings into sense-specific vectors, enhancing disambiguation performance.

Findings

Achieves state-of-the-art results on word-in-context tasks.

Effective decomposition of embeddings into semantic units.

Improves word sense disambiguation accuracy.

Abstract

Word sense disambiguation tries to learn the appropriate sense of an ambiguous word in a given context. The existing pre-trained language methods and the methods based on multi-embeddings of word did not explore the power of the unsupervised word embedding sufficiently. In this paper, we discuss a capsule network-based approach, taking advantage of capsule's potential for recognizing highly overlapping features and dealing with segmentation. We propose a Capsule network-based method to Decompose the unsupervised word Embedding of an ambiguous word into context specific Sense embedding, called CapsDecE2S. In this approach, the unsupervised ambiguous embedding is fed into capsule network to produce its multiple morpheme-like vectors, which are defined as the basic semantic language units of meaning. With attention operations, CapsDecE2S integrates the word context to reconstruct the multiple morpheme-like vectors into the context-specific sense embedding. To train CapsDecE2S, we propose a sense matching training method. In this method, we convert the sense learning into a binary classification that explicitly learns the relation between senses by the label of matching and non-matching. The CapsDecE2S was experimentally evaluated on two sense learning tasks, i.e., word in context and word sense disambiguation. Results on two public corpora Word-in-Context and English all-words Word Sense Disambiguation show that, the CapsDecE2S model achieves the new state-of-the-art for the word in context and word sense disambiguation tasks.