Decomposing Word Embedding with the Capsule Network

Multi-sense word embeddings have been promising solutions for word sense learning. Nevertheless, building large-scale training corpus and learning appropriate word sense are still open issues. In this paper, we propose a method for Decomposing the word Embedding into context-specific Sense representation, called DecE2S. First, the unsupervised polysemy embedding is fed into capsule network to produce its multiple sememelike vectors. Second, with attention operations, DecE2S integrates the word context to represent the context-specific sense vector. To train DecE2S, we design a word matching training method for learning the contextspecific sense representation. DecE2S 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 DesE2S model achieves the new state-of-the-art for the word in context and word sense disambiguation tasks.