Linear Algebraic Structure of Word Senses, with Applications to Polysemy

Word embeddings are ubiquitous in NLP and information retrieval, but it’s unclear what they represent when the word is polysemous, i.e., has multiple senses. Here it is shown that multiple word senses reside in linear superposition within the word embedding and can be recovered by simple sparse coding. The success of the method —which applies to several embedding methods including word2vec— is mathematically explained using the random walk on discourses model (Arora et al., 2015). A novel aspect of our technique is that each word sense is also accompanied by one of about 2000 “discourse atoms” that give a succinct description of which other words co-occur with that word sense. Discourse atoms seem of independent interest, and make the method potentially more useful than the traditional clustering-based approaches to polysemy.