Multi Sense Embeddings from Topic Models
This addresses a critical issue in lexical semantics for NLP applications, offering an incremental improvement over existing word embedding methods.
The paper tackles the problem of representing multiple meanings of polysemous words in vector spaces by proposing a topic modeling-based skip-gram approach for learning multi-prototype word embeddings, and shows that these embeddings outperform state-of-the-art implementations in capturing context and word similarity.
Distributed word embeddings have yielded state-of-the-art performance in many NLP tasks, mainly due to their success in capturing useful semantic information. These representations assign only a single vector to each word whereas a large number of words are polysemous (i.e., have multiple meanings). In this work, we approach this critical problem in lexical semantics, namely that of representing various senses of polysemous words in vector spaces. We propose a topic modeling based skip-gram approach for learning multi-prototype word embeddings. We also introduce a method to prune the embeddings determined by the probabilistic representation of the word in each topic. We use our embeddings to show that they can capture the context and word similarity strongly and outperform various state-of-the-art implementations.