Query Expansion Using Word Embeddings

We present a suite of novel query expansion methods that are based on word embeddings. Using the Word2Vec embedding approach, applied over the entire corpus, we select terms that are semantically related to the query. Our methods either use the terms to expand the original query or integrate them with the effective pseudo-feedback-based relevance model. In the former case, retrieval performance is significantly better than that of using only the query, and in the latter case the performance is significantly better than that of the relevance model.