Query Expansion with Locally-Trained Word Embeddings
This work addresses query expansion for information retrieval, but it is incremental as it builds on existing embedding methods.
The paper tackled the problem of query expansion for information retrieval by showing that locally-trained word embeddings outperform globally-trained ones like word2vec and GloVe, with specific gains in retrieval tasks.
Continuous space word embeddings have received a great deal of attention in the natural language processing and machine learning communities for their ability to model term similarity and other relationships. We study the use of term relatedness in the context of query expansion for ad hoc information retrieval. We demonstrate that word embeddings such as word2vec and GloVe, when trained globally, underperform corpus and query specific embeddings for retrieval tasks. These results suggest that other tasks benefiting from global embeddings may also benefit from local embeddings.