Using Centroids of Word Embeddings and Word Mover's Distance for Biomedical Document Retrieval in Question Answering
This is an incremental improvement for biomedical question answering systems, potentially aiding researchers and clinicians in information retrieval.
The paper tackles biomedical document retrieval for question answering by representing documents and questions as weighted centroids of word embeddings and reranking with a relaxation of Word Mover's Distance, showing competitive performance with PUBMED on BIOASQ data.
We propose a document retrieval method for question answering that represents documents and questions as weighted centroids of word embeddings and reranks the retrieved documents with a relaxation of Word Mover's Distance. Using biomedical questions and documents from BIOASQ, we show that our method is competitive with PUBMED. With a top-k approximation, our method is fast, and easily portable to other domains and languages.