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.
@article{arxiv.1608.03905,
title = {Using Centroids of Word Embeddings and Word Mover's Distance for Biomedical Document Retrieval in Question Answering},
author = {Georgios-Ioannis Brokos and Prodromos Malakasiotis and Ion Androutsopoulos},
journal= {arXiv preprint arXiv:1608.03905},
year = {2016}
}