Abstract
Answering questions that require multi-hop reasoning at web-scale
necessitates retrieving multiple evidence documents, one of which often has
little lexical or semantic relationship to the question. This paper introduces
a new graph-based recurrent retrieval approach that learns to retrieve
reasoning paths over the Wikipedia graph to answer multi-hop open-domain
questions. Our retriever model trains a recurrent neural network that learns to
sequentially retrieve evidence paragraphs in the reasoning path by conditioning
on the previously retrieved documents. Our reader model ranks the reasoning
paths and extracts the answer span included in the best reasoning path.
Experimental results show state-of-the-art results in three open-domain QA
datasets, showcasing the effectiveness and robustness of our method. Notably,
our method achieves significant improvement in HotpotQA, outperforming the
previous best model by more than 14 points.
Users
Please
log in to take part in the discussion (add own reviews or comments).