- TL;DR: Graph-based recurrent retriever that learns to retrieve reasoning paths over Wikipedia Graph outperforms the most recent state of the art on HotpotQA by more than 10 points.
- Abstract: Answering questions that require multi-hop reasoning at web-scale requires 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 trains a recurrent neural network that learns to sequentially retrieve evidence documents in the reasoning path by conditioning on the previously retrieved documents. Our reader ranks the reasoning paths and extracts the answer span included in the best reasoning path. Experimental results demonstrate state-of-the-art results in two open-domain QA datasets showcasing the robustness of our method. Notably, our method achieves significant improvement in HotpotQA fullwiki and distractor settings, outperforming the previous best model by more than 10 points.
- Keywords: Multi-hop Open-domain Question Answering, Graph-based Retrieval, Multi-step Retrieval