Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering

Multi-hop question answering (QA) requires an information retrieval (IR) system that can find \textitmultiple supporting evidence needed to answer the question, making the retrieval process very challenging. This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to \textithop to other relevant evidence. In a setting, with more than \textbfmillion Wikipedia paragraphs, our approach leads to significant boost in retrieval performance. The retrieved evidence also increased the performance of an existing QA model (without any training) on the benchmark by \textbf F1.