HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions
This work provides a more effective evidence retrieval mechanism for multi-hop open-domain QA, which is beneficial for researchers and developers working on complex question answering systems.
This paper addresses the challenge of collecting supporting evidence for multi-hop open-domain Question Answering (QA) by proposing a new retrieval target called "hop," defined as a hyperlink and its corresponding outbound link document. The authors built HopRetriever, which retrieves these hops over Wikipedia, demonstrating significant performance improvements on the HotpotQA dataset compared to previous evidence retrieval methods.
Collecting supporting evidence from large corpora of text (e.g., Wikipedia) is of great challenge for open-domain Question Answering (QA). Especially, for multi-hop open-domain QA, scattered evidence pieces are required to be gathered together to support the answer extraction. In this paper, we propose a new retrieval target, hop, to collect the hidden reasoning evidence from Wikipedia for complex question answering. Specifically, the hop in this paper is defined as the combination of a hyperlink and the corresponding outbound link document. The hyperlink is encoded as the mention embedding which models the structured knowledge of how the outbound link entity is mentioned in the textual context, and the corresponding outbound link document is encoded as the document embedding representing the unstructured knowledge within it. Accordingly, we build HopRetriever which retrieves hops over Wikipedia to answer complex questions. Experiments on the HotpotQA dataset demonstrate that HopRetriever outperforms previously published evidence retrieval methods by large margins. Moreover, our approach also yields quantifiable interpretations of the evidence collection process.