Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering

TL;DR

This paper introduces a bridge reasoning approach for open-domain multi-hop question answering, improving retrieval accuracy by recognizing key linking passages without relying on heavy contextual embeddings.

Contribution

The paper proposes a novel bridge reasoner that identifies linking passages in multi-hop QA, significantly enhancing retrieval performance on the HotpotQA benchmark.

Findings

Achieved 14 F1 points improvement over baseline on HotpotQA.

Competitive results without using memory-inefficient BERT embeddings.

Introduced a weakly supervised training method for the bridge reasoner.

Abstract

A key challenge of multi-hop question answering (QA) in the open-domain setting is to accurately retrieve the supporting passages from a large corpus. Existing work on open-domain QA typically relies on off-the-shelf information retrieval (IR) techniques to retrieve \textbf{answer passages}, i.e., the passages containing the groundtruth answers. However, IR-based approaches are insufficient for multi-hop questions, as the topic of the second or further hops is not explicitly covered by the question. To resolve this issue, we introduce a new sub-problem of open-domain multi-hop QA, which aims to recognize the bridge (\emph{i.e.}, the anchor that links to the answer passage) from the context of a set of start passages with a reading comprehension model. This model, the \textbf{bridge reasoner}, is trained with a weakly supervised signal and produces the candidate answer passages for the \textbf{passage reader} to extract the answer. On the full-wiki HotpotQA benchmark, we significantly improve the baseline method by 14 point F1. Without using any memory-inefficient contextual embeddings, our result is also competitive with the state-of-the-art that applies BERT in multiple modules.