From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering

TL;DR

The paper introduces FE2H, a two-stage framework for multi-hop question answering that simplifies reasoning by progressively selecting relevant documents and transferring a single-hop trained reader, achieving state-of-the-art results.

Contribution

FE2H's novel easy-to-hard two-stage approach reduces complexity and improves multi-hop QA performance without relying on graph-based reasoning or question decomposition.

Findings

Outperforms all other methods on HotpotQA distractor setting

Effective document filtering improves reasoning accuracy

Transfer learning from single-hop to multi-hop enhances performance

Abstract

Multi-hop question answering (QA) is a challenging task requiring QA systems to perform complex reasoning over multiple documents and provide supporting facts together with the exact answer. Existing works tend to utilize graph-based reasoning and question decomposition to obtain the reasoning chain, which inevitably introduces additional complexity and cumulative error to the system. To address the above issue, we propose a simple yet effective novel framework, From Easy to Hard (FE2H), to remove distracting information and obtain better contextual representations for the multi-hop QA task. Inspired by the iterative document selection process and the progressive learning custom of humans, FE2H divides both the document selector and reader into two stages following an easy-to-hard manner. Specifically, we first select the document most relevant to the question and then utilize the question together with this document to select other pertinent documents. As for the QA phase, our reader is first trained on a single-hop QA dataset and then transferred into the multi-hop QA task. We comprehensively evaluate our model on the popular multi-hop QA benchmark HotpotQA. Experimental results demonstrate that our method ourperforms all other methods in the leaderboard of HotpotQA (distractor setting).