arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.09073cs.CL
收藏

询问理解:多跳问答的问题生成

Ask to Understand: Question Generation for Multi-hop Question Answering

Beijing Institute of Technology(北京理工大学)

Jiawei Li, Mucheng Ren, Yang Gao, Yizhe Yang

摘要:

多跳问答(QA)要求机器通过从多个文档中寻找分散的线索和推理来回答复杂的问题。图网络(GN)和问题分解(QD)是目前常用的两种方法。前者利用“黑盒”推理过程来捕捉实体和句子之间的潜在关系,从而取得了良好的性能。同时,后者通过将多跳问题分解为简单的单跳子问题,提供了清晰的推理逻辑路线。在本文中,我们提出了一种新的方法来完成多跳问答的问题生成(QG)的角度。具体来说,我们精心设计了一个端到端的QG模块的基础上,经典的QA模块,这可以帮助模型理解的背景下,问固有的逻辑子问题,从而继承了基于QD的方法的可解释性,并显示出优越的性能。在HotpotQA数据集上的实验表明,我们提出的QG模块的有效性,人工评估进一步阐明了其定量的可解释性,全面的分析表明,QG模块可以生成更好的子问题比QD方法在流畅性,一致性和多样性方面。

英文摘要:

Multi-hop Question Answering (QA) requires the machine to answer complex questions by finding scattering clues and reasoning from multiple documents. Graph Network (GN) and Question Decomposition (QD) are two common approaches at present. The former uses the "black-box" reasoning process to capture the potential relationship between entities and sentences, thus achieving good performance. At the same time, the latter provides a clear reasoning logical route by decomposing multi-hop questions into simple single-hop sub-questions. In this paper, we propose a novel method to complete multi-hop QA from the perspective of Question Generation (QG). Specifically, we carefully design an end-to-end QG module on the basis of a classical QA module, which could help the model understand the context by asking inherently logical sub-questions, thus inheriting interpretability from the QD-based method and showing superior performance. Experiments on the HotpotQA dataset demonstrate that the effectiveness of our proposed QG module, human evaluation further clarifies its interpretability quantitatively, and thorough analysis shows that the QG module could generate better sub-questions than QD methods in terms of fluency, consistency, and diversity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑