arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.07597cs.CL
收藏

一种简单有效的开放域多跳问答桥推理方法

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

University of California, Santa Barbara(加州大学圣巴巴拉分校);IBM Research(IBM研究院)

Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Hong Wang, Shiyu Chang, Murray Campbell, William Yang Wang

摘要:

开放域环境下多跳问答(QA)的一个关键挑战是从大型语料库中准确地检索支持段落。关于开放域QA的现有工作通常依赖于现成的信息检索(IR)技术来检索\textbf{answer passages},即,包含地面实况答案的段落。然而,基于IR的方法对于多跳问题是不够的,因为第二跳或进一步跳的主题没有被问题明确地覆盖。为了解决这个问题,我们引入了一个新的子问题的开放域多跳问答,其目的是识别桥梁(\emph{i.e.},锚链接到答案通道)从上下文的一组开始段落的阅读理解模型。该模型\textbf{bridge reasoner}使用弱监督信号进行训练,并为\textbf{passage reader}生成候选答案通道以提取答案。在完整的wiki HotpotQA基准测试中,我们将基线方法显著改进了14点F1。在不使用任何内存效率低下的上下文嵌入,我们的结果也是具有竞争力的国家的最先进的应用BERT在多个模块。

英文摘要:

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.

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。

↑