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 1909.09253cs.CL
收藏

缺少什么:一种知识缺口引导的多跳问答方法

What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering

Allen Institute for Artificial Intelligence(艾伦人工智能研究所)

Tushar Khot, Ashish Sabharwal, Peter Clark

摘要:

多跳文本问答需要组合来自多个句子的信息。我们关注的是一个自然的环境,与典型的阅读理解不同,每个问题只提供部分信息。模型必须检索并使用额外的知识来正确回答问题。为了应对这一挑战,我们开发了一种新的方法,明确识别所提供的知识和答案选择的关键跨度之间的知识差距。该模型GapQA通过确定跨度和答案选择之间的关系,基于检索到的针对此差距的知识来学习填补此差距。我们建议联合训练一个模型,同时填补这一知识缺口,并将其与提供的部分知识组合在一起。在OpenBookQA数据集上,给定部分知识,明确识别缺失的内容远远优于以前的方法。

英文摘要:

Multi-hop textual question answering requires combining information from multiple sentences. We focus on a natural setting where, unlike typical reading comprehension, only partial information is provided with each question. The model must retrieve and use additional knowledge to correctly answer the question. To tackle this challenge, we develop a novel approach that explicitly identifies the knowledge gap between a key span in the provided knowledge and the answer choices. The model, GapQA, learns to fill this gap by determining the relationship between the span and an answer choice, based on retrieved knowledge targeting this gap. We propose jointly training a model to simultaneously fill this knowledge gap and compose it with the provided partial knowledge. On the OpenBookQA dataset, given partial knowledge, explicitly identifying what's missing substantially outperforms previous approaches.

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。

↑