arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.00993cs.CL
收藏

利用外部知识改进问答

Improving Question Answering with External Knowledge

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Cornell University(康奈尔大学);Tencent AI Lab(腾讯人工智能实验室)

Xiaoman Pan, Kai Sun, Dian Yu, Jianshu Chen, Heng Ji, Claire Cardie, Dong Yu

摘要:

我们专注于科学等学科领域的多项选择问答(QA)任务,我们需要广泛的背景知识和来自给定学科领域参考语料库的事实。在这项工作中,我们探索简单而有效的方法,利用两个来源的外部知识的主题领域的QA。第一种方法利用从开放域资源提取的相关文本片段来丰富原始主题领域参考语料库(即,维基百科),涵盖了问题和答案选项中潜在的模糊概念。与其他QA研究一样,第二种方法通过添加额外的域内主题领域实例来简单地增加训练数据的量。三个具有挑战性的多项选择科学QA任务的实验(即,ARC-Easy、ARC-Challenge和OpenBookQA)证明了我们方法的有效性:与以前的最先进技术相比,我们分别获得了高达8.1%、13.0%和12.8%的准确度绝对增益。虽然我们观察到一致的收益时,我们从维基百科引入的知识,我们发现,采用额外的QA训练实例是不是统一的帮助:性能下降时,增加的实例表现出更高的难度比原来的训练数据。作为利用非结构化外部知识进行主题领域QA的第一批研究之一,我们希望我们的方法,观察和讨论暴露的局限性可能会揭示该领域的进一步发展。

英文摘要:

We focus on multiple-choice question answering (QA) tasks in subject areas such as science, where we require both broad background knowledge and the facts from the given subject-area reference corpus. In this work, we explore simple yet effective methods for exploiting two sources of external knowledge for subject-area QA. The first enriches the original subject-area reference corpus with relevant text snippets extracted from an open-domain resource (i.e., Wikipedia) that cover potentially ambiguous concepts in the question and answer options. As in other QA research, the second method simply increases the amount of training data by appending additional in-domain subject-area instances. Experiments on three challenging multiple-choice science QA tasks (i.e., ARC-Easy, ARC-Challenge, and OpenBookQA) demonstrate the effectiveness of our methods: in comparison to the previous state-of-the-art, we obtain absolute gains in accuracy of up to 8.1%, 13.0%, and 12.8%, respectively. While we observe consistent gains when we introduce knowledge from Wikipedia, we find that employing additional QA training instances is not uniformly helpful: performance degrades when the added instances exhibit a higher level of difficulty than the original training data. As one of the first studies on exploiting unstructured external knowledge for subject-area QA, we hope our methods, observations, and discussion of the exposed limitations may shed light on further developments in the area.

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。

↑