arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.09600cs.CL
收藏

HotpotQA:一个多样的、可解释的多跳问答数据集

HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Carnegie Mellon University(卡内基梅隆大学);Stanford University(斯坦福大学);Université de Montréal(蒙特利尔大学);Google AI(谷歌人工智能)

Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, Christopher D. Manning

摘要:

现有的问答(QA)数据集无法训练QA系统来执行复杂的推理并为答案提供解释。我们介绍了HotpotQA,一个新的数据集,包含113 k个基于维基百科的问答对,具有四个关键特征:(1)问题需要在多个支持文档上寻找和推理来回答;(2)问题是多样的,不受任何预先存在的知识库或知识模式的限制;(3)我们提供推理所需的推理级支持事实,允许QA系统在强监督下进行推理并解释预测;(4)提出了一种新型的事实对比问题,用于测试QA系统提取相关事实并进行必要对比的能力。我们表明,HotpotQA对最新的QA系统具有挑战性,并且支持的事实使模型能够提高性能并做出可解释的预测。

英文摘要:

Existing question answering (QA) datasets fail to train QA systems to perform complex reasoning and provide explanations for answers. We introduce HotpotQA, a new dataset with 113k Wikipedia-based question-answer pairs with four key features: (1) the questions require finding and reasoning over multiple supporting documents to answer; (2) the questions are diverse and not constrained to any pre-existing knowledge bases or knowledge schemas; (3) we provide sentence-level supporting facts required for reasoning, allowing QA systems to reason with strong supervision and explain the predictions; (4) we offer a new type of factoid comparison questions to test QA systems' ability to extract relevant facts and perform necessary comparison. We show that HotpotQA is challenging for the latest QA systems, and the supporting facts enable models to improve performance and make explainable predictions.

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。

↑