arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.01328cs.CL
收藏

DoQA --通过对话式QA提供特定领域的常见问题解答

DoQA -- Accessing Domain-Specific FAQs via Conversational QA

University of the Basque Country (UPV/EHU)(巴斯克大学);Zurich University of Applied Sciences (ZHAW)(苏黎世应用科学大学)

Jon Ander Campos, Arantxa Otegi, Aitor Soroa, Jan Deriu, Mark Cieliebak, Eneko Agirre

摘要:

这项工作的目标是建立会话问答(QA)接口的大量领域特定的信息在FAQ网站。我们提出了DoQA,一个包含2,437个对话和10,917个QA对的数据集。这些对话是从三个Stack Exchange网站收集的,使用了众包的绿野仙踪方法。与以前的工作相比,DoQA包括定义明确的信息需求,导致更连贯和自然的对话,更少的事实问题,并且是多领域的。此外,我们引入了一个更现实的信息检索(IR)的情况下,系统需要找到答案的任何常见问题解答的文件。一个现有的,强大的,系统的结果表明,由于迁移学习从维基百科QA数据集和微调一个单一的FAQ域,它是可能的,建立高质量的会话QA系统的FAQ没有域内训练数据。良好的结果延续到更具挑战性的IR场景。在这两种情况下,仍然有足够的改进空间,正如更高的人类上限所表明的那样。

英文摘要:

The goal of this work is to build conversational Question Answering (QA) interfaces for the large body of domain-specific information available in FAQ sites. We present DoQA, a dataset with 2,437 dialogues and 10,917 QA pairs. The dialogues are collected from three Stack Exchange sites using the Wizard of Oz method with crowdsourcing. Compared to previous work, DoQA comprises well-defined information needs, leading to more coherent and natural conversations with less factoid questions and is multi-domain. In addition, we introduce a more realistic information retrieval(IR) scenario where the system needs to find the answer in any of the FAQ documents. The results of an existing, strong, system show that, thanks to transfer learning from a Wikipedia QA dataset and fine tuning on a single FAQ domain, it is possible to build high quality conversational QA systems for FAQs without in-domain training data. The good results carry over into the more challenging IR scenario. In both cases, there is still ample room for improvement, as indicated by the higher human upperbound.

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。

↑