arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.15115cs.CLcs.LGstat.ML
收藏

表上开放事实检查的联合验证和重排序

Joint Verification and Reranking for Open Fact Checking Over Tables

University of Cambridge(剑桥大学);Facebook AI Research(Facebook AI研究院);University College London(伦敦大学学院)

Michael Schlichtkrull, Vladimir Karpukhin, Barlas Oğuz, Mike Lewis, Wen-tau Yih, Sebastian Riedel

摘要:

结构化信息是事实主张自动验证的重要知识来源。尽管如此,大多数现有的研究都集中在文本数据,最近的几次调查结构化数据已经为闭域设置,其中适当的证据,每个索赔被认为已经检索。在本文中,我们研究了结构化数据在开放域设置的验证,介绍了一个联合重新排序和验证模型,融合证据文件的验证组件。我们的开放领域模型在TabFact数据集上实现了与最先进的闭域模型相当的性能,并展示了包含多个表的性能增益以及启发式检索基线的显着改进。

英文摘要:

Structured information is an important knowledge source for automatic verification of factual claims. Nevertheless, the majority of existing research into this task has focused on textual data, and the few recent inquiries into structured data have been for the closed-domain setting where appropriate evidence for each claim is assumed to have already been retrieved. In this paper, we investigate verification over structured data in the open-domain setting, introducing a joint reranking-and-verification model which fuses evidence documents in the verification component. Our open-domain model achieves performance comparable to the closed-domain state-of-the-art on the TabFact dataset, and demonstrates performance gains from the inclusion of multiple tables as well as a significant improvement over a heuristic retrieval baseline.

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。

↑