arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.09057cs.CL
收藏

基于知识增强的反驳证据提取

Knowledge-Enhanced Evidence Retrieval for Counterargument Generation

Carnegie Mellon University(卡内基梅隆大学);KAIST(韩国科学技术院);Sungkyunkwan University(成均馆大学);University of Dundee(邓迪大学)

Yohan Jo, Haneul Yoo, JinYeong Bak, Alice Oh, Chris Reed, Eduard Hovy

摘要:

寻找反证是许多任务的关键,包括反驳生成。我们建立了一个系统,给定一个声明,检索反证从不同的来源在Web上。该系统的核心是一个自然语言推理(NLI)模型,用于确定候选句子是否是有效的反证。然而,大多数NLI模型,到目前为止,缺乏适当的推理能力,需要找到反证,涉及复杂的推理。因此,我们提出了一个知识增强的NLI模型,旨在处理因果关系和基于实例的推理,将知识图谱。我们的NLI模型优于NLI任务的基线,特别是对于需要有针对性的推理的实例。此外,该NLI模型进一步改进了反证检索系统,特别是更好地发现复杂反证。

英文摘要:

Finding counterevidence to statements is key to many tasks, including counterargument generation. We build a system that, given a statement, retrieves counterevidence from diverse sources on the Web. At the core of this system is a natural language inference (NLI) model that determines whether a candidate sentence is valid counterevidence or not. Most NLI models to date, however, lack proper reasoning abilities necessary to find counterevidence that involves complex inference. Thus, we present a knowledge-enhanced NLI model that aims to handle causality- and example-based inference by incorporating knowledge graphs. Our NLI model outperforms baselines for NLI tasks, especially for instances that require the targeted inference. In addition, this NLI model further improves the counterevidence retrieval system, notably finding complex counterevidence better.

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。

↑