arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.04246cs.CL
收藏

阐明隐含信息:超越句子边界的论元检测

Explicating the Implicit: Argument Detection Beyond Sentence Boundaries

Bar-Ilan University(巴伊兰大学);Allen Institute for Artificial Intelligence(艾伦人工智能研究所);University of Washington(华盛顿大学)

Paul Roit, Aviv Slobodkin, Eran Hirsch, Arie Cattan, Ayal Klein, Valentina Pyatkin, Ido Dagan

AI总结:

本文提出一种基于文本蕴含的跨句论元检测方法,将语义关系编码为独立命题并检验其是否被全文蕴含,无需直接监督,在文档级基准上优于部分有监督方法和当代语言模型。

摘要:

检测谓词的语义论元历来被建模为句子级任务。然而,典型读者对谓词-论元关系的理解范围远不止谓词出现的句子本身。在本工作中,我们通过文本蕴含重新形式化论元检测问题,以捕捉跨句子边界的语义关系。我们提出一种方法,首先将某个语义关系编码为一个简单且独立的命题,然后检验该命题是否被整段文本所蕴含,从而测试该语义关系能否从完整段落中推断出来。我们的方法不需要直接监督——由于数据集稀缺,直接监督通常缺失——而是建立在现有的自然语言推理(NLI)和句子级语义角色标注(SRL)资源之上。这种方法有可能将语用上被理解的关系显式化为一组明确的句子。我们在一个近期的文档级基准上进行了验证,性能优于部分有监督方法和当代语言模型。

英文摘要:

Detecting semantic arguments of a predicate word has been conventionally modeled as a sentence-level task. The typical reader, however, perfectly interprets predicate-argument relations in a much wider context than just the sentence where the predicate was evoked. In this work, we reformulate the problem of argument detection through textual entailment to capture semantic relations across sentence boundaries. We propose a method that tests whether some semantic relation can be inferred from a full passage by first encoding it into a simple and standalone proposition and then testing for entailment against the passage. Our method does not require direct supervision, which is generally absent due to dataset scarcity, but instead builds on existing NLI and sentence-level SRL resources. Such a method can potentially explicate pragmatically understood relations into a set of explicit sentences. We demonstrate it on a recent document-level benchmark, outperforming some supervised methods and contemporary language models.

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。

↑