面向事实核查的文档级声明抽取与去语境化
Document-level Claim Extraction and Decontextualisation for Fact-Checking
AI总结：
本文提出一种文档级声明抽取方法，将声明抽取重构为抽取式摘要以识别核心句子，再通过去语境化改写补充上下文，从而更准确地抽取值得核查的声明并改善证据检索。
摘要：
对于人类事实核查员而言，选择核查哪些声明是一项耗时的工作，尤其是当文档由多个句子组成且包含多个声明时。然而，现有的声明抽取方法更侧重于从单个句子中识别和抽取声明，例如识别一个句子是否包含声明，或声明在句子中的确切边界。在本文中，我们提出了一种面向事实核查的文档级声明抽取方法，旨在从文档中抽取值得核查的声明，并对其进行去语境化，使其能够在脱离上下文的情况下被理解。具体而言，我们首先将声明抽取重构为抽取式摘要，以识别文档中的核心句子，然后通过句子去语境化对这些句子进行改写，以纳入来自原始文档的必要上下文。使用自动指标和一位事实核查专业人士进行的评估表明，我们的方法能够比先前工作更准确地从文档中抽取值得核查的声明，同时还能改善证据检索。
英文摘要：
Selecting which claims to check is a time-consuming task for human fact-checkers, especially from documents consisting of multiple sentences and containing multiple claims. However, existing claim extraction approaches focus more on identifying and extracting claims from individual sentences, e.g., identifying whether a sentence contains a claim or the exact boundaries of the claim within a sentence. In this paper, we propose a method for document-level claim extraction for fact-checking, which aims to extract check-worthy claims from documents and decontextualise them so that they can be understood out of context. Specifically, we first recast claim extraction as extractive summarization in order to identify central sentences from documents, then rewrite them to include necessary context from the originating document through sentence decontextualisation. Evaluation with both automatic metrics and a fact-checking professional shows that our method is able to extract check-worthy claims from documents more accurately than previous work, while also improving evidence retrieval.
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。
