论文标题
为零射门科学事实检查产生科学主张
Generating Scientific Claims for Zero-Shot Scientific Fact Checking
论文作者
论文摘要
由于科学语言的复杂性和缺乏大量的培训数据，因此很难自动化科学事实检查，因为注释需要域专业知识。为了应对这一挑战，我们提出了科学索赔生成，即从科学句子中产生一个或多个原子和可验证的主张的任务，并证明了其在零照片中的有用性，以检查生物医学主张是否有生物医学主张。我们提出了Soppergen-Bart，这是一种新的监督方法，用于产生文献支持的索赔，以及KBIN，这是一种产生索赔否定的新方法。此外，我们将现有的无监督实体索赔生成方法调整为生物医学主张，我们称之为索赔基因。对零拍摄事实检查的实验表明，索赔基因和索赔符号，再加上KBIN，在接受手动注释的索赔和证据培训的完全监督模型的绩效中最多达到90％。一项严格的评估研究表明，与现有基线相比，生成的索赔和否定质量有显着改善
Automated scientific fact checking is difficult due to the complexity of scientific language and a lack of significant amounts of training data, as annotation requires domain expertise. To address this challenge, we propose scientific claim generation, the task of generating one or more atomic and verifiable claims from scientific sentences, and demonstrate its usefulness in zero-shot fact checking for biomedical claims. We propose CLAIMGEN-BART, a new supervised method for generating claims supported by the literature, as well as KBIN, a novel method for generating claim negations. Additionally, we adapt an existing unsupervised entity-centric method of claim generation to biomedical claims, which we call CLAIMGEN-ENTITY. Experiments on zero-shot fact checking demonstrate that both CLAIMGEN-ENTITY and CLAIMGEN-BART, coupled with KBIN, achieve up to 90% performance of fully supervised models trained on manually annotated claims and evidence. A rigorous evaluation study demonstrates significant improvement in generated claim and negation quality over existing baselines
