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 2212.09702cs.CLcs.AIcs.LG
收藏

关于文档级信息抽取中的事件个体化

On Event Individuation for Document-Level Information Extraction

University of Rochester(罗切斯特大学);Johns Hopkins University(约翰斯·霍普金斯大学)

William Gantt, Reno Kriz, Yunmo Chen, Siddharth Vashishtha, Aaron Steven White

AI总结:

本文质疑模板填充作为文档级信息抽取基准的适用性,指出事件个体化难题导致专家分歧,并通过标注研究和错误分析揭示其对指标、数据集及模型学习能力的负面影响,最后探讨了可能的解决方案。

摘要:

随着信息抽取(IE)系统在处理整篇文档方面变得更加熟练,模板填充这一经典任务作为文档级IE的基准重新引起了关注。在这篇立场论文中,我们质疑模板填充是否适合这一目的。我们认为,该任务要求对事件个体化——即区分不同事件的问题——给出明确答案,而即使是人类专家对此也存在分歧。通过一项标注研究和错误分析,我们表明这引发了对模板填充指标的有用性、该任务数据集质量以及模型学习能力的担忧。最后,我们考虑了可能的解决方案。

英文摘要:

As information extraction (IE) systems have grown more adept at processing whole documents, the classic task of template filling has seen renewed interest as benchmark for document-level IE. In this position paper, we call into question the suitability of template filling for this purpose. We argue that the task demands definitive answers to thorny questions of event individuation -- the problem of distinguishing distinct events -- about which even human experts disagree. Through an annotation study and error analysis, we show that this raises concerns about the usefulness of template filling metrics, the quality of datasets for the task, and the ability of models to learn it. Finally, we consider possible solutions.

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。

↑