arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.02804cs.CLcs.AI
收藏

Just ClozE! 一种用于更快评估抽象摘要事实一致性的新型框架

Just ClozE! A Novel Framework for Evaluating the Factual Consistency Faster in Abstractive Summarization

Beijing University of Posts and Telecommunications(北京邮电大学);Shamoon College of Engineering(沙蒙工程学院)

Yiyang Li, Lei Li, Marina Litvak, Natalia Vanetik, Dingxin Hu, Yuze Li, Yanquan Zhou

AI总结:

本文提出基于完形填空的评估框架ClozE,用于快速评估抽象摘要的事实一致性,在保留QA级可解释性和性能的同时将评估时间减少近96%。

摘要:

近年来,抽象摘要中的事实一致性问题受到了广泛关注,摘要与文档之间事实一致性的评估已成为一项重要而紧迫的任务。当前大多数评估指标借鉴自问答(QA)或自然语言推理(NLI)任务。然而,基于QA的指标在实际应用中极为耗时,而基于NLI的指标则缺乏可解释性。在本文中,我们提出了一个基于完形填空的评估框架,称为ClozE,并展示了基于完形填空指标的巨大潜力。它继承了QA的强可解释性,同时保持了NLI级别的推理速度。我们通过在六个人工标注数据集和一个元评估基准GO FIGURE(Gabriel et al., 2021)上的实验证明,相对于基于QA的指标,ClozE可以在保留其可解释性和性能的同时,将评估时间减少近96%。最后,我们讨论了ClozE在实际应用中的三个重要方面,进一步表明与其他指标相比,ClozE具有更好的整体性能。

英文摘要:

The issue of factual consistency in abstractive summarization has received extensive attention in recent years, and the evaluation of factual consistency between summary and document has become an important and urgent task. Most of the current evaluation metrics are adopted from the question answering (QA) or natural language inference (NLI) task. However, the application of QA-based metrics is extremely time-consuming in practice while NLI-based metrics are lack of interpretability. In this paper, we propose a cloze-based evaluation framework called ClozE and show the great potential of the cloze-based metric. It inherits strong interpretability from QA, while maintaining the speed of NLI- level reasoning. We demonstrate that ClozE can reduce the evaluation time by nearly 96% relative to QA-based metrics while retaining their interpretability and performance through experiments on six human-annotated datasets and a meta-evaluation benchmark GO FIGURE (Gabriel et al., 2021). Finally, we discuss three important facets of ClozE in practice, which further shows better overall performance of ClozE compared to other metrics.

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。

↑