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 2201.11176cs.CL
收藏

DiscoScore:用BERT评价语篇生成和语篇连贯

DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence

Heidelberg Institute for Theoretical Studies(海德堡理论研究所);Bielefeld University(比勒费尔德大学);Technische Universität Darmstadt(达姆施塔特工业大学)

Wei Zhao, Michael Strube, Steffen Eger

摘要:

最近,从语篇连贯的角度设计文本生成系统的兴趣越来越大,例如,模拟句子之间的相互依赖关系。尽管如此,最近基于BERT的评估指标在识别连贯性方面仍然很弱,因此在某种程度上无法可靠地发现这些文本生成系统在语篇层面的改进。本文介绍了一个参数化的语篇度量工具DiscoScore,它在中心理论的指导下,使用BERT从不同的角度对语篇连贯进行建模。我们的实验包括16个非语篇和语篇指标,包括DiscoScore和流行的连贯模型,对摘要和文档级机器翻译(MT)进行评估。我们发现,(i)大多数基于BERT的指标与人类评价的连贯性的相关性比十年前发明的早期话语指标要差得多;(ii)最近最先进的BARTScore在系统级操作时很弱-这是特别有问题的,因为系统通常以这种方式进行比较。相比之下,DiscoScore不仅在一致性方面,而且在事实一致性和其他方面,与人类评级实现了强大的系统级相关性,平均超过BARTScore 10个相关点。此外,旨在了解DiscoScore,我们提供的理由话语连贯性的重要性的评估指标,并解释一个变体的优越性。我们的代码可在\url{https://github.com/AIPHES/DiscoScore}上获得。

英文摘要:

Recently, there has been a growing interest in designing text generation systems from a discourse coherence perspective, e.g., modeling the interdependence between sentences. Still, recent BERT-based evaluation metrics are weak in recognizing coherence, and thus are not reliable in a way to spot the discourse-level improvements of those text generation systems. In this work, we introduce DiscoScore, a parametrized discourse metric, which uses BERT to model discourse coherence from different perspectives, driven by Centering theory. Our experiments encompass 16 non-discourse and discourse metrics, including DiscoScore and popular coherence models, evaluated on summarization and document-level machine translation (MT). We find that (i) the majority of BERT-based metrics correlate much worse with human rated coherence than early discourse metrics, invented a decade ago; (ii) the recent state-of-the-art BARTScore is weak when operated at system level -- which is particularly problematic as systems are typically compared in this manner. DiscoScore, in contrast, achieves strong system-level correlation with human ratings, not only in coherence but also in factual consistency and other aspects, and surpasses BARTScore by over 10 correlation points on average. Further, aiming to understand DiscoScore, we provide justifications to the importance of discourse coherence for evaluation metrics, and explain the superiority of one variant over another. Our code is available at \url{https://github.com/AIPHES/DiscoScore}.

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。

↑