arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.11580cs.CL
收藏

错误跨度标注:一种用于机器翻译人工评估的平衡方法

Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation

Microsoft(微软);ETH Zurich(苏黎世联邦理工学院);DFKI(德国人工智能研究中心);UMass Amherst(马萨诸塞大学阿默斯特分校);DCU & IU(都柏林城市大学与印第安纳大学);Dubformer

Tom Kocmi, Vilém Zouhar, Eleftherios Avramidis, Roman Grundkiewicz, Marzena Karpinska, Maja Popović, Mrinmaya Sachan, Mariya Shmatova

AI总结:

本文提出错误跨度标注(ESA)协议,融合直接评估的连续评分与多维质量度量的错误严重程度跨度标记,在WMT23英德翻译上验证其能以更低成本达到与MQM相当的质量。

摘要:

高质量的机器翻译(MT)评估在很大程度上依赖于人工判断。诸如多维质量度量(MQM)之类的综合错误分类方法成本高昂,因为它们耗时且只能由专家完成,而专家的可用性可能有限,尤其是对于低资源语言。另一方面,仅分配总体分数(如直接评估(DA))更简单、更快速,并且可以由任何级别的翻译人员完成,但可靠性较低。在本文中,我们介绍了错误跨度标注(ESA),这是一种人工评估协议,它将DA的连续评分与MQM的高层错误严重程度跨度标记相结合。我们通过将ESA与WMT23中12个MT系统和一个人工参考翻译(英语到德语)的MQM和DA进行比较来验证ESA。结果表明,ESA在相同质量水平下提供比MQM更快、更便宜的标注,且无需昂贵的MQM专家。

英文摘要:

High-quality Machine Translation (MT) evaluation relies heavily on human judgments. Comprehensive error classification methods, such as Multidimensional Quality Metrics (MQM), are expensive as they are time-consuming and can only be done by experts, whose availability may be limited especially for low-resource languages. On the other hand, just assigning overall scores, like Direct Assessment (DA), is simpler and faster and can be done by translators of any level, but is less reliable. In this paper, we introduce Error Span Annotation (ESA), a human evaluation protocol which combines the continuous rating of DA with the high-level error severity span marking of MQM. We validate ESA by comparing it to MQM and DA for 12 MT systems and one human reference translation (English to German) from WMT23. The results show that ESA offers faster and cheaper annotations than MQM at the same quality level, without the requirement of expensive MQM experts.

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。

↑