NMT十篇必读论文（十）BLEU：a Method for Automatic Evaluation of Machine Translation

最新推荐文章于 2024-04-29 10:24:30 发布

ylyyyy

最新推荐文章于 2024-04-29 10:24:30 发布

阅读量2k

点赞数 2

本文链接：https://blog.csdn.net/weixin_40240670/article/details/85112078

版权

原文链接：https://www.jianshu.com/p/15c22fadcba5

BLEU (Bilingual Evaluation Understudy) is an algorithm for evaluating the quality of text which has been machine-translated from one natural language to another. Quality is considered to be the correspondence between a machine's output and that of a human: "the closer a machine translation is to a professional human translation, the better it is" – this is the central idea behind BLEU. BLEU was one of the first metrics to achieve a high correlation with human judgements of quality, and remains one of the most popular automated and inexpensive metric. -- 维基百科

bleu是一种文本评估算法，它是用来评估机器翻译跟专业人工翻译之间的对应关系，核心思想就是机器翻译越接近专业人工翻译，质量就越好，经过bleu算法得出的分数可以作为机器翻译质量的其中一个指标。使用bleu的目的是给出一个快且不差的自动评估解决方案，评估的是机器翻译与人翻译的接近程度。