首页> 外文会议>Conference on machine translation;Annual meeting of the Association for Computational Linguistics >The MuCoW test suite at WMT 2019: Automatically harvested multilingual contrastive word sense disambiguation test sets for machine translation
【24h】

The MuCoW test suite at WMT 2019: Automatically harvested multilingual contrastive word sense disambiguation test sets for machine translation

机译:WMT 2019的MuCoW测试套件:用于机器翻译的自动收集的多语言对比词义消歧测试仪

获取原文

摘要

Supervised Neural Machine Translation (NMT) systems currently achieve impressive translation quality for many language pairs. One of the key features of a correct translation is the ability to perform word sense disambiguation (WSD), i.e., to translate an ambiguous word with its correct sense. Existing evaluation benchmarks on WSD capabilities of translation systems rely heavily on manual work and cover only few language pairs and few word types. We present Mu-CoW, a multilingual contrastive test suite that covers 16 language pairs with more than 200 000 contrastive sentence pairs, automatically built from word-aligned parallel corpora and the wide-coverage multilingual sense inventory of BabelNet. We evaluate the quality of the ambiguity lexicons and of the resulting test suite on all submissions from 9 language pairs presented in the WMT19 news shared translation task, plus on other 5 language pairs using pretrained NMT models.
机译:监督型神经机器翻译(NMT)系统目前可为许多语言对提供令人印象深刻的翻译质量。正确翻译的关键特征之一是能够执行词义歧义消除(WSD),即以正确的意义翻译歧义词。现有的关于翻译系统的WSD功能的评估基准在很大程度上依赖于人工工作,并且仅涵盖很少的语言对和很少的单词类型。我们介绍了Mu-CoW,这是一种多语言对比测试套件,涵盖了16种语言对和20万多个对比句子对,它们是根据与单词对齐的并行语料库和BabelNet的广泛覆盖的多语种感官清单自动构建的。我们根据WMT19新闻共享翻译任务中提供的9种语言对的所有提交内容,以及使用预训练的NMT模型的其他5种语言对的所有提交内容,评估歧义词典的质量以及由此产生的测试套件的质量。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号