首页> 外文会议>Workshop on Human Evaluation of NLP Systems >Is this translation error critical?: Classification-based Human and Automatic Machine Translation Evaluation Focusing on Critical Errors
【24h】

Is this translation error critical?: Classification-based Human and Automatic Machine Translation Evaluation Focusing on Critical Errors

机译:这是一个关键的翻译错误吗?:基于分类的人类和自动机器翻译评估重点是关键错误

获取原文

摘要

This paper discusses a classification-based approach to machine translation evaluation, as opposed to a common regression-based approach in the WMT Metrics task. Recent machine translation usually works well but sometimes makes critical errors due to just a few wrong word choices. Our classification-based approach focuses on such errors using several error type labels, for practical machine translation evaluation in an age of neural machine translation. We have made additional annotations on the WMT 2015-2017 Metrics datasets with fluency and adequacy labels to distinguish different types of translation errors from syntactic and semantic viewpoints. We present our human evaluation criteria for the corpus development and automatic evaluation experiments using the corpus.
机译:本文讨论了基于分类的机器翻译评估方法,而不是在WMT度量任务中的常见回归的方法。 最近的机器翻译通常很好,但由于只有一些错误的单词选择,有时会产生严重的错误。 我们的分类方法专注于使用多个误差类型标签的这种错误,在神经机翻译时代的实际机器翻译评估。 我们在WMT 2015-2017标准数据集中进行了额外的注释,具有流畅性和充足的标签,以区分不同类型的翻译错误与语法和语义观点。 我们介绍了使用语料库的语料库开发和自动评估实验的人为评估标准。

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