首页> 外文会议>Conference of the Association for Machine Translation in the Americas >A language comparison of Human Evaluation and Quality Estimation
【24h】

A language comparison of Human Evaluation and Quality Estimation

机译:人类评估和质量估计的语言比较

获取原文

摘要

1. The main generic QE system has aggregate scores in a similar range as HE. This is promising. 2. Customization is key to QE for evaluation, to shape the output to the custom translation and evaluation guidelines 3. Findings in custom data can help improve accuracy on non-custom errors 4. QE is a rising technology that will be widely present in many MT uses in the near future.
机译:1.主要通用QE系统在类似的范围内具有相似的分数。这是有希望的。 2.自定义是QE进行评估的关键,将输出塑造到自定义翻译和评估指南3.定制数据中的调查结果可以帮助提高非自定义错误的准确性4. QE是一个升高的技术,将广泛存在于许多方面MT在不久的将来使用。

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