首页> 外文会议>Annual meeting of the Association for Computational Linguistics >Integrating Phrase-based Reordering Features into a Chart-based Decoder for Machine Translation
【24h】

Integrating Phrase-based Reordering Features into a Chart-based Decoder for Machine Translation

机译:将基于短语的重排序功能集成到用于机器翻译的基于图表的解码器中

获取原文

摘要

Hiero translation models have two limitations compared to phrase-based models: 1) Limited hypothesis space; 2) No lexicalized reordering model. We propose an extension of Hiero called Phrasal-Hiero to address Hiero's second problem. Phrasal-Hiero still has the same hypothesis space as the original Hiero but incorporates a phrase-based distance cost feature and lexicalized reodering features into the chart decoder. The work consists of two parts: 1) for each Hiero translation derivation, find its corresponding discontinuous phrase-based path. 2) Extend the chart decoder to incorporate features from the phrase-based path. We achieve significant improvement over both Hiero and phrase-based baselines for Arabic-English, Chinese-English and German-English translation.
机译:与基于短语的模型相比,Hiero翻译模型有两个局限性:1)有限的假设空间; 2)没有词汇化的重新排序模型。我们提出了Hiero的扩展,称为Phrasal-Hiero,以解决Hiero的第二个问题。 Phrasal-Hiero仍具有与原始Hiero相同的假设空间,但将基于短语的距离成本特征和词法化的重新编排特征合并到了图表解码器中。该工作包括两个部分:1)对于每个Hiero翻译推导,找到其对应的不连续基于短语的路径。 2)扩展图表解码器以合并基于短语的路径中的功能。我们在阿拉伯文,英文,中文英文和德文-英文翻译的Hiero和基于短语的基准方面均取得了显着改善。

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