首页> 外文期刊>Computer speech and language >Source sentence simplification for statistical machine translation
【24h】

Source sentence simplification for statistical machine translation

机译:统计机器翻译的源句子简化

获取原文
获取原文并翻译 | 示例

摘要

Long sentences with complex syntax and long-distance dependencies pose difficulties for machine translation systems. Short sentences, on the other hand, are usually easier to translate. We study the potential of addressing this mismatch using text simplification: given a simplified version of the full input sentence, can we use it in addition to the full input to improve translation? We show that the spaces of original and simplified translations can be effectively combined using translation lattices and compare two decoding approaches to process both inputs at different levels of integration. We demonstrate on source-annotated portions of WMT test sets and on top of strong baseline systems combining hierarchical and neural translation for two language pairs that source simplification can help to improve translation quality.
机译:具有复杂语法和长距离依赖性的长句子给机器翻译系统带来困难。另一方面,短句子通常更容易翻译。我们研究了使用文本简化来解决这种不匹配的可能性:给定完整输入句子的简化版本,除了完整输入之外我们还可以使用它来改善翻译吗?我们表明,可以使用翻译晶格有效地合并原始翻译和简化翻译的空间,并比较两种解码方法来处理集成度不同的两个输入。我们在WMT测试集的带有源注释的部分上以及在将两种语言对的层次翻译和神经翻译相结合的强大基线系统之上进行了演示,它们简化了源代码有助于提高翻译质量。

著录项

  • 来源
    《Computer speech and language》 |2017年第9期|221-235|共15页
  • 作者单位

    University of Cambridge, Department of Engineering, CB2 1PX Cambridge, U.K.;

    University of Cambridge, Department of Engineering, CB2 1PX Cambridge, U.K.,SDL Research, Cambridge, U.K.;

    University of Cambridge, Department of Engineering, CB2 1PX Cambridge, U.K.;

    University of Cambridge, Department of Engineering, CB2 1PX Cambridge, U.K.;

    University of Cambridge, Department of Engineering, CB2 1PX Cambridge, U.K.,SDL Research, Cambridge, U.K.;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Hierarchical machine translation; Text simplification; Neural machine translation;

    机译:分层机器翻译;文字简化;神经机器翻译;

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