• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>22nd International Conference on Computational Linguistics >Tighter Integration of Rule-based and Statistical MT in Serial System Combination
【24h】

Tighter Integration of Rule-based and Statistical MT in Serial System Combination

机译：串行系统组合中基于规则和统计MT的紧密集成

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Recent papers have described machine translation (MT) based on an automatic post-editing or serial combination strategy whereby the input language is first translated into the target language by a rule-based MT (RBMT) system, then the target language output is automatically post-edited by a phrase-based statistical machine translation (SMT) system. This approach has been shown to improve MT quality over RBMT or SMT alone. In this previous work, there was a very loose coupling between the two systems: the SMT system only had access to the final 1-best translations from RBMT. Furthermore, the previous work involved European language pairs and relatively small training corpora. In this paper, we describe a more tightly integrated serial combination for the Chinese-to-English MT task. We will present experimental evaluation results on the 2008 NIST constrained data track where a significant gain in terms of both automatic and subjective metrics is achieved through the tighter coupling of the two systems.
机译：最近的论文已经描述了基于自动后期编辑或串行组合策略的机器翻译（MT），其中首先通过基于规则的MT（RBMT）系统将输入语言翻译成目标语言，然后自动发布目标语言输出由基于短语的统计机器翻译（SMT）系统编辑。与仅使用RBMT或SMT相比，该方法已显示可以提高MT质量。在之前的工作中，两个系统之间的耦合非常松散：SMT系统只能从RBMT获得最终的1最佳翻译。此外，先前的工作涉及欧洲语言对和相对较小的训练语料库。在本文中，我们描述了一种用于汉英MT任务的更紧密集成的序列组合。我们将在2008年NIST约束的数据轨道上展示实验评估结果，其中通过两个系统之间的紧密结合，可以在自动和主观指标方面获得可观的收益。

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