计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (30): 171-173.

• 数据库与信息处理 • 上一篇    下一篇

基于短语统计机器翻译解码算法的研究与实现

罗 毅,李 淼,朱 鉴,胡冠龙   

  1. 中国科学院 合肥智能机械研究所,合肥 230031
    中国科学技术大学 信息科学技术学院,合肥 230027
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-10-21 发布日期:2007-10-21
  • 通讯作者: 罗 毅

Research and implement of phrase-based statistical machine translation decoding algorithm

LUO Yi,LI Miao,ZHU Jian,HU Guan-long   

  1. Institute of Intelligent Machines,Chinese Academy of Sciences,Hefei 230031,China
    School of Information Science and Technology,University of Science and Technology of China,Hefei 230027,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-10-21 Published:2007-10-21
  • Contact: LUO Yi

摘要: 解码器是统计机器翻译研究的关键部分。在基于短语的统计机器翻译的基础上,结合对数线性模型的思想加入多个特征模型,研究了一种动态规划的柱搜索解码算法。详细介绍此算法在解码器中的具体实现,并对翻译速度和精度作了分析。

Abstract: Decoder is the important part of statistical machine translation research.Based on phrase-based statistical machine translation,a dynamical programming beam search decoding algorithm is put forward combining multi futures model using log-liner model approach.Introduces the implement of the decoder in detail based on this algorithm,and analyzes to the translation speed and precision at last.