基于选择偏向性的统计机器翻译模型-北京大学学报自然科学版.PDFVIP

北京大学学报(自然科学版) 第 52 卷 第 1 期 2016 年 1 月 Acta Scientiarum Naturalium Universitatis Pekinensis, Vol. 52, No. 1 (Jan. 2016) doi: 10.13209/j.0479-8023.2016.013 基于选择偏向性的统计机器翻译模型 † 唐海庆 熊德意 苏州大学计算机科学与技术学院 , 苏州 215006; † 通信作者 , E-mail: dyxiong@ 摘要 针对基于短语的统计机器翻译使用有限的语义知识 , 导致长距离的动宾短语对翻译质量不高的问题 , 提出基于动词选择偏向性的翻译模型, 引入动词对宾语的语义约束信息, 为动词找到合适的宾语翻译。首先 使用条件概率方法 , 训练动词对宾语的选择偏向性 , 然后将选择偏向性作为一个新特征, 集成到基于短语的 翻译系统中。在大规模测试数据集上完成汉语到英语的翻译, 实验结果表明, 基于选择偏向性的翻译模型能 够很好地捕获长距离的语义依赖关系, 从而提高译文质量。 关键词 语义知识 ; 选择偏向性 ; 语义约束 ; 语义依赖 中图分类号 TP391 A Selectional Preference Based Translation Model for SMT TANG Haiqing, XIONG Deyi† School of Computer Science and Technology, Soochow University, Suzhou 215006; † Corresponding author, E-mail: dyxiong@ Abstract The limited semantic knowledge is used in the phrase-based statistical machine translation (SMT), which causes that the translation quality of long-distance verb and its object is low. A selectional preference based translation model is proposed, which inducts the semantic constraints that a verb imposes on its object to select the proper argument-head word for the predicate with long distance. The authors train the corpus to obtain the conditional probability based selectional preferences for verb, and integrate the selectional preferences into a phrase-based translation system and evaluate on a Chinese-to-English translation task with large-scale training data. Experiment results show that the integration of selectional pre