###
Journal of Software:2012.23(6):1472-1485

利用统计搭配模型改进基于实例的机器翻译
刘占一,李生,刘挺,王海峰
(哈尔滨工业大学 计算机科学与技术学院,黑龙江 哈尔滨 150001;百度公司,北京 100085)
Improving Example-Based Machine Translation with Statistical Collocation Model
LIU Zhan-Yi,LI Sheng,LIU Ting,WANG Hai-Feng
(School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China;Baidu.com, Inc, Beijing 100085, China)
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 2880   Download 3319
Received:September 26, 2010    Revised:May 25, 2011
> 中文摘要: 基于实例的机器翻译(example-based machine translation,简称EBMT)使用预处理过的双语例句作为主要翻译资源,通过编辑与待翻译句子匹配的翻译实例来生成译文.在EBMT系统中,翻译实例选择及译文选择对系统性能影响较大.提出利用统计搭配模型来增强EBMT 系统中翻译实例选择及译文选择的能力,提高译文质量.首先,使用单语统计词对齐从单语语料中训练统计搭配模型.然后,利用该模型从3 个方面提高EBMT 的性能:(1) 利用统计搭配模型估计待翻译句子与翻译实例之间的匹配度,从而增强系统的翻译实例选择能力;(2) 通过引入候选译文与上下文之间搭配强度的估计来提高译文选择能力;(3) 使用统计搭配模型检测翻译实例中被替换词的搭配词,同时根据新的替换词及上下文对搭配词进行矫正,进一步提高EBMT系统的译文质量.为了验证所提出的方法,在基于词的EBMT 系统上评价了英汉翻译的译文质量.与基线系统相比,所提出的方法使译文的BLEU 得分提高了4.73~6.48个百分点.在半结构化的EBMT系统上进一步检验了基于统计搭配模型的译文选择方法,从实验结果来看,该方法使译文的BLEU 得分提高了1.82 个百分点.同时,人工评价结果显示,改进后的半结构化EBMT 系统的译文能够表达原文的大部分信息,并且具有较高的流利度.
Abstract:Example-Based machine translation (EBMT) uses a preprocessed bilingual corpus as a main translation knowledge. The final translation is generated by editing examples that match the input sentence. In the EBMT system, the performances of example selection and translation selection heavily influence the quality of the final translation. This paper proposes a method to improve the performance of the EBMT method by using statistical collocation model, which is estimated from monolingual corpora, in three aspects. First, the statistical collocation model is used to estimate the matching degree between the input sentence and examples to improve the performance of the example selection. Second, the performance of translation selection is improved by evaluating the collocation strength of the translation candidates and the context. Third, the collocated words of the translation candidates in the example are detected by the statistical collocation model and then the collocated words are corrected according to the context. In order to evaluate the proposed method, this study conducts a series of experiments. First, the study evaluates the proposed methods in a word-based EBMT system. As compared with the baseline, the methods achieves absolute improvements of 4.73~6.48 BLEU score on English-to-Chinese translation. Then, the study also applies the proposed translation selection method to a semi-structured EBMT system, and the translation qualities are further improved, with an improvement of 1.82 BLEU score. The results of human evaluation show that the translations generated by the improved semi-structured EBMT system can express the majority of the meaning of source sentences, and the fluency of theses translations can also be accepted.
文章编号:     中图分类号:    文献标志码:
基金项目:核高基国家科技重大专项(2011ZX01042-001-001) 核高基国家科技重大专项(2011ZX01042-001-001)
Foundation items:
Reference text:

刘占一,李生,刘挺,王海峰.利用统计搭配模型改进基于实例的机器翻译.软件学报,2012,23(6):1472-1485

LIU Zhan-Yi,LI Sheng,LIU Ting,WANG Hai-Feng.Improving Example-Based Machine Translation with Statistical Collocation Model.Journal of Software,2012,23(6):1472-1485