基于双语依存关系映射的中英文词表构建研究  

Research on Bilingual Dependency Relationship Mapping for Chinese-English Lexicon Construction

作　　者：徐华 刘丹丹 钱龙华 周国栋 

机构地区：[1]苏州大学自然语言处理实验室,苏州大学计算机科学与技术学院,江苏苏州215006

出　　处：《中文信息学报》2013年第1期15-20,共6页Journal of Chinese Information Processing

基　　金：国家自然科学基金资助项目(60873150,90920004,61003153);江苏省自然科学基金资助项目(BK2010219)

摘　　要：基于上下文的双语词表构建方法是比较流行的基于可比较双语语料库的双语词表构建方法。特别地,依存上下文模型从句子的依存树上抽取词语的上下文特征,由于依存关系更能体现词语之间的共现关系,因而这种方法提高了构建双语词表的性能。该文在此基础上,进一步提出了依存关系映射模型,即通过同时匹配依存树中的上下文词语、依存关系类型和方向来实现双语词表的构建。在FBIS语料库上的实验表明,该方法在中文—英文和英文—中文两个方向上的双语词表构建上均取得了较好的性能,这说明了依存关系映射模型在双语词表构建中的有效性。Currently contextbased approach is a popular approach for constructing bilingual lexicons from compara ble bilingual corpora. Specifically, the dependency context model extracts context features from a sentence＇s depend ency tree. This model improves the performance of the bilingual lexicon construction since dependency relationships can better capture the cooccurrence relationship between words. Following this line, this paper further proposes a dependency relationship mapping model, which constructs bilingual lexicon by mapping dependency context words, dependency relationship types and directions simultaneously. The experiments on the FBIS corpus show that, our approach significantly outperforms a stateoftheart system in bilingual lexicon construction from both ChineseEng lish and EnglishChinese. This justifies the effectiveness of our dependency relationship mapping model on bilingual lexicon construction.

关 键 词：双语词表构建 依存上下文模型 依存关系映射 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]