【摘要】 中文术语及未登录词的翻译是机器翻译、跨语言检索中的一个重要问题,这些翻译很难从现有的词典中获取。提出了一种通过搜索引擎从网页中自动获取中文术语英文翻译的方法。通过术语的部分翻译信息,构造出3种查询项模式,提出了多特征的翻译抽取方法。针对传统方法结果准确率不高、候选翻译干扰项多的问题,提出端类比对齐验证、双语对齐度验证、构词法验证3种验证模型来对候选翻译进行有效验证。实验结果表明,获取的双语翻译对准确率高,TOP1的准确率达到97.4%,TOP3的准确率达到98.3%。更多还原

【Abstract】 Extracting translation of Chinese term and oov words is an important problem in many applications such as machine translation and cross-language information retrieval.However,these translations are difficult to access from traditional dictionary.This paper proposed a method to automatically extract English translation of Chinese term from Web by search engine.It constructs three query modes using the partial translation of terms,proposes multi-featured extraction method.Aim at the problem of low accuracy and unrelated translations,it verifies the candidate translations by three verification modes:side analog alignment verification,Bilingual alignment degree verification and word-building verification.Experimental results show that TOP1 accuracy arrives 97.4% and TOP3 98.3%.更多还原