We investigated using the LDC English/Chinese bilingual wordlists for English-Chinese cross language retrieval. It is shown that the Chinese-to-English wordlist can be considered as both a phrase and word dictionary, and is preferable to the English-to-Chinese version in terms of phrase translations and word translation selection. Additional techniques such as target corpus frequency-based term selection and weighting were employed. Experiments show that over 70% of monolingual effectiveness is achievable for the TREC Chinese corpus and retrieval environment with short queries of a few English words.
我们调查了使用LDC的英汉双语单词表进行英汉跨语言检索的情况。结果表明,汉英单词表既可以看作是短语,也可以看作是单词词典,在短语翻译和单词翻译选择方面比英汉翻译更好。采用了其他技术,例如基于目标语料库频率的术语选择和加权。实验表明,对于TREC汉语语料库和检索环境,只需几个英文单词的简短查询,就能达到70%的单语有效性。 P>
Computer Science Department, Queens College, City University of New York, Flushing, NY;
cross language information retrieval;
机译:汉英双语者的跨语言翻译启动不对称:感官模型的检验
机译:英汉跨语言信息检索的混合技术
机译:英汉跨语言信息检索的词汇知识库方法
机译:利用汉英双语单词表进行英汉跨语言信息检索
机译:理解双语词汇组织:中英双语者掩盖的跨语言启动证据。
机译:语言转换中的双语认知控制:英汉后期双语者的功能磁共振成像研究
机译:利用LDC汉英双语单词表进行跨语言信息检索
机译:使用双语词典的英汉跨语言交际