Extracting Chinese-English Bilingual Core Terminology from Parallel Classified Corpora in Special Domain
Extracting Chinese-English Bilingual Core Terminology from Parallel Classified Corpora in Special Domain
复制标题
DOI：
10.1109/wi-iat.2009.280
复制
发表时间：
2009-09
期刊：
影响因子：
--
通讯作者：
Chengzhi Zhang
中科院分区：
文献类型：
--
作者：
Chengzhi Zhang
双语核心术语是双语术语抽取的关键资源。本文利用特定领域文档的关键词列表来抽取候选核心术语。经过关键词提取和术语组计算，分别从分类后的专业领域语料库中提取核心术语。然后，采用双语术语对齐方法，从平行分类语料库中提取特定领域的双语核心术语。实验结果表明，该方法可以快速有效地提取汉英核心术语。
The bilingual core terminology is the key resource for bilingual terminology extraction. In this paper, the keywords lists of the document in special domain are used to extract the candidate core terminology. After the keywords extraction and termhood computation, the core terminologies are extracted from the classified corpora in special domain respectively. Then, the bilingual terminology alignment method is used to extract the bilingual core terminology from the parallel classified corpora in special domain. The experiment result shows that the proposed method can be used to extract the Chinese-English core terminology quickly and efficiently.