Most researchers extracted candidate term using unsupervised method. In this paper, a supervised candidate term extraction method is proposed It combines English Part of Speech and headword expansion chunking strategy. Firstly, it retrieves bilingual snippets from web by term expansion, then, crawls Chinese-English pages and screens out Chinese words from the Chinese-English pages, lastly, a headword expansion chunking strategy is used to identify English phrases and the English Noun phrases and Verb phrases are selected These selected English phrases serve as the last candidate term for term translation mining. Experimental results show that the supervised candidate term extraction method improves the top 10 inclusion rate by 1.6% than baseline system, which verifies that the supervised candidate term extraction method is effective.
展开▼