The English Unknown Term Translation Mining with Improved Bilingual Snippets Collection Strategy

摘要

Most researchers selected the top N snippets returned from web search engine as bilingual corpora. In this paper, an improved bilingual snippets retrieval method is proposed. It combines term expansion, the surface pattern matching model and top N bilingual snippets selection to retrieve bilingual snippets. Firstly, it retrieves bilingual snippets from web by term expansion, then, screens out some bilingual snippets that satisfy the surface pattern matching model, lastly, selects top 100 bilingual snippets from the bilingual snippets that do not satisfy the surface pattern matching model. The top 100 bilingual snippets and those satisfy' the surface pattern matching model serve as the last bilingual corpora for term translation mining. Experimental results show that the improved bilingual snippets retrieving method improves the top 100 inclusion rate by 2.3% than baseline system, which verified that the improved bilingual snippets retrieving method is effective.