English-Chinese OOV translation based on PAT Tree

In Cross-Language Information Retrieval (CLIR) process, Out-Of-Vocabulary (OOV) or the unknown word translation is a significant and challenging issue. Specifically, for English-Chinese OOV translation, OOV term detection and extraction of translation pair still remain to be key problems. In this paper, an English-Chinese OOV translation pattern based on PAT-Tree is proposed. Web-mining is utilized as the corpus source to collect translation pairs, and translation candidates are acquired by Chinese OOV term extraction based on PAT-Tree. The experimental results show that the proposed approach can outperform some of the current translation engines, and is especially efficient in English-Chinese OOV translation.