Phrase Alignment Based on Combination of Multiple Strategies

Phrase translation pairs are very useful for bilingual lexicography, machine translation system, crosslingual information retrieval and many applications in natural language processing. There is phrase boundary information in parsing trees of sentences. Linguistics knowledge in translation lexicon and semantic lexicon, and statistics results from bilingual corpus can be used to align Chinese words and English words, which will provide alignment information for extracting phrase translation pairs. In this paper, we propose a new method to extract phrase translation pairs based on aligning Chinese words and English words in bilingual corpus with multiple alignment strategies. Experimental results indicate that the extracted phrase translation pairs achieve 63.07% at accuracy, when the new method is applied.