Integrating a Phrase-based SMT Model and a Bilingual Lexicon for Human in Semi-Automatic Acquisition of Technical Term Translation Lexicon

This paper presents an attempt at develop-ing a technique of acquiring translation pairs of technical terms with sufficiently high pre-cision from parallel patent documents. The approach taken in the proposed technique is based on integrating the phrase translation table of a state-of-the-art statistical phrase-based machine translation model, and compo-sitional translation generation based on an ex-isting bilingual lexicon for human use. Our evaluation results clearly show that the agree-ment between the two individual techniques definitely contribute to improving precision of translation candidates. We then apply the Support Vector Machines (SVMs) to the task of automatically validating translation candi-dates in the phrase translation table. Experi-mental evaluation results again show that the SVMs based approach to translation candi-dates validation can contribute to improving the precision of translation candidates in the phrase translation table.