Improving English-to-Chinese Translation for Technical Terms Using Morphological Information
Xianchao Wu, See Profile, Xianchao Wu, Naoaki Okazaki, Takashi Tsunakawa · 2008
The continuous emergence of new techni-cal terms and the difficulty of keeping up with neologism in parallel corpora deterio-rate the performance of statistical machine translation (SMT) systems. This paper ex-plores the use of morphological information to improve English-to-Chinese translation for technical terms. To reduce the morpheme-level translation ambiguity, we group the mor-phemes into morpheme phrases and propose the use of domain information for translation candidate selection. In order to find corre-spondences of morpheme phrases between the source and target languages, we propose an al-gorithm to mine morpheme phrase translation pairs from a bilingual lexicon. We also build a cascaded translation model that dynamically shifts translation units from phrase level to word and morpheme phrase levels. The exper-imental results show the significant improve-ments over the current phrase-based SMT sys-tems. 1