Building a Bilingual Lexicon Using Phrase-based Statistical Machine Translation via a Pivot Language
Takashi Tsunakawa, Naoaki Okazaki · 2013
This paper proposes a novel method for building a bilingual lexicon through a pivot language by using phrase-based statisti-cal machine translation (SMT). Given two bilingual lexicons between language pairs Lf–Lp and Lp–Le, we assume these lexi-cons as parallel corpora. Then, we merge the extracted two phrase tables into one phrase table between Lf and Le. Fi-nally, we construct a phrase-based SMT system for translating the terms in the lex-icon Lf–Lp into terms of Le and, ob-tain a new lexicon Lf–Le. In our experi-ments with Chinese-English and Japanese-English lexicons, our system could cover 72.8 % of Chinese terms and drastically im-prove the utilization ratio. 1