This paper proposes a novel method for building a bilingual lexicon through a pivot language by using phrase-based statistical machine translation (SMT). Given two bilingual lexicons between language pairs Lf-Lp and Lp-Le, we assume these lexicons as parallel corpora. Then, we merge the extracted two phrase tables into one phrase table between Lf and Le. Finally, we construct a phrase-based SMT system for translating the terms in the lexicon Lf-Lp into terms of Le and, obtain a new lexicon Lf-Le. In our experiments with Chinese-English and Japanese-English lexicons, our system could cover 72.8% of Chinese terms and drastically improve the utilization ratio.