Translation phrase pair generation apparatus, statistical machine translation apparatus, translation phrase pair generation method, statistical machine translation method, translation phrase pair generation program, statistical machine translation program, and storage medium

摘要

PPROBLEM TO BE SOLVED: To form a phrase pair such that accurate translation can be performed even any learning data. PSOLUTION: A computer executes a procedure for forming a non-normalized first word correspondence from a non-normalized first bilingual corpus and forming a normalized second word correspondence from a normalized second bilingual corpus; and a procedure for extracting a first phrase pair 17c from the first bilingual corpus and the first word correspondence, extracting a second phrase pair 17d from the first bilingual corpus and the second word correspondence, extracting a third phrase pair 17e from the second bilingual corpus and the first word correspondence, extracting a fourth phrase pair 17f from the second bilingual corpus and the second word correspondence, scoring each of the pairs, and storing the scored pairs in a phrase table 19c. PCOPYRIGHT: (C)2008,JPO&INPIT