Sampling-based Alignment and Hierarchical Sub-sentential Alignment in Chinese-Japanese Translation of Patents

摘要

This paper describes Chinese-Japanese translation systems based on different alignment methods using the JPO corpus and our submission (ID: WASUIPS) to the subtask of the 2015 Workshop on Asian Translation. One of the alignment methods used is bilingual hierarchical sub-sentential alignment combined with sampling-based multilingual alignment. We also accelerated this method and in this paper, we evaluate the translation results and time spent on several machine translation tasks. The training time is much faster than the standard baseline pipeline (GIZA++/Moses) and MGIZA/Moses.