Synchronous Constituent Context Model for Inducing Bilingual Synchronous Structures

Traditional Statistical Machine Translation (SMT) systems heuristically extract synchronous structures from word alignments, while synchronous grammar induction provides better solutions that can discard heuristic method and directly obtain statistically sound bilingual synchronous structures. This paper proposes Synchronous Constituent Context Model (SCCM) for synchronous grammar induction. The SCCM is different to all previous synchronous grammar induction systems in that the SCCM does not use the Context Free Grammars to model the bilingual parallel corpus, but models bilingual constituents and contexts directly. The experiments show that valuable synchronous structures can be found by the SCCM, and the end-to-end machine translation experiment shows that the SCCM improves the quality of SMT results.