Paper: Refinements in BTG-based Statistical Machine Translation

ACL ID I08-1066
Title Refinements in BTG-based Statistical Machine Translation
Venue International Joint Conference on Natural Language Processing
Session Main Conference
Year 2008

Bracketing Transduction Grammar (BTG) has been well studied and used in statistical machine translation (SMT) with promising results. However, there are two major issues for BTG-based SMT. First, there is no effec- tive mechanism available for predicting or- ders between neighboring blocks in the orig- inal BTG. Second, the computational cost is high. In this paper, we introduce two re- finements for BTG-based SMT to achieve better reordering and higher-speed decod- ing, which include (1) reordering heuristics to prevent incorrect swapping and reduce search space, and (2) special phrases with tags to indicate sentence beginning and end- ing. The two refinements are integrated into a well-established BTG-based Chinese-to- English SMT system that is trained on large- scale parallel data. Exp...