Paper: Improving Statistical Machine Translation using Lexicalized Rule Selection

ACL ID C08-1041
Title Improving Statistical Machine Translation using Lexicalized Rule Selection
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2008
Authors

This paper proposes a novel lexicalized ap- proach for rule selection for syntax-based statistical machine translation (SMT). We build maximum entropy (MaxEnt) mod- els which combine rich context informa- tion for selecting translation rules dur- ing decoding. We successfully integrate the MaxEnt-based rule selection models into the state-of-the-art syntax-based SMT model. Experiments show that our lexical- ized approach for rule selection achieves statistically significant improvements over the state-of-the-art SMT system.