Improving statistical machine translation using lexicalized rule selection

Abstract

This paper proposes a novel lexicalized approach for rule selection for syntax-based statistical machine translation (SMT). We build maximum entropy (MaxEnt) models which combine rich context information for selecting translation rules during decoding. We successfully integrate the MaxEnt-based rule selection models into the state-of-the-art syntax-based SMT model. Experiments show that our lexicalized approach for rule selection achieves statistically significant improvements over the state-of-the-art SMT system. © 2008 Licensed under the Creative Commons.