Improving Statistical Machine Translation using Lexicalized Rule Selection

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.

• Type: Conference
• Year: 2008
• Where: COLING
• Authors: Zhongjun He, Qun Liu, Shouxun Lin
• Keywords: COLING 2008, Computational Linguistics, Lexicalized Approach, Rule Selection, State-of-the-art Syntax-based Smt