Extending CCG-based Syntactic Constraints in Hierarchical Phrase-Based SMT
Hala Almaghout, Jie Jiang, Andy Way · 2012
In this paper, we describe two approaches to extending syntactic constraints in the Hierarchical Phrase-Based (HPB) Statistical Machine Translation (SMT) model using Combinatory Categorial Grammar (CCG). These extensions target the limitations of previous syntax-augmented HPB SMT systems which limit the coverage of the syntactic constraints applied. We present experiments on Arabic‐English and Chinese‐English translation. Our experiments show that using extended CCG labels helps to increase nonterminal label coverage and achieve significant improvements over the baseline for Arabic‐ English translation. In addition, combining extended CCG labels with CCGaugmented glue grammar helps to improve the performance of the Chinese‐English translation over the baseline systems.