Integrating Phrase-based Reordering Features into Chart-based Decoder for Machine Translation
thuylinh nguyen and Stephan Vogel
The 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013)
Sofia, Bulgaria, August 4-9, 2013
Hiero translation models have two limitations compared to phrase-based models: 1)Limited hypothesis space; 2) No lexicalized reordering model. We propose an extension of Hiero called Phrasal-Hiero to address Hiero's second problem. Phrasal-Hiero still has the same hypothesis space as the original Hiero but incorporates a phrase-based distance cost feature and lexicalized reodering features into the chart decoder. The work consists of two parts: 1) for each Hiero translation derivation, find its corresponding discontinuous phrase-based path. 2) Extend the chart decoder to incorporate features from the phrase-based path. We achieve significant improvement over both Hiero and phrase-based baselines for Arabic-English, Chinese-English and German-English translation.
Conference Manager (V2.61.0 - Rev. 2792M)