A Discriminative Latent Variable-Based "DE" Classifier for Chinese-English SMT

Syntactic reordering on the source-side is an effective way of handling word order differences. The (DE) construction is a flexible and ubiquitous syntactic structure in Chinese which is a major source of error in translation quality. In this paper, we propose a new classifier model -- discriminative latent variable model (DPLVM) -- to classify the DE construction to improve the accuracy of the classification and hence the translation quality. We also propose a new feature which can automatically learn the reordering rules to a certain extent. The experimental results show that the MT systems using the data reordered by our proposed model outperform the baseline systems by 6.42% and 3.08% relative points in terms of the BLEU score on PB-SMT and hierarchical phrase-based MT respectively. In addition, we analyse the impact of DE annotation on word alignment and on the SMT phrase table.

• Type: Journal
• Year: 2010
• Where: COLING
• Authors: Jinhua Du, Andy Way
• Keywords: COLING 2010, Computational Linguistics, Translation Quality, Ubiquitous Syntactic Structure, Word Order Differences