Discriminative Reordering Model Adaptation via Structural Learning

Reordering model adaptation remains a big challenge in statistical machine translation because reordering patterns of translation units often vary dramatically from one domain to another. In this paper, we propose a novel adaptive discriminative reordering model (DRM) based on structural learning, which can capture correspondences among reordering features from two different domains. Exploiting both in-domain and out-of-domain monolingual corpora, our model learns a shared feature representation for cross-domain phrase reordering. Incorporating features of this representation, the DRM trained on out-of-domain corpus generalizes better to in-domain data. Experiment results on the NIST Chinese-English translation task show that our approach significantly outperforms a variety of baselines.

Authors

• Biao Zhang
• Jinsong Su School of Informatics, Xiamen University, China Shanghai Artificial Intelligence Laboratory, China Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, China
• Deyi Xiong Tianjin University
• Hong Duan
• Junfeng Yao School of Film, Xiamen University, Xiamen, China School of Informatics, Xiamen University, Xiamen, China Institute of Artificial Intelligence, Xiamen University, Xiamen, China Xiamen Key Laboratory of Intelligent Storage and Computing, School of Informatics, Xiamen University

Keywords

No keywords are indexed for this paper.