AAAI Publications, Twenty-Fourth International Joint Conference on Artificial Intelligence

Font Size: 
Discriminative Reordering Model Adaptation via Structural Learning
Biao Zhang, Jinsong Su, Deyi Xiong, Hong Duan, Junfeng Yao

Last modified: 2015-06-23


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.

Full Text: PDF