Abstract
In this paper, we propose a novel derivation structure prediction (DSP) model for SMT using recursive neural network (RNN). Within the model, two steps are involved: (1) phrase-pair vector representation, to learn vector representations for phrase pairs; (2) derivation structure prediction, to generate a bilingual RNN that aims to distinguish good derivation structures from bad ones. Final experimental results show that our DSP model can significantly improve the translation quality. © 2014 Association for Computational Linguistics.
Cite
CITATION STYLE
Zhai, F., Zhang, J., Zhou, Y., & Zong, C. (2014). RNN-based derivation structure prediction for SMT. In 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference (Vol. 2, pp. 779–784). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/p14-2126
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
