Abstract
Hierarchical phrase-based translation models have advanced statistical machine translation (SMT). Because such models can improve leveraging of syntactic information, two types of methods (leveraging source parsing and leveraging shallow parsing) are applied to introduce syntactic constraints into translation models. In this paper, we propose a bilingually-constrained recursive neural network (BC-RNN) model to combine the merits of these two types of methods. First we perform supervised learning on a manually parsed corpus using the standard recursive neural network (RNN) model. Then we employ unsupervised bilingually-constrained tuning to improve the accuracy of the standard RNN model. Leveraging the BC-RNN model, we introduce both source parsing and shallow parsing information into a hierarchical phrase-based translation model. The evaluation demonstrates that our proposed method outperforms other state-of-the-art statistical machine translation methods for National Institute of Standards and Technology 2008 (NIST 2008) Chinese-English machine translation testing data.
Preview
Unable to display preview. Download preview PDF.
References
Chiang, D.: Hierarchical phrase-based translation. Computational Linguistics 33(2), 201–228 (2007)
Cherry, C.: Cohesive phrase-based decoding for statistical machine translation. In: ACL 2008, pp. 72–80 (2008)
Liu, Y., Liu, Q.: Joint parsing and translation. In: ACL 2010, pp. 707–715 (2010)
Tamura, A., Watanabe, T., Sumita, E., et al.: Part-of-speech induction in dependency trees for statistical machine translation. In: ACL (1) 2013 (2013)
Watanabe, T., Sumita, E., Okuno, H.G.: Chunk-based statistical translation. In: ACL 2003, pp. 303–310 (2003)
Feng, Y., Zhang, D., Li, M., et al.: Hierarchical chunk-to-string translation. In: Association for computational linguistics 2012, pp. 950–958 (2012)
Socher, R., Manning, C.D., Ng, A.Y.: Learning continuous phrase representations and syntactic parsing with recursive neural networks. In: NIPS-2010 Deep Learning and Unsupervised Feature Learning Workshop 2010, pp. 1–9 (2010)
Mikolov, T., et al.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems 2013 (2013)
Zhang, J., Liu, S., Li, M., Zhou, M., Zong, C.: Bilingually-constrained phrase embeddings for machine translation. In: EMNLP 2014 (2014)
Och, F.J., Ney, H.: Improved statistical alignment models. In: Proceedings of ACL, pp. 440–447 (2000)
Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: Proceedings of the 2003 NAACL (2003)
Chiang, D.: A hierarchical phrase-based model for statistical machine translation. In: ACL 2005 (2005)
Liu, Y., Liu, Q., Lin, S.: Tree-to-string alignment template for statistical machine translation. In: ACL 2006 (2006)
Och, F.J.: Minimum error rate training in statistical machine translation. In: ACL 2003 (2003)
Manning, C.D., Carpenter, B.: Probabilistic parsing using left corner language models. In: 5th ACL International Workshop (1997)
Klein, D., Manning, C.D.: Accurate unlexicalized parsing. In: ACL, pp. 423–430 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Chen, W., Xu, B. (2015). Bilingually-Constrained Recursive Neural Networks with Syntactic Constraints for Hierarchical Translation Model. In: Li, J., Ji, H., Zhao, D., Feng, Y. (eds) Natural Language Processing and Chinese Computing. NLPCC 2015. Lecture Notes in Computer Science(), vol 9362. Springer, Cham. https://doi.org/10.1007/978-3-319-25207-0_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-25207-0_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25206-3
Online ISBN: 978-3-319-25207-0
eBook Packages: Computer ScienceComputer Science (R0)