Abstract
Recent work has shown the effectiveness of neural probabilistic language models(NPLMs) in statistical machine translation(SMT) through both reranking the n-best outputs and direct decoding. However there are still some issues remained for application of NPLMs. In this paper we further investigate through detailed experiments and extension of state-of-art NPLMs. Our experiments on large-scale datasets show that our final setting, i.e., decoding with conventional n-gram LMs plus un-normalized feedforward NPLMs extended with word clusters could significantly improve the translation performance by up to averaged 1.1 Bleu on four test datasets, while decoding time is acceptable. And results also show that current NPLMs, including feedforward and RNN still cannot simply replace n-gram LMs for SMT.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Auli, M., Galley, M., Quirk, C., Zweig, G.: Joint language and translation modeling with recurrent neural networks. In: Proceedings of the 2013 Conference on EMNLP, pp. 1044–1054 (2013)
Bengio, Y., Ducharme, R., Vincent, P., Jauvin, C.: A neural probabilistic language model. Journal of Machine Learning Research (2003)
Brown, P.F., Desouza, P.V., Mercer, R.L., Pietra, V.J.D., Lai, J.C.: Class-based n-gram models of natural language. Computational Linguistics 18(4), 467–479 (1992)
Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. Tech. Rep. TR-10-98, Harvard University Center for Research in Computing Technology (1998)
Chiang, D.: Hierarchical phrase-based translation. Computational Linguistics 33(2), 201–228 (2007)
Clark, J.H., Dyer, C., Lavie, A., Smith, N.A.: Better Hypothesis Testing for Statistical Machine Translation: Controlling for Optimizer Instability. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Oregon, USA, pp. 176–181. Association for Computational Linguistics (June 2011), http://www.aclweb.org/anthology/P11-2031
Devlin, J., Zbib, R., Huang, Z., Lamar, T., Schwartz, R., Makhoul, J.: Fast and robust neural network joint models for statistical machine translation. In: Proceedings of the ACL, Association for Computational Linguistics, Baltimore (2014)
Gutmann, M., Hyvärinen, A.: Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In: Proceedings of AISTATS (2010)
Le, H.S., Allauzen, A., Yvon, F.: Measuring the influence of long range dependencies with neural network language models. In: Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT, Montréal, Canada (2012)
Mikolov, T.: Statistical Language Models Based on Neural Networks. Ph.D. thesis, Brno University of Technology (2012)
Mikolov, T., Deoras, A., Kombrink, S., Burget, L., Černocký, J.H.: Empirical evaluation and combination of advanced language modeling techniques. In: Proceedings of INTERSPEECH, pp. 605–608 (2011)
Mikolov, T., Karafiát, M., Burget, L., Černocký, J.H., Khudanpur, S.: Recurrent neural network based language model. In: Proceedings of INTERSPEECH (2010)
Mnih, A., Hinton, G.: Three new graphical models for statistical language modelling. In: Proceedings of ICML (2007)
Mnih, A., Hinton, G.: A scalable hierarchical distributed language model. In: NIPS (2009)
Mnih, A., Teh, Y.W.: A fast and simple algorithm for training neural probabilistic language models. In: Proceedings of the 29th ICML, pp. 1751–1758 (2012)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of ICML, pp. 807–814 (2010)
Niehues, J., Waibel, A.: Continuous space language models using Restricted Boltzmann Machines. In: Proceedings of IWSLT (2012)
Och, F.J.: Minimum error rate training in statistical machine translation. In: Proceedings of ACL, pp. 160–167 (2003)
Och, F.J., Ney, H.: A systematic comparison of various statistical alignment models. Computational Linguistics 29(1), 19–51 (2003)
Ramabhadran, B., Khudanpur, S., Arisoy, E. (eds.): Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT, Montréal, Canada (June 2012)
Schwenk, H.: Continuous space language models. Computer Speech and Language 21, 492–518 (2007)
Schwenk, H.: Continuous-space language models for statistical machine translation. Prague Bulletin of Mathematical Linguistics 93, 137–146 (2010)
Sundermeyer, M., Oparin, I., Gauvain, J.L., Freiberg, B., Schluter, R., Ney, H.: Comparison of feedforward and recurrent neural network language models. In: Proceedings of ICASSP (2013)
Vaswani, A., Zhao, Y., Fossum, V., Chiang, D.: Decoding with large-scale neural language models improves translation. In: Proceedings of the 2013 Conference on EMNLP, pp. 1387–1392.
Wu, Y., Lu, X., Yamamoto, H., Matsuda, S., Hori, C., Kashioka, H.: Factored language model based on recurrent neural network. In: Proceedings of COLING 2012, Mumbai, India, pp. 2835–2850 (December 2012)
Wuebker, J., Peitz, S., Rietig, F., Ney, H.: Improving statistical machine translation with word class models. In: Proceedings of EMNLP, pp. 1377–1381 (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Zhao, Y., Huang, S., Chen, H., Chen, J. (2014). An Investigation on Statistical Machine Translation with Neural Language Models. In: Sun, M., Liu, Y., Zhao, J. (eds) Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. NLP-NABD CCL 2014 2014. Lecture Notes in Computer Science(), vol 8801. Springer, Cham. https://doi.org/10.1007/978-3-319-12277-9_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-12277-9_16
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12276-2
Online ISBN: 978-3-319-12277-9
eBook Packages: Computer ScienceComputer Science (R0)