Abstract
The authors explore the fast query techniques for n-gram language model (LM) in statistical machine translation (SMT), and then propose a compact WFSA (weighted finite-state automaton) based LM motivated by the contextual features in process of model queries. It is demonstrated that the query based on WFSA can effectively avoid the redundant queries and accelerate the query speed. Furthermore, it is revealed that investigating a simple caching techni que can further speed up the query. The experiment results show that this method can finally speed up the LM query by 75% in relative. With the LM order increasing, the performance benefits by WFSA will be much more significant.
This work was supported by 863 program in China (No. 2011AA01A207).
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
Thorsten, B., Popat, A.C., Peng, X., Franz, J.O., Jeffrey, D.: Large Language Models in Machine Translation. In: Proceedings of EMNLP-CoNLL, pp. 858–867 (2007)
Goodman, J.: A Bit of Progress in Language Modeling. Technical report. Microsoft Research (2001)
Marcello, F., Mauro, C.: Efficient handling of n-gram language models for statis tical machine translation. In: Proceedings of the 2nd Workshop on Statistical Machine Translation, pp. 88–95 (2007)
David, T., Miles, O.: Randomised language modelling for statistical machine translation. In: Proceedings of the ACL, pp. 512–519 (2007)
Kevin, K., Jonathan, G.: An overview of probabilistic tree transducers for na tural language processing. In: Proceedings of CICLing (2005)
David, C., Jonathan, G., Kevin, K., Adam, P., Sujith, R.: Bayesian inference for Finite-State transducers. In: Proceedings of the NAACL, pp. 447–455 (2010)
Adam, P., Dan, K.: Faster and Smaller N-Gram Language Models. In: Proceedings of the ACL, pp. 258–267 (2011)
Zhifei, L., Sanjeev, K.: A scalable decoder for parsing- based machine translation with equivalent language model state maintenance. In: Proceedings of the Second Workshop on Syntax and Structure in Statistical Translation, pp. 10–18 (2008)
Kenneth, H.: KenLM: Faster and Smaller Language Model Queries. In: Proceedings of the 6th Workshop on Statistical Machine Translation, pp. 187–197 (2011)
Lambert, M., William, B.: Statistical phrase-based speech translation. In: Proceedings of ICASSP (2006)
Okan, K., Willian, B., Philip, R.: A generative probabilistic OCR model for NLP applications. In: Proceedings of the HLT-NAACL (2003)
Alexis, N., Yannick, E., Frédéric, B., Thierry, S., de Renato, M.: A language model combining N-grams and stochastic finite state automata. In: Proceedings of Eurospeech (1999)
Reinhard, K., Hermann, N.: Improved backing-off for m-gram language modeling. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 181–184 (1995)
Slava, M.K.: Estimation of probabilities from sparse data for the language model component of a speech recognizer. IEEE Transactions on Acoustics, Speech and Signal Processing, 400–401 (1987)
Andreas, S.: SRILM: An extensible language modeling toolkit. In: Proceedings of Interspeech (2002)
Edward, W., Bhiksha, R.: Quantization based language model compression. In: Proceedings of Eurospeech (2001)
David, C.: A hierarchical phrase-based model for statistical machine translation. In: Proceedings of ACL, pp. 263–270 (2005)
David, C.: Hierarchical phrase-based translation. Computational Linguistics 33(2), 201–228 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fu, X., Wei, W., Lu, S., Ke, D., Xu, B. (2012). Compact WFSA Based Language Model and Its Application in Statistical Machine Translation. In: Zhou, M., Zhou, G., Zhao, D., Liu, Q., Zou, L. (eds) Natural Language Processing and Chinese Computing. NLPCC 2012. Communications in Computer and Information Science, vol 333. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34456-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-34456-5_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34455-8
Online ISBN: 978-3-642-34456-5
eBook Packages: Computer ScienceComputer Science (R0)