Abstract
In this paper, we study the discriminative modeling of Spoken Language Understanding (SLU) using Conditional Random Fields (CRF) and Statistical Machine Translation (SMT) alignment models. Previous discriminative approaches to SLU have been dependent on n-gram features. Other previous works have used SMT alignment models to predict the output labels. We have used SMT alignment models to align the abstract labels and trained CRF to predict the labels. We show that the state transition features improve the performance. Furthermore, we have compared the proposed method with two baseline approaches; Hidden Vector States (HVS) and baseline-CRF. The results show that for the F-measure the proposed method outperforms HVS by \(1.74\,\%\) and baseline-CRF by \(1.7\,\%\) on ATIS corpus.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The first author of [4] is Christian Raymond, so we name this alignment in such way.
- 2.
City names may contain more than one words and so the other labels, in this case the other words’ status will be cont, e.g. for the city name “Los Angeles”, “Los” is labeled as SR.ACity.start and “Angeles” is labeled as SR.ACity.cont.
References
Dahl, D.A., Bates, M., Brown, M., Fisher, W., Hunicke-Smith, K., Pallett, D., Pao, C., Rudnicky, A., Shriberg, E.: Expanding the scope of the atis task: the atis-3 corpus. In: Proceedings of the workshop on Human Language Technology, Association for Computational Linguistics, pp. 43–48 (1994)
Pieraccini, R., Tzoukermann, E., Gorelov, Z., Gauvain, J.L., Levin, E., Lee, C.H., Wilpon, J.G.: A speech understanding system based on statistical representation of semantics. In: IEEE International Conference on Acoustics, Speech, and Signal Processing 1992, ICASSP-92, vol. 1, pp. 193–196. IEEE (1992)
He, Y., Young, S.: Semantic processing using the hidden vector state model. Comput. Speech Lang. 19(1), 85–106 (2005)
Raymond, C., Riccardi, G.: Generative and discriminative algorithms for spoken language understanding. In: International Conference on Speech Communication and Technologies, Antwerp, Belgium, August 2007, pp. 1605–1608 (2007)
Wang, Y.Y., Acero, A.: Discriminative models for spoken language understanding. In: International Conference on Speech Communication and Technologies, Citeseer (2006)
Lafferty, J., McCallum, A., Pereira, F.C.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proceedings of 18th International Conference on Machine Learning, Morgan Kaufmann, pp. 282–289 (2001)
Pietra, S.D., Epstein, M., Roukos, S., Ward, T.: Fertility models for statistical natural language understanding. In: Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, pp. 168–173 (1997)
Macherey, K., Och, F.J., Ney, H.: Natural language understanding using statistical machine translation. In: INTERSPEECH, Citeseer, pp. 2205–2208 (2001)
Macherey, K., Bender, O., Ney, H.: Applications of statistical machine translation approaches to spoken language understanding. IEEE Trans. Audio Speech Lang. Process. 17(4), 803–818 (2009)
Brown, P.F., Pietra, V.J.D., Pietra, S.A.D., Mercer, R.L.: The mathematics of statistical machine translation: parameter estimation. Comput. Linguist. 19(2), 263–311 (1993)
Khadivi, S., Ney, H.: Automatic filtering of bilingual corpora for statistical machine translation. In: Montoyo, A., Muńoz, R., Métais, E. (eds.) NLDB 2005. LNCS, vol. 3513, pp. 263–274. Springer, Heidelberg (2005)
Vogel, S., Ney, H., Tillmann, C.: Hmm-based word alignment in statistical translation. In: Proceedings of the 16th conference on Computational Linguistics- Volume 2, Association for Computational Linguistics, pp. 836–841 (1996)
Khadivi, S., Zolnay, A., Ney, H.: Automatic text dictation in computer-assisted translation. In: International Conference on Speech Communication and Technologies, pp. 2265–2268 (2005)
Och, F.J., Ney, H.: Giza++: Training of statistical translation models (2000)
Kudo, T.: Crf++: Yet another crf toolkit. Software available at http://crfpp.sourceforge.net (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Aliannejadi, M., Khadivi, S., Ghidary, S.S., Bokaei, M.H. (2014). Discriminative Spoken Language Understanding Using Statistical Machine Translation Alignment Models. In: Movaghar, A., Jamzad, M., Asadi, H. (eds) Artificial Intelligence and Signal Processing. AISP 2013. Communications in Computer and Information Science, vol 427. Springer, Cham. https://doi.org/10.1007/978-3-319-10849-0_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-10849-0_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10848-3
Online ISBN: 978-3-319-10849-0
eBook Packages: Computer ScienceComputer Science (R0)