Abstract
There are two main strategies to adapt a Spoken Language Understanding system to deal with languages different from the original (source) language: test-on-source and train-on-target. In the train-on-target approach, a new understanding model is trained in the target language, which is the language in which the test utterances are pronounced. To do this, a segmented and semantically labeled training set for each new language is needed. In this work, we use several general-purpose translators to obtain the translation of the training set and we apply an alignment process to automatically segment the training sentences. We have applied this train-on-target approach to estimate the understanding module of a Spoken Dialog System for the DIHANA task, which consists of an information system about train timetables and fares in Spanish. We present an evaluation of our train-on-target multilingual approach for two target languages, French and English.
This work has been partially funded by the project ASLP-MULAN: Audio, Speech and Language Processing for Multimedia Analytics (MEC TIN2014-54288-C4-3-R).
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
Similar content being viewed by others
References
Benedí, J.M., Lleida, E., Varona, A., Castro, M.J., Galiano, I., Justo, R., López de Letona, I., Miguel, A.: Design and acquisition of a telephone spontaneous speech dialogue corpus in Spanish: DIHANA. In: LREC 2006, pp. 1636–1639 (2006)
Calvo, M., Hurtado, L.-F., García, F., Sanchís, E.: A Multilingual SLU system based on semantic decoding of graphs of words. In: Torre Toledano, D., Ortega Giménez, A., Teixeira, A., González Rodríguez, J., Hernández Gómez, L., San Segundo Hernández, R., Ramos Castro, D. (eds.) IberSPEECH 2012. CCIS, vol. 328, pp. 158–167. Springer, Heidelberg (2012). doi:10.1007/978-3-642-35292-8_17
Calvo, M., Hurtado, L.F., Garca, F., Sanchis, E., Segarra, E.: Multilingual spoken language understanding using graphs and multiple translations. Comput. Speech Lang. 38, 86–103 (2016)
Dinarelli, M., Moschitti, A., Riccardi, G.: Concept segmentation and labeling for conversational speech. In: Interspeech, Brighton, UK (2009)
Esteve, Y., Raymond, C., Bechet, F., Mori, R.D.: Conceptual decoding for spoken dialog systems. In: Proceedings of EuroSpeech 2003, pp. 617–620 (2003)
García, F., Hurtado, L., Segarra, E., Sanchis, E., Riccardi, G.: Combining multiple translation systems for spoken language understanding portability. In: Proceedings of IEEE Workshop on Spoken Language Technology (SLT), pp. 282–289 (2012)
Hahn, S., Dinarelli, M., Raymond, C., Lefèvre, F., Lehnen, P., De Mori, R., Moschitti, A., Ney, H., Riccardi, G.: Comparing stochastic approaches to spoken language understanding in multiple languages. IEEE Trans. Audio Speech Lang. Process. 6(99), 1569–1583 (2010)
He, Y., Young, S.: A data-driven spoken language understanding system. In: Proceedings of ASRU 2003, pp. 583–588 (2003)
Hurtado, L., Segarra, E., García, F., Sanchis, E.: Language understanding using n-multigram models. In: Vicedo, J.L., Martínez-Barco, P., Muńoz, R., Saiz Noeda, M. (eds.) EsTAL 2004. LNCS (LNAI), vol. 3230, pp. 207–219. Springer, Heidelberg (2004). doi:10.1007/978-3-540-30228-5_19
Jabaian, B., Besacier, L., Lefèvre, F.: Comparison and combination of lightly supervised approaches for language portability of a spoken language understanding system. IEEE Trans. Audio Speech Lang. Process. 21(3), 636–648 (2013)
Koehn, P., et al.: Moses: open source toolkit for statistical machine translation. In: Proceedings of ACL Demonstration Session, pp. 177–180 (2007)
Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: International Conference on Machine Learning, pp. 282–289. Citeseer (2001)
Lefèvre, F.: Dynamic Bayesian networks and discriminative classifiers for multi-stage semantic interpretation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2007, vol. 4, pp. 13–16. IEEE (2007)
Ortega, L., Galiano, I., Hurtado, L.F., Sanchis, E., Segarra, E.: A statistical segment-based approach for spoken language understanding. In: Proceedings of InterSpeech 2010, Makuhari, Chiba, Japan, pp. 1836–1839 (2010)
Segarra, E., Sanchis, E., Galiano, M., García, F., Hurtado, L.: Extracting semantic information through automatic learning techniques. IJPRAI 16(3), 301–307 (2002)
Servan, C., Camelin, N., Raymond, C., Bchet, F., Mori, R.D.: On the use of machine translation for spoken language understanding portability. In: Proceedings of ICASSP 2010, pp. 5330–5333 (2010)
Tür, G., Mori, R.D.: Spoken Language Understanding: Systems for Extracting Semantic Information from Speech, 1st edn. Wiley, Hoboken (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
García-Granada, F., Segarra, E., Millán, C., Sanchis, E., Hurtado, LF. (2016). A Train-on-Target Strategy for Multilingual Spoken Language Understanding. In: Abad, A., et al. Advances in Speech and Language Technologies for Iberian Languages. IberSPEECH 2016. Lecture Notes in Computer Science(), vol 10077. Springer, Cham. https://doi.org/10.1007/978-3-319-49169-1_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-49169-1_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49168-4
Online ISBN: 978-3-319-49169-1
eBook Packages: Computer ScienceComputer Science (R0)