Clarification Question Generation for Speech Recognition Error Recovery Using Monolingual SMT

Abstract:

Clarification dialogue is an efficient and direct way of handling speech recognition errors in speech interface applications. In this paper we present a new approach to Clarification Question (CQ) generation. Monolingual phrase-based SMT (PB-SMT) framework is introduced to generate robust and flexible CQs. A parallel corpus from simulated error to manually annotated CQ is established and used for training the model. A new type of generalized phrase pair is expanded from conventional translation phrase table. Combining both generalized and conventional phrase pairs, a two-step decoding process is carried out to generate CQs. Both manually and automatic metrics are used to evaluate the quality of generated CQs. Experimental results show that our method can effectively generate reasonable CQs form miss-recognized utterances, and generated CQs can be used to prompt a clarification dialogue for error handling.

• Periodical: Advanced Materials Research (Volumes 756-759)
• Pages: 1072-1077
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.756-759.1072
• Online since: September 2013
• Authors: Dong Yu
• Keywords: Clarification Dialogue, Monolingual SMT, Question Generation, Speech Recognition Error Recovery

References

[1] Schlangen D., Causes and Strategies for Requesting Clarification in Dialogue, In Proceedings of the 5th SIGdial Workshop on Discourse and Dialogue. Boston, 2004, pp.136-143.

[2] Purver M., CLARIE: Handling Clarification Requests in a Dialogue System, Research on Language & Computation, vol. 4, no. 2, pp.259-288, (2006).

DOI: 10.1007/s11168-006-9006-y

[3] Skantze G., Exploring human error recovery strategies: Implications for spoken dialogue systems., Speech Communication, vol. 45, no. 3, 2005, pp.325-341.

DOI: 10.1016/j.specom.2004.11.005

[4] Lewis C., Fabbrizio G.D., A clarification algorithm for spoken dialogue system, In Proceedings of. ICASSP2005, Philadelphia, (2005).

[5] Misu, T., Kawahara, T. Dialogue strategy to clarify user's queries for document retrieval system with speech interface,. Speech Commun-ication, vol. 48, no. 9, 2006, pp.1137-1150.

DOI: 10.1016/j.specom.2006.04.001

[6] Sangkeun J., Cheongjae L., Gary G. L., Three Phase Verification for Spoken Dialog Clarification, In Proceedings of IUI2006, Sydney, 2006, pp.55-61.

[7] Quirk, C., Brockett, C., Dolan, W. Monolingual machine translation for paraphrase generation., In Proceedings of EMNLP. pp.142-149, (2004).

[8] Koehn P., Och F. J., Marcu D., Statistical phrase-based translation, In Proceedings of NAACL/ HLT, 2003, pp.48-54.

DOI: 10.21236/ada461156

[9] Gao S., Xu B., Huang T. Y., A new framework for Mandarin LVCSR base on one-pass decoder, In Proceedings of ISCSLP 2000, Beijing, 2000, pp.49-52.

[10] Stuttle M. N., Williams J. D., Young S. A Framework for Dialogue Data Collection with a Simulated ASR Channel., In Proceedings of ICSLP, Jeju, South Korea, (2004).

DOI: 10.21437/interspeech.2004-128

[11] Wessel F., Schluter R., Macherey K., Ney H., Confidence measures for large vocabulary continuous speech recognition, IEEE Transactions on Speech and Audio Processing, vol. 9, no. 3, 2001, pp.288-298.

DOI: 10.1109/89.906002