Language modeling for content extraction in human-computer dialogues

In this paper we discuss the role of language modeling in a novel natural language dialogue system designed to automatically route incoming customer calls. We arrive at two significant conclusions: First, standard word error rate measures do not reflect application specific requirements; highly reliable content extraction is possible with relatively high word error rates. Secondly blending human-human data with human-machine data did not improve the performance in language modeling.

[1]  Gerard Salton,et al.  The SMART Retrieval System , 1971 .

[2]  Qiru Zhou,et al.  An approach to continuous speech recognition based on layered self-adjusting decoding graph , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Richard Sproat,et al.  Multilingual Text-to-Speech Synthesis: The Bell Labs Approach , 1998, CL.

[4]  Chin-Hui Lee,et al.  Speech technology integration and research platform: a system study , 1997, EUROSPEECH.

[5]  Bob Carpenter,et al.  Dialogue Management in Vector-Based Call Routing , 1998, ACL.

[6]  Giuseppe Riccardi,et al.  How may I help you? , 1997, Speech Commun..

[7]  Wu Chou,et al.  Decision tree state tying based on segmental clustering for acoustic modeling , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[8]  Bob Carpenter,et al.  Natural language call routing: a robust, self-organizing approach , 1998, ICSLP.

[9]  Hermann Ney,et al.  Evaluating dialog systems used in the real world , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[10]  Shrikanth S. Narayanan,et al.  Probing the relationship between qualitative and quantitative performance measures for voice-enabled telecommunication services , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[11]  Slava M. Katz,et al.  Estimation of probabilities from sparse data for the language model component of a speech recognizer , 1987, IEEE Trans. Acoust. Speech Signal Process..