Skip to main content
SpringerLink
Log in

Call classification using recurrent neural networks, support vector machines and finite state automata

  • Regular Paper
  • Published:
Knowledge and Information Systems Aims and scope Submit manuscript

Abstract

Our objective is spoken-language classification for helpdesk call routing using a scanning understanding and intelligent-system techniques. In particular, we examine simple recurrent networks, support-vector machines and finite-state transducers for their potential in this spoken-language-classification task and we describe an approach to classification of recorded operator-assistance telephone utterances. The main contribution of the paper is a comparison of a variety of techniques in the domain of call routing. Support-vector machines and transducers are shown to have some potential for spoken-language classification, but the performance of the neural networks indicates that a simple recurrent network performs best for helpdesk call routing.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Allen J, Ferguson G, Ringger EK et al (2001) Dialogue Systems: From Theory to Practice in TRAINS-96. In: Dale R, Moisl H, Somers H (eds) Handbook of natural language processing. Marcel Dekker, New York, pp 347–376

  2. Allen J, Ferguson G, Stent A (2001) An architecture for more realistic conversational systems. In: Proceedings of intelligent user interfaces (IUI-01), Santa Fe, NM

  3. Arai K, Wright JH, Riccardi G et al (1999) Grammar fragment acquisition using syntactic and semantic clustering. Speech Commun 27:43–62

    Google Scholar 

  4. Attwater D, Edgington M, Durston P et al (2000) Practical issues in the application of speech technology to network and customer service applications. Speech Commun 31:279–291

    Google Scholar 

  5. Brill E, Florian R, Henderson JC et al (1998) Beyond N-Grams: Can linguistic sophistication improve language modeling? In: Boitet C, Whitelock P (eds) Proceedings of the thirty-sixth annual meeting of the association for computational linguistics and seventeenth international conference on computational linguistics, Morgan Kaufmann Publishers, San Francisco, CA, pp 186–190

  6. Burges CJ (1998) A tutorial on support vector machines for pattern recognition. Data Mining Knowl Discov 2:121–167

    Google Scholar 

  7. Burton-Roberts N (1986) Analysing sentences. An introduction to English syntax. Longman Group UK Ltd, England

  8. Carpenter B, Chu-Carroll J (1998) Natural language call routing: a robust self-organizing approach. ICSLP 98, Sydney, pp 2059–2062

    Google Scholar 

  9. Chapelle O, Vapnik V (2000) Model selection for support vector machines. In: Solla S, Leen T, Muller K-R (eds) Advances in neural information processing systems, vol 12. MIT Press, Cambridge, MA

  10. Charniak E (1993) Statistical language learning. MIT Press, Cambridge, MA

  11. Chou W, Zhou Q, Kuo H-K J et al (2000) Natural language call steering for service applications. In: Proceedings of the international conference on spoken language processing, Beijing, China

  12. Chu-Carroll J, Carpenter B (1998) Dialogue management in vector-based call routing. COLING-ACL98, pp 256–262

  13. Chu-Carroll J, Carpenter B (1999) Vector-based natural language call routing. J Comput Ling 25(3):361–388

    Google Scholar 

  14. Durston PJ, Farrell M, Attwater D et al (2001) OASIS natural language call steering trial. In: Proceedings of Eurospeech, vol 2, pp 1323–1326

  15. Edgington M, Attwater D, Durston P (1999) OASIS—a framework for spoken language call steering. In: Proceedings of Eurospeech '99, Budapest Hungary, pp 923–926

  16. Elman JL, Bates EA, Johnson MH et al (1996) Rethinking innateness. MIT Press, Cambridge, MA

  17. Elman JL (1991) Distributed representations simple recurrent networks and grammatical structure. Mach Learn 7:195–225

    Google Scholar 

  18. Elman JL (1990) Finding structure in time. Cognitive Sci 14:179–211

    Article  Google Scholar 

  19. Feng J, Williams P (2001) The generalization error of the symmetric and scaled support vector machines. IEEE Trans on Neural Net 12(5):1255–1260

    Google Scholar 

  20. Ferguson G, Allen JF (1998) TRIPS: an integrated intelligent problem-solving assistant. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI-98), Maddison, WI, pp 567–573

  21. Forman G (2002) Choose your words carefully: an empirical study of feature selection metrics or text classification. In: Proceedings of the 13th European conference on machine learning ECML '02 and 6th European conference on principles and practice of knowledge discovery in databases PKDD, Helsinki, Finland

  22. Garner PN (1997) On topic identification and dialogue move recognition. Comput Speech Lang 11:275–306

    Article  Google Scholar 

  23. Glass1999 Glass JR (1999) Challenges for spoken dialogue systems. In: Proceedings of IEEE ASRU Workshop, Key

  24. Gorin AL, Riccardi G, Wright JH (1997) How may I help you? Speech Commun 23:113–127

    Google Scholar 

  25. Gorin AL, Wright JH, Riccardi G et al (2000) Semantic information processing of spoken language. In: Proceedings of 2000 International ATR Workshop on Multilingual Speech Communication, Kyoto Japan, October 2000, pp 13–16

  26. Gunn S (1998) Support vector machines for classification and regression. ISIS Technical Report

  27. Harman D (1995) Overview of the fourth text retrieval conference. In: Proceedings of TREC

  28. Joachims T (1999) Making large-scale SVM learning practical. In: Schölkopf B, Burges C, Smola A (eds) Advances in kernel methods: support vector learning. MIT Press, Cambridge, MA

  29. Joachims T (2000) Estimating the generalization performance of an SVM efficiently. In: Proceedings of International Conference on Machine Learning

  30. Joachims T (2002) Learning to classify text using support vector machines. Kluwer Academic Publishers, Boston, MA

  31. Jordan M (1986) Attractor dynamics and parallelism in a connectionist sequential machine. In: Proceedings of the Eighth Annual Conference of the Cognitive Science Society, Amherst, pp 531–546

  32. Jurafsky D, Martin JH (2000) Speech and language processing. Prentice Hall, Upper Saddle River, NJ

  33. Landauer TK, Foltz PW, Laham D (1998) An introduction to latent semantic analysis. Discourse Process 25:259–284

    Google Scholar 

  34. LeCun Y, Bottou L, Orr G et al (1998) Efficient backprop. In: Orr G, Muller K (eds) Neural networks: tricks of the trade, Springer, Berlin Heidelberg New York

  35. McDonough J, Ng K, Jeanrenaud P et al (1994) Approaches to topic identification on the switchboard corpus. In: Proceedings of IEEE international conference on acoustics speech and signal processing, Adelaide, Australia, pp 385–388

  36. McTear MF (2000) Intelligent interface technology: from theory to reality? Interact Comput 12:323–336

    Google Scholar 

  37. McTear MF (2002) Spoken dialogue technology: enabling the conversational user interface. ACM Comput Surv 34(1):90–169

    Article  Google Scholar 

  38. Moghaddam B, Yang M-H (2001) Sex with support vector machines. In: Leen TK, Dietterich TG, Tresp V (eds) Advances in neural information processing systems, vol 13. MIT Press, Cambridge, MA, pp 960–966

  39. Opper M, Urbanczik R (2001) Universal learning curves of support vector machines. Phys Rev Lett 86(19):4410–4413

    Article  Google Scholar 

  40. Platt JC (1998) Sequential minimal optimization: a fast algorithm for training support vector machines. Technical Report MSR-TR-98-14

    Google Scholar 

  41. Pyka C (1992) Management of hypotheses in an integrated speech-language architecture. In: Proceedings of 10th European conference on artificial intelligence

  42. Roche E, Schabes Y (1997) Finite-state language processing. MIT, London

  43. Salton G, McGill M (1983) Introduction to modern information retrieval. McGraw Hill, New York

  44. Schölkopf B (1998) SVMs-a practical consequence of learning theory. IEEE Intell Syst pp: 18–21

    Google Scholar 

  45. Schölkopf B, Burges C, Vapnik V (1995) Extracting support data for a given task. In: Fayyad UM, Uthurusamy R (eds) Proceedings first international conference on knowledge discovery and data mining AAAI, Press, Menlo Park, CA, pp 252–257

  46. Stitson MO, Weston JAE, Gammerman A et al (1996) Theory of support vector machines. Technical Report CSD-TR-96-17

  47. Stolcke A, Shriberg E, Bates R et al (1998) Dialog act modeling for conversational speech. In: Proceedings of AAAI-98 spring symposium on applying machine learning to discourse processing

  48. CJ (1979) Information retrieval, 2nd edn. Butterworths, London

  49. Vapnik VN (1995) The nature of statistical learning theory. Springer Verlag, Berlin Heidelberg New York

  50. Wermter S (1995) Hybrid connectionist natural language processing. Chapman and Hall Thomson International, London, UK

  51. Wermter S, Panchev C, Arevian G (1999) Hybrid neural plausibility networks for news agents. In: Proceedings of the National Conference on Artificial Intelligence, Orlando, FL

  52. Wermter S, Weber V (1997) SCREEN: learning a flat syntactic and semantic spoken language analysis. J Artif Intell Res 6(1):35–85

    Google Scholar 

  53. Wermter S (2000) Neural fuzzy preference integration using neural preference Moore machines. Int J Neural Syst 10(4):287–309

    MATH  Google Scholar 

  54. Wermter S (1999) Preference Moore machines for neural fuzzy integration. In: Proceedings of the international joint conference on artificial intelligence, Stockholm, pp 840–845

  55. Wermter S, Panchev C, Houlsby J (1999) Language disorders in the brain: distinguishing aphasia forms with recurrent networks. In: Proceedings of AAAI 99 conference workshop on neuroscience and neural computation, Orlando, FL, pp 93–98

  56. Yang Y-J, Chien L-F, Lee L-S (2002) Speaker intention modeling for large vocabulary Mandarin spoken dialogues. ICSLP '96, vol 2, pp 713–716

  57. Young SR, Hauptmann AG, Ward WH et al (1989) High level knowledge sources in usable speech recognition systems. Commun ACM 32:183–194

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. University of Sunderland, School of Computing and Technology, St. Peter's Way, Sunderland, SR6 0DD, United Kingdom

    Sheila Garfield & Stefan Wermter

Authors
  1. Sheila Garfield
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Stefan Wermter
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

Sheila Garfield received a BSc (Hons) in computing from the University of Sunderland in 2000 where, as part of her programme of study, she completed a project associated with aphasic language processing. She received her PhD from the same university, in 2004, for a programme of work connected with hybrid intelligent systems and spoken-language processing. In her PhD thesis, she collaborated with British Telecom and suggested a novel hybrid system for call routing. Her research interests are natural language processing, hybrid systems, intelligent systems.

Stefan Wermter holds the Chair in Intelligent Systems and is leading the Intelligent Systems Division at the University of Sunderland, UK. His research interests are intelligent systems, neural networks, cognitive neuroscience, hybrid systems, language processing and learning robots. He has a diploma from the University of Dortmund, Germany, an MSc from the University of Massachusetts, USA, and a PhD in habilitation from the University of Hamburg, Germany, all in Computer Science. He was a Research Scientist at Berkeley, CA, before joining the University of Sunderland. Professor Wermter has written edited, or contributed to 8 books and published about 80 articles on this research area.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Garfield, S., Wermter, S. Call classification using recurrent neural networks, support vector machines and finite state automata. Knowl Inf Syst 9, 131–156 (2006). https://doi.org/10.1007/s10115-005-0198-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-005-0198-5

Keywords

Search

Navigation