Skip to main content
SpringerLink
Log in

Evolvable dialogue state tracking for statistical dialogue management

  • Review Article
  • Published:
Frontiers of Computer Science Aims and scope Submit manuscript

Abstract

Statistical dialogue management is the core of cognitive spoken dialogue systems (SDS) and has attracted great research interest. In recent years, SDS with the ability of evolution is of particular interest and becomes the cuttingedge of SDS research. Dialogue state tracking (DST) is a process to estimate the distribution of the dialogue states at each dialogue turn, given the previous interaction history. It plays an important role in statistical dialogue management. To provide a common testbed for advancing the research of DST, international DST challenges (DSTC) have been organised and well-attended by major SDS groups in the world. This paper reviews recent progresses on rule-based and statistical approaches during the challenges. In particular, this paper is focused on evolvable DST approaches for dialogue domain extension. The two primary aspects for evolution, semantic parsing and tracker, are discussed. Semantic enhancement and a DST framework which bridges rule-based and statistical models are introduced in detail. By effectively incorporating prior knowledge of dialogue state transition and the ability of being data-driven, the new framework supports reliable domain extension with little data and can continuously improve with more data available. Thismakes it excellent candidate for DST evolution. Experiments show that the evolvable DST approaches can achieve the state-of-the-art performance and outperform all previously submitted trackers in the third DSTC.

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. Williams J D, Young S. Partially observable Markov decision processes for spoken dialog systems. Computer Speech & Language, 2007, 21(2): 393–422

    Article  Google Scholar 

  2. Thomson B, Young S. Bayesian update of dialogue state: a POMDP framework for spoken dialogue systems. Computer Speech & Language, 2010, 24(4): 562–588

    Article  Google Scholar 

  3. Young S, Gašic M, Keizer S, Mairesse F, Schatzmann J, Thomson B, Yu K. The hidden information state model: a practical framework for POMDP-based spoken dialogue management. Computer Speech & Language, 2010, 24(2): 150–174

    Article  Google Scholar 

  4. Young S, Gasic M, Thomson B, Williams J D. POMDP-based statistical spoken dialog systems: a review. Proceedings of the IEEE, 2013, 101(5): 1160–1179

    Article  Google Scholar 

  5. Williams J D. Challenges and opportunities for state tracking in statistical spoken dialog systems: results from two public deployments. IEEE Journal of Selected Topics in Signal Processing, 2012, 6(8): 959–970

    Article  Google Scholar 

  6. Williams J D. A belief tracking challenge task for spoken dialog systems. In: Proceedings of NAACL-HLTWorkshop on Future Directions and Needs in the Spoken Dialog Community: Tools and Data. 2012, 23–24

    Google Scholar 

  7. Williams J, Raux A, Ramachandran D, Black A. The dialog state tracking challenge. In: Proceedings of the SIGDIAL 2013 Conference., 2013, 404–413

    Google Scholar 

  8. Henderson M, Thomson B, Williams J D. The second dialog state tracking challenge. In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)., 2014, 263–272

    Chapter  Google Scholar 

  9. Henderson M, Thomson B, Williams J D. The third dialog state tracking challenge. In: Proceedings of IEEE Spoken Language Technology Workshop (SLT)., 2014

    Google Scholar 

  10. Yu K, Sun K, Chen L, Zhu S. Constrained markov bayesian polynomial for efficient dialogue state tracking. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2015, 23(12): 2177–2188

    Article  Google Scholar 

  11. Sun K, Xie Q, Yu K. Recurrent polynomial network for dialogue state tracking. 2015, arXiv preprint arXiv: 1507.03934

    Google Scholar 

  12. Kim D, Henderson M, Gasic M, Tsiakoulis P, Young S J. The use of discriminative belief tracking in pomdp-based dialogue systems. In: Proceedings of IEEE Spoken Language Technology Workshop (SLT)., 2014, 354–359

    Google Scholar 

  13. Henderson M, Thomson B, Williams J. The second dialog state tracking challenge. In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discowrse and Dialogue., 2014, 263

    Chapter  Google Scholar 

  14. Young S. CUED standard dialogue acts. Report, Cambridge University, Engineering Department,, 2007

    Google Scholar 

  15. He Y, Young S. Spoken language understanding using the hidden vector state model. Speech Communication, 2006, 48(3): 262–275

    Article  Google Scholar 

  16. Wong YW, Mooney R J. Learning synchronous grammars for semantic parsing with lambda calculus. Annual Meeting-Association for Computational Linguistics., 2007, 45(1): 960

    Google Scholar 

  17. Zettlemoyer L S, Collins M. Online learning of relaxed CCG grammars for parsing to logical form. In: Proceedings of the Joint Conference on Emperical Methods in Natural Language Processing and Computational Natural Language Learning., 2007, 878–887

    Google Scholar 

  18. Sha F, Pereira F. Shallow parsing with conditional random fields. In: Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology., 2003, 134–141

    Google Scholar 

  19. Jurcicek F, Mairesse F, Gašic M, Keizer S, Thomson B, Yu K, Young S. Transformation-based learning for semantic parsing. In: Proceedings of INTERSPEECH., 2009, 2719–2722

    Google Scholar 

  20. Yao K, Zweig G, Hwang M Y, Shi Y, Yu D. Recurrent neural networks for language understanding. In: Proceedings of INTERSPEECH., 2013, 2524–2528

    Google Scholar 

  21. Yao K, Peng B, Zhang Y, Yu D, Zweig G, Shi Y. Spoken language understanding using long short-term memory neural networks. In: Proceedings of IEEE Spoken Language Technology Workshop., 2014, 189–194

    Google Scholar 

  22. Guo D Z, Tur G, Yih W T, Zweig G. Joint semantic utterance classification and slot filling with recursive neural networks. In: Proceedings of IEEE Spoken Language Technology Workshop., 2014, 554–559

    Google Scholar 

  23. Mairesse F, Gasic M, Jurcícek F, Keizer S, Thomson B, Yu K, Young S. Spoken language understanding from unaligned data using discriminative classification models. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing., 2009

    Google Scholar 

  24. Henderson M, GasicM, Thomson B, Tsiakoulis P, Yu K, Young S. Discriminative spoken language understanding using word confusion networks. In: Proceedings of IEEE Spoken Language Technology Workshop., 2012, 176–181

    Google Scholar 

  25. Raymond C, Riccardi G. Generative and discriminative algorithms for spoken language understanding. In: Proceedings of INTERSPEECH., 2007, 1605–1608

    Google Scholar 

  26. Zhu S, Chen L, Sun K, Zheng D, Yu K. Semantic parser enhancement for dialogue domain extension with little data. In: Proceedings of IEEE Spoken Language Technology Workshop (SLT)., 2014

    Google Scholar 

  27. Lee S, Eskenazi M. Recipe for building robust spoken dialog state trackers: dialog state tracking challenge system description. In: Proceedings of the SIGDIAL 2013 Conference., 2013, 414–422

    Google Scholar 

  28. Sun K, Chen L, Zhu S, Yu K. The SJTU system for dialog state tracking challenge 2. In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)., 2014, 318–326

    Chapter  Google Scholar 

  29. Lee S. Structured discriminative model for dialog state tracking. In: Proceedings of the SIGDIAL 2013 Conference., 2013, 442–451

    Google Scholar 

  30. Kim S, Banchs R. Sequential labeling for tracking dynamic dialog states. In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue., 2014, 332

    Chapter  Google Scholar 

  31. Henderson M, Thomson B, Young S. Deep neural network approach for the dialog state tracking challenge. In: Proceedings of the SIGDIAL 2013 Conference., 2013, 467–471

    Google Scholar 

  32. Henderson M, Thomson B, Young S. Word-based dialog state tracking with recurrent neural networks. In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)., 2014, 292–299

    Chapter  Google Scholar 

  33. Williams J D. Web-style ranking and SLU combination for dialog state tracking. In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL). 2014, 282–291

    Chapter  Google Scholar 

  34. Zilka L, Marek D, Korvas M, Jurcicek F. Comparison of Bayesian discriminative and generative models for dialogue state tracking. In: Proceedings of the SIGDIAL 2013 Conference., 2013, 452–456

    Google Scholar 

  35. Wang Z, Lemon O. A simple and generic belief tracking mechanism for the dialog state tracking challenge: on the believability of observed information. In: Proceedings of the SIGDIAL 2013 Conference., 2013, 423–432

    Google Scholar 

  36. Sun K, Chen L, Zhu S, Yu K. A generalized rule based tracker for dialogue state tracking. In: Proceedings of IEEE Spoken Language Technology Workshop (SLT)., 2014, 330–335

    Google Scholar 

  37. Achterberg T. SCIP: Solving constraint integer programs. Mathematical Programming Computation,, 2009, 1(1): 1–41

    Article  MathSciNet  MATH  Google Scholar 

  38. Wang Z. HWU baseline belief tracker for dstc 2 & 3. Technical Report., 2013

    Google Scholar 

  39. Henderson M, Thomson B, Young S. Robust dialog state tracking using delexicalised recurrent neural networks and unsupervised adaptation. In: Proceedings of IEEE Spoken Language Technology Workshop (SLT)., 2014, 360–365

    Google Scholar 

  40. Kadlec R, Vodolan M, Libovicky J, Macek J, Kleindienst J. Knowledge-based dialog state tracking. In: Proceedings of IEEE Spoken Language Technology Workshop., 2014, 348–353

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab, Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China

    Kai Yu, Lu Chen, Qizhe Xie & Su Zhu

  2. Department of Computer Science, Cornell University, Ithaca, NY, 14853, USA

    Kai Sun

Authors
  1. Kai Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lu Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kai Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Qizhe Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Su Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kai Yu.

Additional information

Kai Yu received his BE and MS from Tsinghua University, China in 1999 and 2002, respectively. He then obtained his PhD from Cambridge University, UK in 2006. He is currently a research professor at Shanghai Jiao Tong University, China. His main research interests include speech recognition, synthesis, language understanding and dialogue management. He was selected into the 1000 Overseas Talent Plan (Young Talent) by Chinese government and is the Awardee of the NSFC Excellent Young Scholars Program in 2012. He is a member of the Technical Committee of the Speech, Language, Music and Auditory Perception Branch of the Acoustic Society of China.

Lu Chen received his BS from the School of Computer Science and Technology, Huazhong University of Science & Technology, China in 2013. He is currently a PhD student in the SpeechLab, Department of Computer Science and Engineering, Shanghai Jiao Tong University, China. His research interests include dialogue management and machine learning.

Kai Sun received his BS in computer science from Shanghai Jiao Tong University, China in 2015. Then he worked for his PhD in the Department of Computer Science at Cornell University, USA. His current research interests include speech and language processing, machine learning, and AI in games.

Qizhe Xie is currently a BS student in ACM class in Zhiyuan College, Shanghai Jiao Tong University, China. His research interests include dialogue state tracking, machine learning and natural language processing.

Su Zhu received his BS in computer science from Xi’an Jiao Tong University, China in 2013. He is currently a PhD student in computer science at Shanghai Jiao Tong University, China. His main research interests include language understanding and machine learning.

Electronic supplementary material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yu, K., Chen, L., Sun, K. et al. Evolvable dialogue state tracking for statistical dialogue management. Front. Comput. Sci. 10, 201–215 (2016). https://doi.org/10.1007/s11704-015-5209-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11704-015-5209-4

Keywords

Search

Navigation