Chatbot Components and Architectures

  • Boris Galitsky


In the Introduction, we discussed that chatbot platforms offered by enterprises turned out to be good for simple cases, not really enterprise-level deployments. In this chapter we make a first step towards industrial–strength chatbots. We will outline the main components of chatbots and show various kinds of architectures employing these components. The descriptions of these components will be the reader’s starting points to learning them in-depth in the consecutive chapters.

Building a chatbot for commercial use via data-driven methods poses two main challenges. First is broad-coverage: modeling natural conversation in an unrestricted number of topics is still an open problem as shown by the current concentration of research on dialogues in restricted domains. Second is the difficulty to get a clean, systematic, unbiased and comprehensive datasets of open-ended and task-oriented conversations, which makes it difficult for chatbot improvement and limits the viability of using purely data-driven methods such as neural networks.

We will explore the usability of rule-based and statistical machine learning - based dialogue managers, the central component in a chatbot architecture. We conclude this chapter by illustrating specific learning architectures, based on active and transfer learning.


  1. Allen JF, Perrault CR (1980) Analyzing intention in utterances. Artif Intell 15(3):143–178CrossRefGoogle Scholar
  2. Allen JF, Schubert LK (1991) The TRAINS project TRAINS technical note. Department of Computer Science/University of Rochester, RochesterCrossRefGoogle Scholar
  3. Applin SA, Fischer MD (2015) New technologies and mixed-use convergence: how humans and algorithms are adapting to each other. In: Technology and Society (ISTAS), 2015 IEEE international symposium on, IEEE, pp 1–6Google Scholar
  4. Bohus D, Rudnicky AI (2009) The RavenClaw dialog management framework: architecture and systems. Comput Speech Lang 23(3):332–361CrossRefGoogle Scholar
  5. Burgan D (2017) Dialogue systems & dialogue management. DST Group TR-3331.
  6. Burtsev M, Seliverstov A, Airapetyan R, Arkhipov M, Baymurzina D, Bushkov N, Gureenkova O, Khakhulin T, Kuratov Y, Kuznetsov D, Litinsky A, Logacheva V, Lymar A, Malykh V, Petrov M, Polulyakh V, Pugachev L, Sorokin A, Vikhreva M, Zaynutdinov M (2018) DeepPavlov: open-source library for dialogue systems. In: ACL-system demonstrations, pp 122–127Google Scholar
  7. Cassell J, Bickmore T, Campbell L, Vilhjálmsson H (2000) Human conversation as a system framework: designing embodied conversational agents, Embodied conversational agents. MIT Press, Boston, pp 29–63Google Scholar
  8. Chabernaud F (2017) Multimodal interactions with a chatbot and study of interruption recovery in conversation. Masters thesis. Heriot-Watt UniversityGoogle Scholar
  9. Daiber J, Max Jakob, Chris Hokamp, PN Mendes (2013) Improving efficiency and accuracy in multilingual entity extraction. In: Proceedings of the 9th international conference on semantic systems (I-Semantics)Google Scholar
  10. Dragone P (2015) Non-sentential utterances in dialogue: experiments in classification and interpretation. In: Proceedings of the 19th workshop on the semantics and pragmatics of dialogue, Gothenburg, Sweden, pp 170–171. Gothenburg UniversityGoogle Scholar
  11. Ferragina P, Scaiella U (2010) Tagme: on-the-fly annotation of short text fragments (by Wikipedia entities). In: Proceedings of the 19th ACM international conference on information and knowledge management. ACM, New York, pp 1625–1628Google Scholar
  12. Galitsky B (2004) A library of behaviors: implementing commonsense reasoning about mental world. In: International conference on knowledge-based and intelligent information and engineering systems, pp 307–313Google Scholar
  13. Galitsky B (2013) Exhaustive simulation of consecutive mental states of human agents. Knowl-Based Syst 43:1–20CrossRefGoogle Scholar
  14. Galitsky B (2016) Theory of mind engine. In: Computational autism. Springer, ChamCrossRefGoogle Scholar
  15. Galitsky B (2017) Matching parse thickets for open domain question answering. Data Knowl Eng 107:24–50CrossRefGoogle Scholar
  16. Galitsky B, de la Rosa JL (2011) Concept-based learning of human behavior for customer relationship management. Inf Sci 181(10):2016–2035CrossRefGoogle Scholar
  17. Galitsky BA, Ilvovsky D (2017) Chatbot with a discourse structure-driven dialogue management. EACL Demo E17-3022. Valencia, SpainGoogle Scholar
  18. Galitsky B, Kovalerchuk B (2014) Improving web search relevance with learning structure of domain concepts. Clusters Orders Trees: Methods Appl 92:341–376MathSciNetGoogle Scholar
  19. Galitsky B, Pampapathi R (2005) Can many agents answer questions better than one? First Monday 10(1)Google Scholar
  20. Galitsky BA, Parnis A (2017) How children with autism and machines learn to interact. In: Autonomy and artificial intelligence: a threat or savior. Springer, ChamGoogle Scholar
  21. Galitsky BA, Shpitsberg I (2015) Evaluating assistance to individuals with autism in reasoning about mental world. Artificial intelligence applied to assistive technologies and smart environments: papers from the 2015 AAAI workshopGoogle Scholar
  22. Galitsky B, Shpitsberg I (2016) Autistic learning and cognition, in computational autism. Springer, ChamGoogle Scholar
  23. Galitsky B, Kuznetsov SO, Samokhin MV (2005) Analyzing conflicts with concept-based learning. International conference on conceptual structures, pp 307–322Google Scholar
  24. Galitsky B, González MP, Chesñevar CI (2009) A novel approach for classifying customer complaints through graphs similarities in argumentative dialogue. Decis Support Syst:46, 717–43, 729Google Scholar
  25. Griol D, Molina J, Sanchis de Miguel A (2014) Developing multimodal conversational agents for an enhanced e-learning experience. ADCAIJ: Adv Dist Comput Artif Intell J 3:13. 10.14201CrossRefGoogle Scholar
  26. Haptik (2018) Open source chatbot NER
  27. Hiraoka T, Neubig G, Yoshino K, Toda T and Nakamura S (2017) Active learning for example-based dialog systems. IWSDSCrossRefGoogle Scholar
  28. Horvitz E, Breese J, Heckerman D, Hovel D, Rommelse K (1998) The Lumiere project: Bayesian user modeling for inferring the goals and needs of software users. In: Proceedings of the 14th conference on uncertainty in artificial intelligence, Madison, Wisconsin. Morgan Kaufmann Publishers Inc, San Francisco, pp 256–265Google Scholar
  29. Hu B, Lu Z, Li H, Chen Q (2014) Convolutional neural network architectures for matching natural language sentences. In: Proceedings of the advances in neural information processing systems, Montréal, Canada, pp 2042–2050Google Scholar
  30. Jurafsky D, Martin JH (2009) Speech and language processing (Pearson International), 2nd edn. Pearson/Prentice Hall, Upper Saddle River. ISBN 978-0-13-504196-3Google Scholar
  31. Krause B, Damonte M, Dobre M, Duma D, Fainberg J, Fancellu F, Kahembwe E, Cheng J, Webber B (2017) Edina: building an open domain socialbot with self-dialogues.
  32. Kronlid F (2006) Turn taking for artificial conversational agents. In: Proceedings of the international workshop on cooperative information agents. Springer, Edinburgh, pp 81–95CrossRefGoogle Scholar
  33. Larsson S, Traum DR (2000) Information state and dialogue management in the TRINDI dialogue move engine toolkit. Nat Lang Eng 6(3&4):323–340CrossRefGoogle Scholar
  34. Lee S-I, Sung C, Cho S-B (2001) An effective conversational agent with user modeling based on Bayesian network. In: Proceedings of the web intelligence: research and development. Springer, Maebashi City, pp 428–432CrossRefGoogle Scholar
  35. Lee C, Jung S, Kim S, Lee GG (2009) Example-based dialog modeling for practical multi-domain dialog system. Speech Comm 51:466CrossRefGoogle Scholar
  36. Lee C, Jung S, Kim K, Lee D, Lee GG (2010) Recent approaches to dialog management for spoken dialog systems. Journal of Computing Science and Engineering 4(1):1–22CrossRefGoogle Scholar
  37. Levin E, Pieraccini R, Eckert W (2000) A stochastic model of human-machine interaction for learning dialog strategies. IEEE Trans Speech Audio Proces 8(1):11–23CrossRefGoogle Scholar
  38. Lim S, Oh K, Cho S-B (2010) A spontaneous topic change of dialogue for conversational agent based on human cognition and memory. In: Proceedings of the international conference on agents and artificial intelligence. Springer, Valencia, pp 91–100Google Scholar
  39. Liu H, Lin T, Sun H, Lin W, Chang C-W, Zhong T, Rudnicky A (2017a) RubyStar: a non-task-oriented mixture model dialog system. First Alexa Prise comptions proceedingsGoogle Scholar
  40. Liu M, Shi J, Li Z, Li C, Zhu J, Liu S (2017b) Towards better analysis of deep convolutional neural networks. IEEE Trans Vis Comput Graph 23(1):91–100. CrossRefGoogle Scholar
  41. LuperFoy S, Loehr D, Duff D, Miller K, Reeder F, Harper L (1998) An architecture for dialogue management, context tracking, and pragmatic adaptation in spoken dialogue systems. In: Proceedings of the 36th ACL and the 17th ACL-COLING, Montreal, Canada, pp 794–801Google Scholar
  42. Manning CD, Surdeanu M, Bauer J, Finkel J, Bethard SJ, McClosky (2014) The stanford CoreNLP natural language processing toolkit. Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp 55–60, Baltimore, Maryland USA, June 23–24Google Scholar
  43. Marschner C, Basilyan M (2014) Identification of intents from query reformulations in search. US Patent App. 14/316,719 (June 26 2014)Google Scholar
  44. McTear M (2002) Spoken dialogue technology: enabling the conversational user interface. ACM Comput Surv 34(1):90–169CrossRefGoogle Scholar
  45. McTear M, Callejas Z, Griol D (2016) Evaluating the conversational interface. In: The conversational interface. Springer, Cham, pp 379–402CrossRefGoogle Scholar
  46. Meng F, Lu Z, Tu Z, Li H, Liu Q (2015) A deep memory-based architecture for sequence-to-sequence learning. In: Proceedings of the ICLR workshop, San Juan, Puerto RicoGoogle Scholar
  47. Mingxuan W, Zhengdong L, Li H, Jiang W, Liu WJQ (2015) A convolutional architecture for word sequence prediction. In: Proceedings of the 53rd ACL, Beijing, China, pp 9Google Scholar
  48. Murao H, Kawaguchi N, Matsubara S, Inagaki Y (2001) Example- based query generation for spontaneous speech. Proceedings of ASRUGoogle Scholar
  49. Nio L, Sakti S, Neubig G, Toda T, Nakamura S (2014) Utiliz- ing human-to-human conversation examples for a multi domain chat-oriented dialog system. Trans IEICE E97:1497CrossRefGoogle Scholar
  50. Nisimura R, Nishihara Y, Tsurumi R, Lee A, Saruwatari H, Shikano K (2003) Takemaru-kun: speech-oriented information system for real world re- search platform. In: Proceedings of LUARGoogle Scholar
  51. Papangelis A, Karkaletsis V, Makedon F (2012) Online complex action learning and user state estimation for adaptive dialogue systems. In: Proceedings of the 24th IEEE international conference on tools with artificial intelligence, Piraeus, Greece, pp 642–649. IEEEGoogle Scholar
  52. Raux A, Eskenazi M (2012) Optimizing the turn-taking behavior of task-oriented spoken dialog systems. ACM Trans Speech Lang Proces 9(1):1CrossRefGoogle Scholar
  53. Sacks H, Schegloff EA, Jefferson G (1974) A simplest systematics for the organization of turn-taking for conversation. Language 50(4):696–735CrossRefGoogle Scholar
  54. Schröder M (2010) The SEMAINE API: towards a standards-based framework for building emotion-oriented systems. Adv Hum Comput Interact 2010:319–406. CrossRefGoogle Scholar
  55. Serban IV, Sordoni A, Bengio Y, Courville A, Pineau J (2016) Building end-to-end dialogue systems using generative hierarchical neural network models. In: Proceedings of the 30th AAAI conference on artificial intelligence, Phoenix, Arizona, pp 3776–3783Google Scholar
  56. Shawar BA, Atwell E (2007) Chatbots: are they really useful? LDV Forum 22:29–49Google Scholar
  57. Skantze G (2007) Error handling in spoken dialogue systems-managing uncertainty, grounding and miscommunication. Doctoral thesis in Speech Communication. KTH Royal Institute of Technology. Stockholm, SwedenGoogle Scholar
  58. Smith C, Crook N, Dobnik S, Charlton D, Boye J, Pulman S, De La Camara RS, Turunen M, Benyon D, Bradley J (2011) Interaction strategies for an affective conversational agent. Presence Teleop Virt 20(5):395–411CrossRefGoogle Scholar
  59. Singaraju G (2019) Introduction to embedding in natural language processing. Google Scholar
  60. Sordoni A, Galle M, Auli M, Brockett C, Mitchell YM, Nie J-Y, Gao J, Dolan B (2015) A neural network approach to context- sensitive generation of conversational responses, Proceedings of NAACLGoogle Scholar
  61. Stent A, Dowding J, Gawron JM, Bratt EO, Moore R (1999) The command talk spoken dialogue system. In: Proceedings of the 37th annual meeting of the association for computational linguistics on computational linguistics. Association for Computational Linguistics, College Park, pp 183–190CrossRefGoogle Scholar
  62. Su P-H, Vandyke D, Gasic M, Kim D, Mrksic N, Wen T-H, Young S (2015) Learning from real users: Rating dialogue success with neural networks for reinforcement learning in spoken dialogue systems. In: INTERSPEECHGoogle Scholar
  63. Vinyals O, Le QV (2015) A neural conversational model. In: ICML deep learning workshopGoogle Scholar
  64. Wallace RS (2009) The anatomy of A.l.i.c.e, Parsing the Turing Test. pp 181–210Google Scholar
  65. Weizenbaum J (1966) ELIZA—a computer program for the study of natural language communication between man and machine. Commun ACM 9(1):36–45CrossRefGoogle Scholar
  66. Wiemer-Hastings P, Graesser AC, Harter D, Group TR (1998) The foundations and architecture of AutoTutor. In Proceedings of the International Conference on Intelligent Tutoring Systems, San Antonio, Texas, pp 334–343. SpringerGoogle Scholar
  67. Williams JD, Young S (2007) Partially observable Markov decision processes for spoken dialog systems. Comput Speech Lang 21(2):393–422CrossRefGoogle Scholar
  68. Wollmer M, Schuller B, Eyben F, Rigoll G (2010) Combining long short-term memory and dynamic Bayesian networks for incremental emotion-sensitive artificial listening. IEEE J Sel Top Sig Proces 4(5):867–881CrossRefGoogle Scholar
  69. Xu B, Guo X, Ye Y, Cheng J (2012) An improved random forest classifier for text categorization. JCP 7:2913–2920Google Scholar
  70. Yankelovich N, Baatz E (1994) SpeechActs: a framework for building speech applications. In: Proceedings of the American Voice I/O Society conference, San Jose, California, pp 20–23. CiteseerGoogle Scholar
  71. Zhou H, Huang M, Zhang T, Zhu X, Liu B (2017) Emotional chatting machine: emotional conversation generation with internal and external memory. arXiv preprint arXiv. 1704.01074Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Boris Galitsky
    • 1
  1. 1.Oracle (United States)San JoseUSA

Personalised recommendations