Electronics and Telecommunications Trends (전자통신동향분석)

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Trends in Deep-neural-network-based Dialogue Systems

심층 신경망 기반 대화처리 기술 동향

  • Published : 2019.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we introduce trends in neural-network-based deep learning research applied to dialogue systems. Recently, end-to-end trainable goal-oriented dialogue systems using long short-term memory, sequence-to-sequence models, among others, have been studied to overcome the difficulties of domain adaptation and error recognition and recovery in traditional pipeline goal-oriented dialogue systems. In addition, some research has been conducted on applying reinforcement learning to end-to-end trainable goal-oriented dialogue systems to learn dialogue strategies that do not appear in training corpora. Recent neural network models for end-to-end trainable chit-chat systems have been improved using dialogue context as well as personal and topic information to produce a more natural human conversation. Unlike previous studies that have applied different approaches to goal-oriented dialogue systems and chit-chat systems respectively, recent studies have attempted to apply end-to-end trainable approaches based on deep neural networks in common to them. Acquiring dialogue corpora for training is now necessary. Therefore, future research will focus on easily and cheaply acquiring dialogue corpora and training with small annotated dialogue corpora and/or large raw dialogues.

Keywords

Acknowledgement

Grant : 준지도학습형 언어지능 원천기술 및 이에 기반한 외국인 지원용 한국어 튜터링 서비스 개발

Supported by : 정보통신기획평가원

References

  1. J.D. Williams and S. Young, "Partially Observable Markov Decision Processes for Spoken Dialog Systems," Comput. Speech Language, vol. 21, no. 2, 2007, pp. 393-422, doi: 10.1016/j.csl.2006.06.008.
  2. S. Young et al., "Pomdp-Based Statistical Spoken Dialog Systems: A Review," Proc. IEEE, vol. 101, no. 5, 2013, pp. 1160-1179, doi:10.1109/JPROC.2012.2225812.
  3. T. Zhao and M. Eskenazi, "Towards End-to-End Learning for Dialog State Tracking and Management Using Deep Reinforcement Learning," in Proc. Annu. Meeting Special Interest Group Discourse Dialogue (SIGDIAL), Los Angeles, CA, USA, Sept. 2016, pp. 1-10.
  4. A. Bordes et al., "Learning End-to-End Goal-Oriented Dialog," in Proc. Int. Conf. Learning Representations (ICLR), Toulon, France, Apr. 2017, pp. 1-5.
  5. J.D. Williams et al., "Hybrid Code Networks: Practical and Efficient End-to-End Dialog Control with Supervised and Reinforcement Learning," in Proc. Annu. Meeting Association Comput. Linguistics (ACL), Vancouver, Canada, 2017, pp. 665-677.
  6. B. Liu and I. Lane, "An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog," in Proc. Annu. Conf. Int. Speech Commun. Association (INTERSPEECH), Stockholm, Sweden, Aug. 2017, pp. 2506-2510.
  7. A. Madotto et al., "Mem2seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems," in Proc. Annu. Meeting Association Comput. Linguistics (ACL), Melbourne, Australia, July 2018, pp. 1468-1478.
  8. B. Dhingra et al., "Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access," in Proc. Annu. Meeting Association Comput. Linguistics (ACL), Vancouver, Canada, 2017, pp. 484-495.
  9. B. Liu and I. Lane, "Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models," in IEEE Autom. Speech Recogn. Understanding Workshop (ASRU), Okinawa, Japan, Dec. 2017, pp. 482-489.
  10. X. Li et al., "End-to-end Task-Completion Neural Dialogue Systems." in Proc. Int. Joint Conf. Natural Language Process. (IJCNLP), Taipei, Taiwan, 2017, pp. 733-743.
  11. I. Ahmed and S. Singh, "AIML Based Voice Enabled Artificial Intelligent Chatterbot." Int. J. u- e- Service, Sci. Technol., vol. 8, no. 2, Feb. 2015, pp. 375-384. https://doi.org/10.14257/ijunesst.2015.8.2.36
  12. B. Wilcox and S. Wilcox, "Winning the Loebner's," 2014, http://brilligunderstanding.com/Winning.pdf.
  13. O. Vinyals and Q. Le, "A Neural Conversational Model," in Proc. ICML, Lille, France, 2015, pp. 1-8.
  14. 황금하 외, "목적지향 대화시스템을 위한 챗봇 연구", 정보처리학회논문지, 제6권 제11호, 2017, pp. 499-507. https://doi.org/10.3745/KTSDE.2017.6.11.499
  15. J.X. Huang et al., "Improve the Chatbot Performance for the DBCALL System Using a Hybrid Method and a Domain Corpus," in Future-Proof CALL: Language Learning Exploration Encounters-Short Papers from EUROCALL, 2018, pp. 100-105, doi:10.14705/rpnet.2018.26.820.
  16. L. Shang et al., "Neural Responding Machine for Short-Text Conversation," in Proc. ACL, Beijing, China, July 2015, pp. 1577-1586.
  17. J. Li et al., "A Diversity-Promoting Objective Function for Neural Conversation Models," in Proc. HLT-NAACL, San Diego, CA, USA, June 2016, pp. 110-119.
  18. T. Zhao et al., "Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders," in Proc. Annu. Meeting Association Comput. Linguistics (ACL), Vancouver, Canada, 2017, pp. 654-664.
  19. A. Sordoni et al., "A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion," in Proc. Conf. Inf. Knowl. Manag., Melbourne, Australia, Oct. 2015, pp. 553-562.
  20. I.V. Serban et al., "Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models," in Proc. AAAI, Phoenix, AZ, USA, Feb. 2016, pp. 3776-3783.
  21. I.V. Serban et al., "A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues," in Proc. AAAI Artif. Intell., San Francisco, CA, USA, Feb. 2017, pp. 3295-3301.
  22. C. Xing et al., "Hierarchical Recurrent Attention Network for Response Generation," in Proc. AAAI Artif. Intell., New Orleans, LA, USA, Feb. 2018, pp. 5610-5617.
  23. C. Xing, et al., "Topic Aware Neural Response Generation," in Proc. AAAI Artif. Intell., San Francisco, CA, USA, Feb. 2017, pp. 3351-3357.
  24. M. Ghazvininejad et al., "A Knowledge-Grounded Neural Conversation Model," in Proc. AAAI Artif. Intell., New Orleans, LA, USA, Feb. 2018, pp. 5510-5517.
  25. E. Dinan et al., "Wizard of Wikipedia-Knowledge-Powered Conversational Agents," in Proc. Int. Conf. Learning Representations, New Orleans, LA, USA, May 2019, pp. 1-8.
  26. S. Zhang et al., "Personalizing Dialogue Agents: I have a dog, do you have pets too?" in Proc. Association Comput. Lignuistics, Melbourne, Australia, July 2018, pp. 2204-2213.
  27. J. Weston, "Memory Networks," in Proc. Int. Conf. Learning Representations, San Diego, CA, USA, Dec. 2015.
  28. S. Sukhbaatar et al., "End-To-End Memory Networks," in Proc. NIPS, Montreal, Canada, Dec. 2015, pp. 1-9.
  29. A. Miller et al., "Key-Value Memory Networks for Directly Reading Documents," in Proc. Conf. Empirical Methods Natural Language Process., Austin, TX, USA, Nov. 2016, pp. 1400-1409.
  30. A. Kumar et al., "Ask Me Anything: Dynamic Memory Networks for Natural Language Processing," in Proc. Int. Conf. Mach. Learning, New York, USA, June 2016.
  31. E. Dinan et al., "The Second Conversational Intelligence Challenge(ConvAI2)," 2019, arXiv: 1902.00098, https://arxiv.org/pdf/1902.00098.pdf.
  32. DSTC8, "The Eighth Dialog System Technology Challenge," https://sites.google.com/dstc.community/dstc8.
  33. Jason Weston, "ConvAI2 Competition: Future Work," http://convai.io/NeurIPSConvAI2FutureWork.pptx
  34. S. Ravuri and A. Stolcke, "Recurrent Neural Network and LSTM Models for Lexical Utterance Classification," in Proc. Interspeech, Dresden, Germana, Sept. 2015, pp. 135-139.
  35. J.Y. Lee and F. Dernoncourt, "Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks," in Proc. NAACL-HLT, San Diego, CA, USA, June, 2016, pp. 515-520.
  36. X. Ma and E. Hovy, "End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF," arXiv: 1603.01354v5, 2016.
  37. E. Simonnet et al., "Exploring the use of attention-based recurrent neural networks for spoken language understanding," in Proc. Mach. Learning Spoken Language Understanding Interactions, Montreal, Canada, 2015, pp. 1-7.
  38. D. Hakkani-Tur et al., "Multi-Domain Joint Semantic Frame Parsing Using bi-Directional RNN-LSTM," in Proc. Interspeech, San Francisco, CA, USA, Sept. 2016, pp. 715-719.
  39. B. Liu and I. Lane, "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling," in Proc. Interspeech, San Francisco, CA, USA, Sept. 2016, pp. 685-689.
  40. C.-W. Goo et al., "Slot-Gated Modeling for Joint Slot Filling and Intent Prediction," in Proc. NAACL-HLT, New Orleans, LA, USA, June 2018, pp. 753-757.
  41. Y. Wang et al., "A bi-Model Based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling," in Proc. NAACL-HLT, New Orleans, LA, USA, June 2018, pp. 309-314.
  42. Q. Chen et al., "BERT for Joint Intent Classification and Slot Filling," 2019, arXiv: 1902.10909v1.
  43. R. Gupta et al., "An Efficient Approach to Encoding Context for Spoken Language Understanding," 2018, arXiv: 1807.00267v1.
  44. Y.-N. Chen et al., "End-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding," in Proc. Interspeech, San Francisco, CA, USA, Sept. 2016, pp. 3245-3249.
  45. D. Serdyuk et al., "Towards End-to-End Spoken Language Understanding," 2018, arXiv: 1802.08395v1.
  46. S.K. Choi et al., "Using a Dialogue System Based on Dialogue Maps for Computer Assisted Second Language Learning," in EUROCALL, Limassol, Cyprus, Aug. 2016, pp. 106-112.
  47. I.V. Serban et al., "A Survey of Available Corpora for Building Data-Driven Dialogue Systems," 2015, arXiv preprint arXiv:1512.05742.
  48. I.V. Serban et al., "A Survey of Available Corpora for Building Data-Driven Dialogue Systems," https://breakend.github.io/Dialog-Datasets/.
  49. R. Lowe et al., "The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems," in SIGDIAL, Prague, Czech Republic, Spet. 2015. pp. 285-294.
  50. P Budzianowski et al., "Multiwoz-a Largescale Multi-domain Wizard-of-Oz Dataset for Taskoriented Dialogue Modelling," in Proc. Conf. Empirical Methods Natural Language Process., Brussels, Belgium, 2018, pp. 5016-5026.
  51. W.S. Lasecki et al., "Conversations in the Crowd: Collecting Data for Task-Oriented Dialog Learning," in AAAI Conf., Bellevue, WA, USA, 2013, pp. 2-5.
  52. M. Eric et al., "Key-Value Retrieval Networks for Task-Oriented Dialogue," in SIGDIAL Conf., Saarbrucken, Germany, Aug. 2017, pp. 37-49.