A Survey of Response Generation of Dialogue Systems

Authors: Yifan Fan, Xudong Luo, Pingping Lin

Abstract:

An essential task in the field of artificial intelligence is to allow computers to interact with people through natural language. Therefore, researches such as virtual assistants and dialogue systems have received widespread attention from industry and academia. The response generation plays a crucial role in dialogue systems, so to push forward the research on this topic, this paper surveys various methods for response generation. We sort out these methods into three categories. First one includes finite state machine methods, framework methods, and instance methods. The second contains full-text indexing methods, ontology methods, vast knowledge base method, and some other methods. The third covers retrieval methods and generative methods. We also discuss some hybrid methods based knowledge and deep learning. We compare their disadvantages and advantages and point out in which ways these studies can be improved further. Our discussion covers some studies published in leading conferences such as IJCAI and AAAI in recent years.

Keywords: Retrieval, generative, deep learning, response generation, knowledge.

References:

[1] K. Abe, K. Kurokawa, K. Taketa, S. Ohno, and H. Fujisaki. A new method for dialogue management in an intelligent system for information retrieval. In Processings of the 16th International Conference on Spoken Language Processing, pages 1–4, 2008.
[2] J. Aron. How innovative is Apple’s new voice assistant, Siri? New Scientist, 212(2836):24–24, 2011.
[3] C. Asakiewicz, E.A. Stohr, S. Mahajan, and L. Pandey. Building a cognitive application using watson deepqa. IT Professional, 19(4):36–44, 2017.
[4] A. Bordes, Y. L. Boureau, and J. Weston. Learning end-to-end goal-oriented dialog. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, pages 1–15, 2017.
[5] T. Broens, S. Pokraev, J. Sinderen, M.V.and Koolwaaij, and P.D. Costa. Context-aware, ontology-based service discovery. In Proceedings of the 2004 European Symposium on Ambient Intelligence, pages 72–83, 2004.
[6] C. Chen, Q.Q. Zhu, R. Yan, and J.F. Liu. A summary of research on open domain dialogue system based on deep learning. Chinese Journal of Computers, 42(7):1439–1461, 2019. (In chinese).
[7] H. Chen, X. Liu, D. Yin, and J. Tang. A survey on dialogue systems: Recent advances and new frontiers. Acm Sigkdd Explorations Newsletter, 19(2):25–35, 2017.
[8] B. Dhingra, L. Li, X. Li, J. Gao, Y.-N. Chen, F. Ahmed, and L. Deng. Towards end-to-end reinforcement learning of dialogue agents for information access. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, volume 1, pages 484–495, 2017.
[9] P. Ehrenbrink, S. Osman, and S. M¨oller. Google now is for the extraverted, cortana for the introverted: Investigating the influence of personality on ipa preference. In Proceedings of the 29th Australian Conference on Computer-Human Interaction, pages 257–265, 2017.
[10] M. Eric and C. D. Manning. Key-value retrieval networks for task-oriented dialogue. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 37–49, 2017.
[11] D. Goddeau, H. Meng, J. Polifroni, S. Seneff, and S. Busayapongchai. A form-based dialogue manager for spoken language applications. In Proceedings of the 4th International Conference on Spoken Language Processing, pages 701–704, 1996.
[12] S.Z. He, C. Liu, K. Liu, and J. Zhao. Generating natural answers by incorporating copying and retrieving mechanisms in sequence-to-sequence learning. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, page 199208, 2017.
[13] T. Holstein, M. Wallmyr, J. Wietzke, and R. Land. Current Challenges in Compositing Heterogeneous User Interfaces for Automotive Purposes, pages 531–542. Computer Science, 2015.
[14] L. Hurtado, J. Planells, E. Segarra, and E. Sanchis. Spoken dialog systems based on online generated stochastic finite-state transducers. Speech Communication, 83:81–93, 2016.
[15] V. Ilievski, C. Musat, A. Hossmann, and M. Baeriswyl. Goal-oriented chatbot dialog management bootstrapping with transfer learning. In Proceedings of the 27th International Joint Conference on Artificial Intelligence Organization, pages 4115–4120, 2018.
[16] E.S. Juliano, F. Andre, and Siegfried H. An open vocabulary semantic parser for end-user programming using natural language. In Proceedings of the 12th IEEE International Conference on Semantic Computing, pages 77–83, 2019.
[17] K. Kim, C. Lee, D. Lee, J. Choi, S. Jung, and G.G. Lee. Modeling confirmations for example-based dialog management. In Proceedingd of 3rd IEEE Spoken Language Technology Workshop, pages 324–329, 2010.
[18] S. Kim, I. Kang, and N. Kwak. Semantic sentence matching with densely-connected recurrent and co-attentive information. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence, volume 33, pages 6586–6593, 2019.
[19] S. Koo, G.G. Lee, and H. Yu. Mathematical model for processing multi-user requests on POMDP hybrid dialog management. In Proceedings of the 10th International Conference on Ubiquitous Information Management and Communication, pages 1–4, 2016.
[20] J.-P. Kruth, T.V. Ginderachter, P.-I. Tanaya, and P. Valckenaers. The use of finite state machines for task-based machine tool control. Computers in Industry, 46(3):247–258, 2001.
[21] C. Lee, Y.S. Cha, and T.Y. Kuc. Implementation of dialogue system for intelligent service robots. In Processings of 2rd International Conference on Control, Automation and Systems, pages 2038–2041, 2008.
[22] C. Lee, S. Jung, M. Jeong, and G.G. Lee. Chat and goal-oriented dialog together: a unified example-based architecture for multi-domain dialog management. In Proceedings of the 1st IEEE Spoken Language Technology Workshop, pages 194–197, 2006.
[23] C. Lee, S. Jung, S. Kim, and G.G Lee. Example-based dialog modeling for practical multi-domain dialog system. Speech Communication, 51(5):466–484, 2009.
[24] J. Li, W. Monroe, A. Ritter, M. Galley, J. Gao, and D. Jurafsky. Deep reinforcement learning for dialogue generation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1192–1202, 2016.
[25] J. Li, W. Monroe, T. Shi, S. Jean, A. Ritter, and D. Jurafsky. Adversarial learning for neural dialogue generation. In Proceedings of the 22nd Empirical Methods in Natural Language Processing, page 21572169, 2017.
[26] X.-S Li. Design and implementation of question answering system based on retrieval and answer generation. Master’s thesis, 2019.
[27] Y. Li, J. Cao, and Y.B. Wang. Implementation of intelligent question answering system based on basketball knowledge graph. In Proceedings of the 2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference, pages 2601–2604, 2019.
[28] Y. Li, K. Qian, W.Y. Shi, and Z. Yu. End-to-end trainable non-collaborative dialog system. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, pages 8293–8302, 2020.
[29] Z.D. Lu and H. Li. A deep architecture for matching short texts. In Proceedings of the 2013 Neural Information Processing Systems, page 13671375, 2013.
[30] A. Madotto, C.S. Wu, and P. Fung. Mem2seq: Effectively incorporating knowledge bases into end-to-end task-oriented dialog systems. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pages 1468–1478, 2018.
[31] H. Mei, M. Bansal, and M.R. Walter. Coherent dialogue with attention-based language models. In Proceedings of the 31st AAAI Conference on Artificial Intelligence, pages 3252–3258, 2017.
[32] F. Mi, M. Huang, J. Zhang, and B. Faltings. Meta-learning for low-resource natural language generation in task-oriented dialogue systems. In Proceedings of the 28th International Joint Conference on Artificial Intelligence Organization, pages 3151–3157, 2019.
[33] H. Noh, S. Ryu, D. Lee, K. Lee, C. Lee, and G.G Lee. An example-based approach to ranking multiple dialog states for flexible dialog management. IEEE Journal of Selected Topics in Signal Processing, 6(8):943–958, 2012.
[34] H.J. Oh, C.H. Lee, M.G. Jang, and K.Y. Lee. An intelligent TV interface based on statistical dialogue management. IEEE Transactions on Consumer Electronics, 53(4):1602–1607, 2007.
[35] M.-J. Peng, Y.W. Qin, C.X. Tang, and X.M. Deng. An e-commerce customer service robot based on intention recognition model. Journal of Electronic Commerce in Organizations, 14(1):34–44, 2016.
[36] M. Qiu, F.-L Li, S. Wang, X. Gao, Y. Chen, W. Zhao, H. Chen, J. Huang, and Chu W. Alime chat: A sequence to sequence and rerank based chatbot engine. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, volume 2, page 498503, 2017.
[37] A. Raux and M. Eskenazi. A finite-state turn-taking model for spoken dialog systems. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 629–637, 2009.
[38] A. Ritter, C. Cherry, and W.B. Dolan. Data-driven response generation in social media. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, page 583593, 2011.
[39] I. V. Serban, C. Sankar, M. Germain, S. Zhang, Z. Lin, S. Subramanian, T. Kim, M. Pieper, S. Chandar, and N. R. Ke. A deep reinforcement learning chatbot. arXiv preprint arXiv:1709.02349, 2017.
[40] I.V. Serban, A. Sordoni, R. Lowe, L. Charlin, J. Pineau, A. Aaron Courville, and Y. Bengio. A hierarchical latent variable encoder-decoder model for generating dialogues. In Proceedings of the 31st AAAI Conference on Artificial Intelligence, pages 2157–2169, 2017.
[41] L.F. Shang, Z.D. Lu, and H. Li. Neural responding machine for short-text conversation. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), page 15771586, 2015.
[42] Y. Shao, S. Gouws, D. Britz, A. Goldie, B. Strope, and R. Kurzweil. Generating high-quality and informative conversation responses with sequence-to-sequence models. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, page 22102219, 2017.
[43] B. Shen and D. Inkpen. Speech intent recognition for robots. In Proceedingds of the 3rd International Conference on Mathematics and Computers in Sciences and in Industry, pages 185–189, 2017.
[44] Y.L. Shen, X.D. He, L. Gao, J.F. Deng, and G. Mesnil. Learning semantic representations using convolutional neural networks for web search. In Proceedings of the 2014 International World Wide Web Conference, page 373374, 2014.
[45] Z.X. Shi and M.L. Huang. A deep sequential model for discourse parsing on multi-party dialogues. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence, pages 7007–7013, 2019.
[46] O. Sihombing, N. Zendrato, Y. Laia, M. Nababan, D. Sitanggang, W. Purba, D. Batubara, S. Aisyah, E. Indra, and S. Siregar. Smart home design for electronic devices monitoring based wireless gateway network using cisco packet tracer. Journal of Physics Conference Series, 1007(1):12–21, 2018.
[47] H.Y. Song, W.-N. Zhang, J.-W. Hu, and T. Liu. Generating persona consistent dialogues by exploiting natural language inference. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, pages 1–8, 2020.
[48] Y. Song, R. Yan, X. Li, D. Zhao, and M. Zhang. Two are better than one: An ensemble of retrieval- and generation-based dialog systems. arXiv preprint arXiv:1610.07149, 2016.
[49] Y.P. Song, X.Y. Zhou, and H. Wu. shall i be your chat companion?: Towards an online human-computer conversation system. In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, page 649658, 2016.
[50] R. Tanaka, A. Ozeki, S. Kato, and A. Lee. Context and knowledge aware conversational model and system combination for grounded response generation. Computer Speech & Language, 62:1–10, 2020.
[51] A. Verma and A. Arora. Reflexive hybrid approach to provide precise answer of user desired frequently asked question. In Proceedings of the 7th International Conference on Cloud Computing, Data Science and Engineering - Confluence, pages 159–162, 2017.
[52] S.X. Wan, Y.Y. Lan, J.F. Guo, L. Xu, J. Pang, and X.Q. Cheng. A deep architecture for semantic matching with multiple positional sentence representations. In Proceedings of the 2016 National Conference on Artificial Intelligence, page 28352841, 2016.
[53] J. Wang, J.H. Liu, W. Bi, X.J. Liu, K.J. He, R.F. Xu, and M. Yang. Improving knowledge-aware dialogue generation via knowledge base question answering. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, pages 1–8, 2020.
[54] W. Wang, M. Huang, X. Xu, F. Shen, and L. Nie. Chat more: Deepening and widening the chatting topic via a deep model. In Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, page 255264, 2018.
[55] Y. Wang, F.-J. Ren, and C.-Q. Quan. Review of dialogue management methods in spoken dialogue system. Computer Science, 42(6):1–6, 2015. (In chinese).
[56] Y.-G Wei, X.-M. Zhu, S. Bo, and B. Sun. Comparative studies of aiml. In Proceedings of the 3rd International Conference on Systems and Informatics, pages 344–349, 2016.
[57] T.-H. Wen, D. Vandyke, N. Mrksic, M. Gasic, L. M. Rojas-Barahona, P.-H. Su, S. Ultes, and S. Young. A network-based end-to-end trainable task-oriented dialogue system. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, volume 1, pages 438–449, 2017.
[58] J. Wu, M. Li, and C.H. Lee. A probabilistic framework for representing dialog systems and entropy-based dialog management through dynamic stochastic state evolution. IEEE/ACM Transactions on Audio Speech and Language Processing, 23(11):2026–2035, 2015.
[59] Y. Wu, G. Nong, W.-H Chan, and L.-B. Han. Checking big suffix and lcp arrays by probabilistic methods. IEEE Transactions on Computers, 65(10):1667–1674, 2017.
[60] Y. Wu, W. Wu, C. Xing, M. Zhou, and Z.J. Li. Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, volume 1, page 496505, 2017.
[61] Y. Wu, W. Wu, D. Yang, C. Xu, and Z. Li. Neural response generation with dynamic vocabularies. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, pages 5594–5601, 2018.
[62] H. Xu, J. Bao, and J. Wang. Knowledge-graph based proactive dialogue generation with improved meta-learning. arXiv preprint arXiv:2004.08798, 2020.
[63] Z. Yan, N. Duan, P. Chen, M. Zhou, J. Zhou, and Z. Li. Building task-oriented dialogue systems for online shopping. In Proceedings of the 31st AAAI Conference on Artificial Intelligence, pages 4618–4625, 2017.
[64] M. Yang, Q.G Jiang, Y. Shen, Q.Y. Wu, Z. Zhao, and W. Zhoue. Hierarchical human-like strategy for aspect-level sentiment classification with sentiment linguistic knowledge and reinforcement learning. Neural Networks, 117:240–248, 2019.
[65] YanR., Y.P. Song, and H. Wu. Learning to respond with deep neural networks for retrieval-based human-computer conversation system. In Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, page 5564, 2016.
[66] W.P. Yin, H. Schtze, B. Xiang, and B. Zhou. Abcnn: Attention-based convolutional neural network for modeling sentence pairs. Transactions of the Association for Computational Linguistics, 4(1):259–272, 2016.
[67] Y.Y. Zhang, Q. Fang, S.S. Qian, and C.S. Xu. Knowledge-aware attentive wasserstein adversarial dialogue response generation. ACM Transactions on Intelligent Systems and Technology, 11(4):1–15, 2020.
[68] Z.S. Zhang, J.T. Li, P.F. Zhu, H. Zhao, and G.S. Liu. Modeling multi-turn conversation with deep utterance aggregation. In Proceedings of the 27th International Conference on Computational Linguistics, page 37403752, 2018.
[69] T.-C. Zhao, K. Xie, and M. Eskenazi. Rethinking action spaces for reinforcement learning in end-to-end dialog agents with latent variable models. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, page 12081218, 2019.
[70] X.L. Zhao, W. Wu, C.Y. Tao, C. Xu, D.Y. Zhao, and R. Yan. Low-resource knowledge-grounded dialogue generation. In Proceedings of the 2020 International Conference on Learning Representations, pages 1–14, 2020.
[71] X.Y. Zhou, L. Li, D.X. Dong, Y. Liu, Y. Chen, W.X. Zhao, D. H. Yu, and H. Wu. Multi-turn response selection for chatbots with deep attention matching network. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, volume 1, page 11181127, 2018.