Abstract
Neural response generation can automatically produce replies for open-domain dialogue systems without hand-crafted rules or templates. Current studies follow a non-context-adaptive paradigm that employs a single response generator to deal with all dialogues. However, as a dialogue progresses, its textual characteristics (e.g., context length, information volume, involving topics) are changing, so are the issues challenging its response generation. Non-context-adaptive response generators are inflexible and may fail to achieve globally good performance without considering the differences existing among dialogues. In this paper, we propose a novel framework named as C ontext-A daptive R esponse G eneration (CARG), which assembles two different response generators to respectively handle long and short dialogues. Specifically, given a dialogue, CARG first classifies it into short or long types according to the number of its containing utterances. For a short dialogue, CARG employs a sequential reader (SR) to concatenates all utterances into a sequence aiming to construct the dialogue context by limited semantics. For a long dialogue where irrelevant noises and relevant contexts both exist, CARG uses a jumping reader (JR) to generate the response, which treats the latest utterance as the anchor and further performs selective context utilization under its guidance. We introduce ensemble learning strategy to conduct the training and testing of CARG. Extensive experimental results on two benchmark chat corpora show that the proposed CARG framework can outperform various competitive baselines, validating its effectiveness on response generation.
Similar content being viewed by others
Notes
The dataset can be downloaded at http://yanran.li/dailydialog.html.
The dataset can be downloaded at https://github.com/facebookresearch/ParlAIhttps://github.com/facebookresearch/ParlAI.
The code of our own implementations will be open-sourced at https://github.com/katherinelyx when published.
References
Brown T.B, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler DM, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language Models are Few-Shot Learners. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html
Chen H, Ren Z, Tang J, Zhao Y.E, Yin D (2018) Hierarchical variational memory network for dialogue generation. In: Proceedings of the 2018 world wide web conference on world wide web, WWW 2018, Lyon, France, April 23-27, 2018, pp 1653–1662. https://doi.org/10.1145/3178876.3186077
Cho K, van Merrienboer B, Bahdanau D, Bengio Y (2014) On the properties of neural machine translation: Encoder-decoder approaches. In: Proceedings of SSST@EMNLP 2014, eighth workshop on syntax, semantics and structure in statistical translation, Doha, Qatar, 25 October 2014, pp 103–111. Association for Computational Linguistics. https://doi.org/10.3115/v1/W14-4012, https://aclanthology.org/W14-4012/
Cho K, van Merrienboer B, Gülçehre Ç, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 conference on empirical methods in natural language processing, EMNLP 2014, October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, ACL, pp 1724–1734. https://doi.org/10.3115/v1/d14-1179
Clark L, Pantidi N, Cooney O, Doyle PR, Garaialde D, Edwards J, Spillane B, Gilmartin E, Murad C, Munteanu C, Wade V, Cowan BR (2019) What makes a good conversation?: challenges in designing truly conversational agents. In: Proceedings of the 2019 CHI conference on human factors in computing systems, CHI 2019, Glasgow, Scotland, UK, May 04-09, 2019, ACM p 475. https://doi.org/10.1145/3290605.3300705
Cuayáhuitl H, Lee D, Ryu S, Cho Y, Choi S, Indurthi SR, Yu S, Choi H, Hwang I, Kim J (2019) Ensemble-based deep reinforcement learning for chatbots. Neurocomputing 366:118–130. https://doi.org/10.1016/j.neucom.2019.08.007
Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein J, Doran C, Solorio T (eds) Proceedings of the 2019 conference of the north American chapter of the association for computational linguistics: human language technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pp 4171–4186. Association for Computational Linguistics. https://doi.org/10.18653/v1/n19-1423
Gao J, Galley M, Li L (2019) Neural approaches to conversational AI. Found Trends Inf Retr 13(2-3):127–298. https://doi.org/10.1561/1500000074
Gu JC, Ling ZH, Zhu X, Liu Q (2019) Dually interactive matching network for personalized response selection in retrieval-Based chatbots. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, Association for Computational Linguistics, pp 1845–1854
Hao M, Cao W, Liu Z, Wu M, Xiao P (2020) Visual-audio emotion recognition based on multi-task and ensemble learning with multiple features. Neurocomputing 391:42–51. https://doi.org/10.1016/j.neucom.2020.01.048
Huang M, Zhu X, Gao J (2020) Challenges in building intelligent open-domain dialog systems. ACM Trans Inf Syst 38(3):21:1–21:32. https://doi.org/10.1145/3383123
Lan T, Mao X, Wei W, Gao X, Huang H (2020) PONE: a novel automatic evaluation metric for open-domain generative dialogue systems. ACM Trans Inf Syst 39(1):71–737. https://doi.org/10.1145/3423168
Li J, Galley M, Brockett C, Gao J, Dolan B (2016) A diversity-promoting objective function for neural conversation models. In: NAACL HLT 2016, The 2016 conference of the north American chapter of the association for computational linguistics: human language technologies, San Diego California, USA, June 12-17, 2016, The Association for Computational Linguistics, pp 110–119. https://doi.org/10.18653/v1/n16-1014
Li X, Xiong H, Chen Z, Huan J, Xu C, Dou D (2021) In-network ensemble: deep ensemble learning with diversified knowledge distillation. ACM Trans Intell Syst Technol 12(5):63:1–63:19. https://doi.org/10.1145/3473464
Li Y, Su H, Shen X, Li W, Cao Z, Niu S (2017) Dailydialog: a manually labelled multi-turn dialogue dataset. In: Proceedings of the eighth international joint conference on natural language processing, IJCNLP 2017, Taipei, Taiwan, November 27 - December 1, 2017 - Volume 1: Long Papers, Asian Federation of Natural Language Processing, pp 986–995
Lin Z, Cai D, Wang Y, Liu X, Zheng H, Shi S (2020) The world is not binary: learning to rank with grayscale data for dialogue response selection. In: Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), Association for Computational Linguistics, pp 9220–9229. https://doi.org/10.18653/v1/2020.emnlp-main.741. https://www.aclweb.org/anthology/2020.emnlp-main.741
Ling Y, Cai F, Chen H, de Rijke M (2020) Leveraging context for neural question generation in open-domain dialogue systems. In: WWW ’20: the web conference 2020, Taipei, Taiwan, April 20-24, 2020, ACM / IW3C2, pp 2486–2492. https://doi.org/10.1145/3366423.3379996
Ling Y, Cai F, Hu X, Liu J, Chen W, Chen H (2021) Context-controlled topic-aware neural response generation for open-domain dialog systems. Inf Process Manag 58(1):102392. https://doi.org/10.1016/j.ipm.2020.102392
Liu Y, Feng S, Wang D, Song K, Ren F, Zhang Y (2021) A graph reasoning network for multi-turn response selection via customized pre-training. In: Thirty-Fifth AAAI conference on artificial intelligence, AAAI 2021, thirty-third conference on innovative applications of artificial intelligence, IAAI 2021, The eleventh symposium on educational advances in artificial intelligence, EAAI 2021, virtual event, February 2-9, 2021, AAAI Press, pp 13433–13442. https://ojs.aaai.org/index.php/AAAI/article/view/17585
Ma W, Cui Y, Liu T, Wang D, Wang S, Hu G (2020) Conversational word embedding for retrieval-based dialog system. In: Proceedings of the 58th annual meeting of the association for computational linguistics pp 1375–1380. ArXiv:2004.13249, https://doi.org/10.18653/v1/2020.acl-main.127
Mao Y, Cai F, Guo Y, Chen H (2021) Incorporating emotion for response generation in multi-turn dialogues. Appl Intell. https://doi.org/10.1007/s10489-021-02819-z
Olabiyi O, Khazane A, Salimov A, Mueller E (2019) An adversarial learning framework for a persona-based multi-turn dialogue model. In: Proceedings of the workshop on methods for optimizing and evaluating neural language generation. https://doi.org/10.18653/v1/W19-2301. http://aclweb.org/anthology/W19-2301. Association for Computational Linguistics, Minneapolis, Minnesota, pp 1–10
Pan Z.F, Bai K, Wang Y, Zhou L, Liu X (2019) Improving open-domain dialogue systems via multi-turn incomplete utterance restoration. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, Association for Computational Linguistics, pp 1824–1833. https://doi.org/10.18653/v1/D19-1191
Papineni K, Roukos S, Ward T, Zhu W (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics, July 6-12, 2002, Philadelphia, PA, USA, ACL, pp. 311–318. https://doi.org/10.3115/1073083.1073135. https://aclanthology.org/P02-1040/
Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21:140:1–140:67
Serban IV, Sordoni A, Bengio Y, Courville AC, Pineau J (2016) Building end-to-end dialogue systems using generative hierarchical neural network models. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, February 12-17, 2016, Phoenix, Arizona, USA, AAAI Press, pp 3776–3784
Serban IV, Sordoni A, Lowe R, Charlin L, Pineau J, Courville AC, Bengio Y (2017) A hierarchical latent variable encoder-decoder model for generating dialogues. In: Proceedings of the thirty-first AAAI conference on artificial intelligence, February 4-9, 2017, San Francisco, California, USA, AAAI Press, pp 3295–3301
Shen L, Feng Y (2020) CDL: curriculum dual learning for emotion-controllable response generation. In: Proceedings of the 58th annual meeting of the association for computational linguistics, ACL 2020, Online, July 5-10, 2020, Association for Computational Linguistics, pp 556–566. https://doi.org/10.18653/v1/2020.acl-main.52https://doi.org/10.18653/v1/2020.acl-main.52
Shen X, Su H, Niu S, Demberg V (2018) Improving variational encoder-decoders in dialogue generation. In: Proceedings of the thirty-second AAAI conference on artificial intelligence, (AAAI-18), the 30th innovative applications of artificial intelligence (IAAI-18), and the 8th AAAI symposium on educational advances in artificial intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018, AAAI Press, pp 5456–5463. https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16402
Shum H, He X, Li D (2018) From eliza to xiaoice: challenges and opportunities with social chatbots. Frontiers Inf Technol Electron Eng 19(1):10–26. https://doi.org/10.1631/FITEE.1700826
Song Y, Li CT, Nie JY, Zhang M, Zhao D, Yan R (2018) An ensemble of retrieval-based and generation-based human-computer conversation systems. In: Proceedings of the 27th international joint conference on artificial intelligence, IJCAI’18, AAAI Press, p 4382–4388
Su H, Shen X, Zhang R, Sun F, Hu P, Niu C, Zhou J (2019) Improving multi-turn dialogue modelling with utterance rewriter. In: Proceedings of the 57th conference of the association for computational linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, Association for Computational Linguistics, pp 22–31. https://doi.org/10.18653/v1/p19-1003
Su Y, Cai D, Zhou Q, Lin Z, Baker S, Cao Y, Shi S, Collier N, Wang Y (2021) Dialogue response selection with hierarchical curriculum learning. In: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, Association for Computational Linguistics, pp 1740–1751. https://doi.org/10.18653/v1/2021.acl-long.137
Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems 27: annual conference on neural information processing systems 2014, December 8-13 2014, Montreal, Quebec, Canada, pp 3104–3112
Tuan Y, Chen Y, Lee H (2019) Dykgchat: Benchmarking dialogue generation grounding on dynamic knowledge graphs. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, Association for Computational Linguistics, pp 1855–1865. https://doi.org/10.18653/v1/D19-1194
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems 30: annual conference on neural information processing systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp 5998–6008
Wang W, Huang M, Xu X, Shen F, Nie L (2018) Chat more: deepening and widening the chatting topic via a deep model. In: The 41st International ACM SIGIR conference on research & development in information retrieval, SIGIR 2018, Ann Arbor, MI, USA, July 08-12, 2018, ACM, pp 255–264. https://doi.org/10.1145/3209978.3210061
Wang Y, Wu L, Xia Y, Qin T, Zhai C, Liu T (2020) Transductive ensemble learning for neural machine translation. In: The thirty-fourth AAAI conference on artificial intelligence, AAAI 2020, the thirty-second innovative applications of artificial intelligence conference, IAAI 2020, The tenth AAAI symposium on educational advances in artificial intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020, AAAI Press, pp 6291–6298. https://ojs.aaai.org/index.php/AAAI/article/view/6097
Williams JD, Raux A, Henderson M (2016) The dialog state tracking challenge series: a review. Dialogue Discourse 7(3):4–33. http://dad.uni-bielefeld.de/index.php/dad/article/view/3685
Wu Q, Wang P, Shen C, Reid ID, van den Hengel A (2018) Are you talking to me? reasoned visual dialog generation through adversarial learning. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, Computer Vision Foundation / IEEE Computer Society, pp 6106–6115. https://doi.org/10.1109/CVPR.2018.00639. http://openaccess.thecvf.com/content_cvpr_2018/html/Wu_Are_You_Talking_CVPR_2018_paper.html
Wu Y, Wei F, Huang S, Wang Y, Li Z, Zhou M (2019) Response generation by context-aware prototype editing. In: The thirty-third AAAI conference on artificial intelligence, AAAI 2019, the thirty-first innovative applications of artificial intelligence conference, IAAI 2019, the ninth AAAI symposium on educational advances in artificial intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019, AAAI Press, pp 7281–7288. https://doi.org/10.1609/aaai.v33i01.33017281
Xing C, Wu Y, Wu W, Huang Y, Zhou M (2018) Hierarchical recurrent attention network for response generation. In: Proceedings of the thirty-second AAAI conference on artificial intelligence, (AAAI-18), the 30th innovative applications of artificial intelligence (IAAI-18), and the 8th AAAI symposium on educational advances in artificial intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018, AAAI Press, pp 5610–5617
Xu F, Xu G, Wang Y, Wang R, Ding Q, Liu P, Zhu Z (2021) Diverse dialogue generation by fusing mutual persona-aware and self-transferrer. https://doi.org/10.1007/s10489-021-02660-4
Yang M, Huang W, Tu W, Qu Q, Shen Y, Lei K (2020) Multitask learning and reinforcement learning for personalized dialog generation: an empirical study. IEEE Transactions on Neural Networks and Learning Systems
Zhang H, Liu Z, Xiong C, Liu Z (2020) Grounded conversation generation as guided traverses in commonsense knowledge graphs. In: Proceedings of the 58th annual meeting of the association for computational linguistics, ACL 2020, Online, July 5-10, 2020, Association for Computational Linguistics, pp 2031–2043. https://doi.org/10.18653/v1/2020.acl-main.184
Zhang J, Tao C, Xu Z, Xie Q, Chen W, Yan R (2019) Ensemblegan: Adversarial learning for retrieval-generation ensemble model on short-text conversation. In: Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval, SIGIR’19. https://doi.org/10.1145/3331184.3331193. Association for Computing Machinery, New York, pp 435–444
Zhang S, Dinan E, Urbanek J, Szlam A, Kiela D, Weston J (2018) Personalizing dialogue agents: I have a dog, do you have pets too?. In: Proceedings of the 56th annual meeting of the association for computational linguistics, ACL 2018, Melbourne, Australia, July 15-20, 2018, Volume 1: Long Papers, Association for Computational Linguistics, pp 2204–2213. https://doi.org/10.18653/v1/P18-1205. https://aclanthology.org/P18-1205/
Zhang T, Kishore V, Wu F, Weinberger KQ, Artzi Y (2020) Bertscore: evaluating text generation with BERT. In: 8Th international conference on learning representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. Openreview.net
Zhang W, Cui Y, Wang Y, Zhu Q, Li L, Zhou L, Liu T (2018) Context-sensitive generation of open-domain conversational responses. In: Proceedings of the 27th international conference on computational linguistics, COLING 2018, Santa Fe, New Mexico, USA, August 20-26, 2018, Association for Computational Linguistics, pp 2437–2447. https://aclanthology.org/C18-1206/
Zhang Y, Sun S, Galley M, Chen Y, Brockett C, Gao X, Gao J, Liu J, Dolan B (2020) DIALOGPT : large-scale generative pre-training for conversational response generation. In: Proceedings of the 58th annual meeting of the association for computational linguistics: system demonstrations, ACL 2020, Online, July 5-10, 2020, Association for Computational Linguistics, pp 270–278. https://doi.org/10.18653/v1/2020.acl-demos.30
Zhang Y, Wang Y, Zhang L, Zhang Z, Gai K (2019) Improve diverse text generation by self labeling conditional variational auto encoder. In: IEEE international conference on acoustics, speech and signal processing, ICASSP 2019, Brighton, United Kingdom, May 12-17, 2019, IEEE, pp 2767–2771. https://doi.org/10.1109/ICASSP.2019.8683090
Zhao X, Wu W, Xu C, Tao C, Zhao D, Yan R (2020) Knowledge-grounded dialogue generation with pre-trained language models. In: Proceedings of the 2020 conference on empirical methods in natural language processing, EMNLP 2020, Online, November 16-20, 2020, Association for Computational Linguistics, pp 3377–3390. https://doi.org/10.18653/v1/2020.emnlp-main.272
Zhou K, Zhang K, Wu Y, Liu S, Yu J (2019) Unsupervised context rewriting for open domain conversation. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, Association for Computational Linguistics, pp 1834–1844. https://doi.org/10.18653/v1/D19-1192
Zhou L, Gao J, Li D, Shum H (2020) The design and implementation of xiaoice, an empathetic social chatbot. Comput Linguist 46(1):53–93. https://doi.org/10.1162/coli_a_00368
Zhou X, He J, Yang C (2022) An ensemble learning method based on deep neural network and group decision making. Knowl Based Syst 239:107801. https://doi.org/10.1016/j.knosys.2021.107801
Zhou ZH (2012) Ensemble methods: foundations and algorithms ensemble methods: foundations and algorithms
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ling, Y., Liang, Z., Wang, T. et al. Sequential or jumping: context-adaptive response generation for open-domain dialogue systems. Appl Intell 53, 11251–11266 (2023). https://doi.org/10.1007/s10489-022-04067-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-04067-1