Elamur Research⌕
☰
home / papers / 2018 / The Design and Implementation of XiaoIce, an Empathetic Social Chatbot

The Design and Implementation of XiaoIce, an Empathetic Social Chatbot

Paper · 2018 · Li Zhou, Jianfeng Gao, Di Li et al.

Summary

Most dialogue systems either chat briefly or complete tasks. This paper reports on Microsoft XiaoIce, an open-domain social chatbot built to become a long-term companion that meets users' needs for communication, affection and belonging. The authors combine IQ (knowledge, language and image understanding, a large set of skills) with EQ (empathy and social skills) and a consistent persona. They model social chat as hierarchical decision-making over Markov Decision Processes (MDPs), in which a dialogue manager picks among skills such as Core Chat. An empathetic computing module tracks the user's emotions, intent and mood throughout a conversation. The system is optimized for long-term engagement rather than single exchanges. Engagement is measured by expected Conversation-turns Per Session (CPS), averaged over months of logs, which makes the metric hard to game with bland replies. According to large-scale online logs, XiaoIce averages a CPS of 23, which the authors say exceeds both other chatbots and typical human conversations. The work matters as an industrial-scale example of designing chatbots around emotional engagement and ethics, not just task success.

Key points

  • XiaoIce launched in China in May 2014 and has reached over 660 million active users. It operates in five countries (China, Japan, USA, India, Indonesia) and is available through over 40 platforms, among them WeChat, QQ, Weibo, Facebook Messenger and LINE. In Japan it operates under the name Rinna.
  • The architecture consists of a dialogue manager, Core Chat, more than 230 skills (e.g., music chat, Song-On-Demand, Ticket-Booking) and an empathetic computing module.
  • The proposed success metric is expected CPS, used together with the Number of Active Users (NAU). XiaoIce reports an average CPS of 23.
  • Personas are designed per region from analysis of user conversations. The WeChat version presents as an 18-year-old girl who is reliable, sympathetic and humorous.
  • The authors name several open challenges: a unified modeling framework, grounding conversations in real-world entities, proactive assistance, and ethical design. For proactive assistance, they cite Rinna's Coupon skill, which achieved higher conversion rates than traditional ad channels.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🏢MicrosoftRedmond · United States325 works · 142,931 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksPsychology · 1,552 worksSocial Psychology · 306 works

🧭 Topics 1Research subjects and languages the work is about.Dialogue systems · 624 works

💡 Concepts 1Key ideas and methods explained on our concept pages.Chatbots · 54 works

Cite

Cite as Li Zhou, Jianfeng Gao, Di Li and Heung-Yeung Shum. 2018. The Design and Implementation of XiaoIce, an Empathetic Social Chatbot. arXiv:1812.08989.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.1812.08989 · arXiv 1812.08989

@misc{zhou2018design,
  title = {{The Design and Implementation of XiaoIce, an Empathetic Social Chatbot}},
  author = {Li Zhou, Jianfeng Gao, Di Li and Heung-Yeung Shum},
  year = {2018},
  doi = {10.48550/arxiv.1812.08989},
  eprint = {1812.08989},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1812.08989}
}

References

64 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Joshua Albrecht and Rebecca Hwa. A re-examination of machine learning approaches for sentence-level mt evaluation. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 880–887, Prague, Czech Republic, June 2007. find
  2. Peter Anderson, Basura Fernando, Mark Johnson, and Stephen Gould. Spice: Semantic propositional image caption evaluation. In European Conference on Computer Vision, pages 382–398. Springer, 2016.
  3. Peter Anderson, Xiaodong He, Chris Buehler, Damien Teney, Mark Johnson, Stephen Gould, and Lei Zhang. Bottom-up and top-down attention for image captioning and visual question answering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 6077–6086, 2018. find
  4. I Asimov. “the bicentennial man” in i. asimov, the bicentennial man and other stories, 1984. find
  5. Satanjeev Banerjee and Alon Lavie. Meteor: An automatic metric for mt evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and/or summarization, pages 65–72, 2005.
  6. Sheryl Brahnam. Strategies for handling customer abuse of ecas. Abuse: The darker side of humancomputer interaction, pages 62–67, 2005. find
  7. Yang Cai. Empathic computing. In Ambient Intelligence in Everyday Life, pages 67–85. Springer, 2006. find
  8. Wen-Feng Cheng, Chao-Chung Wu, Ruihua Song, Jianlong Fu, Xing Xie, and Jian-Yun Nie. Image inspired poetry generation in xiaoice. arXiv preprint arXiv:1808.03090, 2018. — [arXiv:1808.03090](https://arxiv.org/abs/1808.03090) find
  9. Kyunghyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, and Yoshua Bengio. On the properties of neural machine translation: Encoder–decoder approaches. In Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, pages 103–111, Doha, Qatar, October 2014. UR… — On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
  10. Kenneth Mark Colby, Sylvia Weber, and Franklin Dennis Hilf. Artificial paranoia. Artificial Intelligence, 2(1):1–25, 1971. find
  11. Heriberto Cuayáhuitl, Seonghan Ryu, Donghyeon Lee, and Jihie Kim. A study on dialogue reward prediction for open-ended conversational agents. NeurIPS Workshop on Conversational AI, 2018. find
  12. Amanda Cercas Curry and Verena Rieser. \# metoo alexa: How conversational systems respond to sexual harassment. In Proceedings of the Second ACL Workshop on Ethics in Natural Language Processing, pages 7–14, 2018. find
  13. Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. Wizard of wikipedia: Knowledge-powered conversational agents. CoRR, abs/1811.01241, 2018.
  14. Hao Fang, Saurabh Gupta, Forrest Iandola, Rupesh K Srivastava, Li Deng, Piotr Dollár, Jianfeng Gao, Xiaodong He, Margaret Mitchell, John C Platt, et al. From captions to visual concepts and back. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1473–1482, 2015. find
  15. Hao Fang, Hao Cheng, Elizabeth Clark, Ariel Holtzman, Maarten Sap, Mari Ostendorf, Yejin Choi, and Noah A Smith. Sounding board–university of washington’s alexa prize submission. Alexa prize proceedings, 2017. find
  16. Hao Fang, Hao Cheng, Maarten Sap, Elizabeth Clark, Ari Holtzman, Yejin Choi, Noah A Smith, and Mari Ostendorf. Sounding board: A user-centric and content-driven social chatbot. NAACL HLT 2018, page 96, 2018. find
  17. Denis Fedorenko, Nikita Smetanin, and Artem Rodichev. Avoiding echo-responses in a retrieval-based conversation system. In Conference on Artificial Intelligence and Natural Language, pages 91–97. Springer, 2018. find
  18. Pascale Fung, Dario Bertero, Yan Wan, Anik Dey, Ricky Ho Yin Chan, Farhad Bin Siddique, Yang Yang, Chien-Sheng Wu, and Ruixi Lin. Towards empathetic human-robot interactions. CoRR, abs/1605.04072, 2016. URL http://arxiv.org/abs/1605.04072. — [arXiv:1605.04072](https://arxiv.org/abs/1605.04072) ↗
  19. Michel Galley, Chris Brockett, Alessandro Sordoni, Yangfeng Ji, Michael Auli, Chris Quirk, Margaret Mitchell, Jianfeng Gao, and Bill Dolan. deltaBLEU: A discriminative metric for generation tasks with intrinsically diverse targets. In ACL-IJCNLP, page 445–450, 2015. find
  20. Chuang Gan, Zhe Gan, Xiaodong He, Jianfeng Gao, and Li Deng. Stylenet: Generating attractive visual captions with styles. In Proc IEEE Conf on Computer Vision and Pattern Recognition, pages 3137–3146, 2017. find
  21. Jianfeng Gao, Patrick Pantel, Michael Gamon, Xiaodong He, and Li Deng. Modeling interestingness with deep neural networks. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2–13, 2014. find
  22. Jianfeng Gao, Michel Galley, and Lihong Li. Neural approaches to conversational ai. Foundations and Trends R in Information Retrieval, 13(2-3):127–298, 2019. find
  23. Marjan Ghazvininejad, Chris Brockett, Ming-Wei Chang, Bill Dolan, Jianfeng Gao, Wen-tau Yih, and Michel Galley. A knowledge-grounded neural conversation model. In Proc. of AAAI, 2018. find
  24. Minlie Huang, Xiaoyan Zhu, and Jianfeng Gao. Challenges in building intelligent open-domain dialog systems. arXiv preprint arXiv:1905.05709, 2019a. find
  25. Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, and Larry Heck. Learning deep structured semantic models for web search using clickthrough data. In CIKM, pages 2333–2338. ACM, 2013. find
  26. Qiuyuan Huang, Pei Liu, Lei Zhang, Dapeng Wu, and Jianfeng Gao. Interweaved hierarchical neural networks for image commenting. unpublished report, 2019b. find
  27. Chandra Khatri, Behnam Hedayatnia, Anu Venkatesh, Jeff Nunn, Yi Pan, Qing Liu, Han Song, Anna Gottardi, Sanjeev Kwatra, Sanju Pancholi, et al. Advancing the state of the art in open domain dialog systems through the alexa prize. arXiv preprint arXiv:1812.10757, 2018. — [arXiv:1812.10757](https://arxiv.org/abs/1812.10757) find
  28. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. A diversity-promoting objective function for neural conversation models. In NAACL-HLT, 2016a.
  29. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. A persona-based neural conversation model. In ACL, 2016b.
  30. Jiwei Li, Will Monroe, Alan Ritter, Dan Jurafsky, Michel Galley, and Jianfeng Gao. Deep reinforcement learning for dialogue generation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1192–1202, 2016c.
  31. Chin-Yew Lin. Rouge: A package for automatic evaluation of summaries. In Proceedings of the ACL workshop. Association for Computational Linguistics, 2004.
  32. Chia-Wei Liu, Ryan Lowe, Iulian Serban, Michael Noseworthy, Laurent Charlin, and Joelle Pineau. How NOT to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation. In Proceedings of EMNLP 2016, Austin, Texas, USA, November 1-4, 2016, page…
  33. Ryan Lowe, Michael Noseworthy, Iulian Vlad Serban, Nicolas Angelard-Gontier, Yoshua Bengio, and Joelle Pineau. Towards an automatic turing test: Learning to evaluate dialogue responses. In Proceedings of ACL 2017, Vancouver, Canada, July 30 - August 4, Volume 1: Long Papers, pages 1116–1126, 2017. d…
  34. Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze. Introduction to information retrieval. Cambridge University Press, 2008. ISBN 978-0-521-86571-5. find
  35. Abraham Harold Maslow. A theory of human motivation. Psychological review, 50(4):370, 1943. find
  36. Alexander Patrick Mathews, Lexing Xie, and Xuming He. Senticap: Generating image descriptions with sentiments. In AAAI, pages 3574–3580, 2016. find
  37. Teruhisa Misu, Kallirroi Georgila, Anton Leuski, and David Traum. Reinforcement learning of question-answering dialogue policies for virtual museum guides. In Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 84–93. Association for Computational Li… find
  38. Meredith Ringel Morris, Annuska Zolyomi, Catherine Yao, Sina Bahram, Jeffrey P Bigham, and Shaun K Kane. With most of it being pictures now, i rarely use it: Understanding twitter’s evolving accessibility to blind users. In Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems… find
  39. Nasrin Mostafazadeh, Chris Brockett, Bill Dolan, Michel Galley, Jianfeng Gao, Georgios Spithourakis, and Lucy Vanderwende. Image-grounded conversations: Multimodal context for natural question and response generation. In Proceedings of the Eighth International Joint Conference on Natural Language Pr…
  40. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting on association for computational linguistics, pages 311–318. Association for Computational Linguistics, 2002.
  41. Baolin Peng, Xiujun Li, Lihong Li, Jianfeng Gao, Asli Celikyilmaz, Sungjin Lee, and Kam-Fai Wong. Composite task-completion dialogue policy learning via hierarchical deep reinforcement learning. In EMNLP, pages 2231–2240, 2017. find
  42. Rosalind W Picard. Affective computing. MIT press, 2000. find
  43. Ashwin Ram, Rohit Prasad, Chandra Khatri, Anu Venkatesh, Raefer Gabriel, Qing Liu, Jeff Nunn, Behnam Hedayatnia, Ming Cheng, Ashish Nagar, et al. Conversational ai: The science behind the alexa prize. arXiv preprint arXiv:1801.03604, 2018. find
  44. Steven J. Rennie, Etienne Marcheret, Youssef Mroueh, Jerret Ross, and Vaibhava Goel. Self-critical sequence training for image captioning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.
  45. Ananya Sai, Mithun Das Gupta, Mitesh M. Khapra, and Mukundhan Srinivasan. Response generation by context-aware prototype editing. In Proceedings of AAAI 2019, Honolulu, Hawaii, USA, January 27-February 1, 2019, 2019. find
  46. Anna Schmidt and Michael Wiegand. A survey on hate speech detection using natural language processing. In Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media, pages 1–10, 2017.
  47. Iulian Vlad Serban, Alessandro Sordoni, Yoshua Bengio, Aaron C Courville, and Joelle Pineau. Building end-to-end dialogue systems using generative hierarchical neural network models. In AAAI, volume 16, pages 3776–3784, 2016.
  48. Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron C. Courville, and Yoshua Bengio. A hierarchical latent variable encoder-decoder model for generating dialogues. In AAAI, pages 3295–3301, 2017.
  49. Lifeng Shang, Zhengdong Lu, and Hang Li. Neural responding machine for short-text conversation. In ACL-IJCNLP, pages 1577–1586, July 2015.
  50. Bayan Abu Shawar and Eric Atwell. Different measurements metrics to evaluate a chatbot system. In Proceedings of the workshop on bridging the gap: Academic and industrial research in dialog technologies, pages 89–96. Association for Computational Linguistics, 2007. find
  51. Yelong Shen, Xiaodong He, Jianfeng Gao, Li Deng, and Grégoire Mesnil. A latent semantic model with convolutional-pooling structure for information retrieval. In Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, pages 101–110. ACM, 2014. find
  52. Heung-Yeung Shum, Xiaodong He, and Di Li. From eliza to xiaoice: Challenges and opportunities with social chatbots. CoRR, abs/1801.01957, 2018. URL http://arxiv.org/abs/1801.01957. — [arXiv:1801.01957](https://arxiv.org/abs/1801.01957) ↗
  53. Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, and Bill Dolan. A neural network approach to context-sensitive generation of conversational responses. In NAACL-HLT, May 2015.
  54. Ilya Sutskever, Oriol Vinyals, and Quoc Le. Sequence to sequence learning with neural networks. In NIPS, pages 3104–3112, 2014.
  55. Richard S. Sutton, Doina Precup, and Satinder P. Singh. Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence, 112(1–2): 181–211, 1999. An earlier version appeared as Technical Report 98-74, Department of Computer Science, University of M… find
  56. Ramakrishna Vedantam, C Lawrence Zitnick, and Devi Parikh. Cider: Consensus-based image description evaluation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4566–4575, 2015.
  57. Oriol Vinyals and Quoc Le. A neural conversational model. In ICML Deep Learning Workshop, July 2015.
  58. Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan. Show and tell: A neural image caption generator. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3156–3164, 2015.
  59. Richard S Wallace. The anatomy of alice. In Parsing the Turing Test, pages 181–210. Springer, 2009. find
  60. Joseph Weizenbaum. Eliza—a computer program for the study of natural language communication between man and machine. Communications of the ACM, 9(1):36–45, 1966. find
  61. Bowen Wu, Baoxun Wang, and Hui Xue. Ranking responses oriented to conversational relevance in chat-bots. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 652–662, 2016. find
  62. Qiang Wu, Christopher JC Burges, Krysta M Svore, and Jianfeng Gao. Adapting boosting for information retrieval measures. Information Retrieval, 13(3):254–270, 2010. find
  63. Chen Xing, Wei Wu, Yu Wu, Jie Liu, Yalou Huang, Ming Zhou, and Wei-Ying Ma. Topic aware neural response generation. In AAAI, volume 17, pages 3351–3357, 2017. find
  64. Kai Zhang, Wei Wu, Fang Wang, Ming Zhou, and Zhoujun Li. Learning distributed representations of data in community question answering for question retrieval. In Proceedings of the Ninth ACM International Conference on Web Search and Data Mining, pages 533–542. ACM, 2016. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhou-2018-design-implementation-xiaoice-empathetic-social/