Elamur Research⌕
☰
home / papers / 2020 / You Impress Me: Dialogue Generation via Mutual Persona Perception

You Impress Me: Dialogue Generation via Mutual Persona Perception

Paper · 2020 · Qian Liu, Yihong Chen, Bei Chen et al.

Summary

Open-domain chit-chat systems usually learn to imitate human replies. They rarely model whether the two speakers actually come to understand each other, even though cognitive science suggests that mutual understanding is central to good conversation. The authors propose P2BOT (Persona Perception Bot), a framework built on PERSONA-CHAT, where each speaker has a persona described by a few profile sentences.

P2BOT has two parts:

  • Transmitter generates responses. It is a GPT-initialised transformer, first trained with MLE and then fine-tuned through self-play reinforcement learning between two simulated interlocutors.
  • Receiver maps the impressions formed from a partner's utterances and that partner's real persona into a shared latent space, then scores how well they match.

These match scores become "mutual persona perception" rewards for the Transmitter, combined with a language-modelling reward. On PERSONA-CHAT, P2BOT beats strong baselines in both automatic metrics and human evaluation. Its replies are more consistent, engaging and informative. The work matters because it treats mutual understanding, not only imitation, as an explicit training signal for personalised dialogue agents.

Key points

  • Transmitter architecture: 12 stacked transformer layers initialised from GPT. An auxiliary Next Utterance Prediction classifier sits on a [CLS] token and is trained against sampled distractors. At inference, its score is mixed (weight α) with the length-normalised beam-search likelihood to rank candidates.
  • Self-play setup: the speaker who opens the dialogue acts as a user with frozen parameters, while the other speaker is the learnable agent. The first utterance is taken directly from the dataset.
  • Receiver probing: tested on a synthesized set with 31 persona distractors per dialogue (32 candidates), using Hits@1 and MRR. It gains 26.3% absolute Hits@1 over an IR baseline in the original-persona mode and also performs well on revised (rephrased) personas.
  • Reported weaknesses: self-play can fall into repetitive cycles, and the bots sometimes ask redundant questions, possibly because of reward-shaping hyperparameters.
  • Code: released at github.com/SivilTaram/Persona-Dialogue-Generation. The authors list conversational recommender systems as future work.

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

🎓Fudan UniversityShanghai · China65 works · 19,402 citations🏢Microsoft Research AsiaBeijing · China54 works · 59,921 citations🎓University College LondonLondon · United Kingdom59 works · 16,463 citations🎓Beihang UniversityBeijing · China27 works · 8,089 citations

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

🧭 Topics 1Research subjects and languages the work is about.Dialogue systems · 401 works

Cite

Cite as Qian Liu, Yihong Chen, Bei Chen, Jian-Guang Lou, Zixuan Chen, Bin Zhou and Dongmei Zhang. 2020. You Impress Me: Dialogue Generation via Mutual Persona Perception. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.acl-main.131

@inproceedings{liu2020you,
  title = {{You Impress Me: Dialogue Generation via Mutual Persona Perception}},
  author = {Qian Liu, Yihong Chen, Bei Chen, Jian-Guang Lou, Zixuan Chen, Bin Zhou and Dongmei Zhang},
  booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
  year = {2020},
  doi = {10.18653/v1/2020.acl-main.131},
  url = {https://doi.org/10.18653/v1/2020.acl-main.131}
}

References

37 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, May 7-9, 2015, San Diego, CA, USA.
  2. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
  3. Emily Dinan, Varvara Logacheva, Valentin Malykh, Alexander H. Miller, Kurt Shuster, Jack Urbanek, Douwe Kiela, Arthur Szlam, Iulian Serban, Ryan Lowe, Shrimai Prabhumoye, Alan W. Black, Alexander I. Rudnicky, Jason Williams, Joelle Pineau, Mikhail Burtsev, and Jason Weston. 2019. The second conversa…
  4. Jia-Chen Gu, Zhen-Hua Ling, Xiaodan Zhu, and Quan Liu. 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 Na… find
  5. Uri Hasson, Asif A Ghazanfar, Bruno Galantucci, Simon Garrod, and Christian Keysers. 2012. Brain-to-brain coupling: a mechanism for creating and sharing a social world. Trends in cognitive sciences. find
  6. Geoffrey E. Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the knowledge in a neural network. CoRR, abs/1503.02531.
  7. Chaitanya K. Joshi, Fei Mi, and Boi Faltings. 2017. Personalization in goal-oriented dialog. CoRR, abs/1706.07503. — [arXiv:1706.07503](https://arxiv.org/abs/1706.07503) find
  8. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, May 7-9, 2015, San Diego, CA, USA. find
  9. Mike Lewis, Denis Yarats, Yann Dauphin, Devi Parikh, and Dhruv Batra. 2017. Deal or no deal? end-to-end learning of negotiation dialogues. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark. Association for Computational Linguis…
  10. Andrea Madotto, Zhaojiang Lin, Chien-Sheng Wu, and Pascale Fung. 2019. Personalizing dialogue agents via meta-learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019, Florence, Italy. Association for Computational Linguistics.
  11. Pierre-Emmanuel Mazaré, Samuel Humeau, Martin Raison, and Antoine Bordes. 2018. Training millions of personalized dialogue agents. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018, Brussels, Belgium. Association for Computational Linguistics.
  12. Alexander Miller, Will Feng, Dhruv Batra, Antoine Bordes, Adam Fisch, Jiasen Lu, Devi Parikh, and Jason Weston. 2017. ParlAI: A dialog research software platform. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2017, Copenhagen,…
  13. Oluwatobi Olabiyi, Anish Khazane, Alan Salimov, and Erik T. Mueller. 2019. An adversarial learning framework for a persona-based multi-turn dialogue model. CoRR, abs/1905.01992. find
  14. Jiwei Li, Michel Galley, Chris Brockett, Georgios Spithourakis, Jianfeng Gao, and Bill Dolan. 2016a. A persona-based neural conversation model. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, Berlin, Germany. Association for Computational Linguis…
  15. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, ACL 2002, Philadelphia, Pennsylvania, USA. Association for Computational Ling…
  16. Jiwei Li, Will Monroe, Alan Ritter, Dan Jurafsky, Michel Galley, and Jianfeng Gao. 2016b. Deep reinforcement learning for dialogue generation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas. Association for Computational Linguisti…
  17. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Te-jani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and…
  18. Qian Liu, Bei Chen, Haoyan Liu, Jian-Guang Lou, Lei Fang, Bin Zhou, and Dongmei Zhang. 2019. A split-and-recombine approach for follow-up query analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural La… find
  19. Liangchen Luo, Wenhao Huang, Qi Zeng, Zaiqing Nie, and Xu Sun. 2019. Learning personalized end-to-end goal-oriented dialog. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence, AAAI Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language underst… find
  20. Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron C. Courville, In Proceedings of the 17th Conference in Uncertainty in Artificial Intelligence, UAI 2001, August 2-5, 2001, University of Washington, Seattle, Washington, USA. find
  21. Morgan Kaufmann. and Yoshua Bengio. 2017. A hierarchical latent variable encoder-decoder model for generating dialogues. In Proceedings of the 31st AAAI Conference on Artificial Intelligence, AAAI 2019, February 4-9, 2017, San Francisco, California, USA. AAAI Press.
  22. Haoyu Song, Wei-Nan Zhang, Jingwen Hu, and Ting Liu. 2020. Generating persona consistent dialogues by exploiting natural language inference. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, AAAI 2020, February 7-12, 2020, New York City, New York, USA. AAAI Press. find
  23. Haoyu Song, Weinan Zhang, Yiming Cui, Dong Wang, and Ting Liu. 2019. Exploiting persona information for diverse generation of conversational responses. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019, August 10-16, 2019, Macao, China. find
  24. Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, and Bill Dolan. 2015. A neural network approach to context-sensitive generation of conversational responses. In Proceedings of the 2015 Conference of the North American Chapte…
  25. Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, NIPS 2014, December 8-13 2014, Montreal, Quebec, Canada. find
  26. Richard S. Sutton, David A. McAllester, Satinder P. Singh, and Yishay Mansour. 1999. Policy gradient methods for reinforcement learning with function approximation. In Advances in Neural Information Processing Systems 12: Annual Conference on Neural Information Processing Systems 1999, NIPS 1999, No… find
  27. Anna Tigunova, Andrew Yates, Paramita Mirza, and Gerhard Weikum. 2019. Listening between the lines: Learning personal attributes from conversations. In Proceedings of the World Wide Web Conference, WWW 2019, May 13-17, 2019, San Francisco, CA, USA. ACM. find
  28. Ronald J. Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning. find
  29. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, and Jamie Brew. 2019a. Huggingface’s transformers: State-of-the-art natural language processing. CoRR, abs/1910.03771.
  30. Thomas Wolf, Victor Sanh, Julien Chaumond, and Clement Delangue. 2019b. TransferTransfo: A transfer learning approach for neural network based conversational agents. CoRR, abs/1901.08149. find
  31. Yu Wu, Wei Wu, Chen Xing, Ming Zhou, and Zhoujun Li. 2017. 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, ACL 2017, Vancouver, Canada. Associati…
  32. Min Yang, Wenting Tu, Qiang Qu, Zhou Zhao, Xiaojun Chen, and Jia Zhu. 2018. Personalized response generation by dual-learning based domain adaptation. Neural Networks. find
  33. Yury Zemlyanskiy and Fei Sha. 2018. Aiming to know you better perhaps makes me a more engaging dialogue partner. In Proceedings of the 22nd Conference on Computational Natural Language Learning, CoNLL 2018, Brussels, Belgium. Association for Computational Linguistics. find
  34. Hainan Zhang, Yanyan Lan, Jiafeng Guo, Jun Xu, and Xueqi Cheng. 2018a. Reinforcing coherence for sequence to sequence model in dialogue generation. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018, July 13-19, 2018, Stockholm, Sweden. find
  35. Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 2018b. 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. Association fo…
  36. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, NIPS 2017, December…
  37. Lex Weaver and Nigel Tao. 2001. The optimal reward baseline for gradient-based reinforcement learning. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/liu-2020-you-impress-me-dialogue-generation/