{"type":"ScholarlyArticle","title":"Exploiting Persona Information for Diverse Generation of Conversational Responses","authors":[{"name":"Haoyu Song","slug":"haoyu-song","given":"Haoyu","family":"Song","affiliation":"Research Center for Social Computing and Information Retrieval , Harbin Institute of Technology , China"},{"name":"Wei-Nan Zhang","slug":"wei-nan-zhang","given":"Wei-Nan","family":"Zhang","affiliation":"Research Center for Social Computing and Information Retrieval , Harbin Institute of Technology , China; Peng Cheng Laboratory , Shenzhen , China"},{"name":"Yiming Cui","slug":"yiming-cui","given":"Yiming","family":"Cui","affiliation":"Research Center for Social Computing and Information Retrieval , Harbin Institute of Technology , China; Joint Laboratory of HIT and iFLYTEK (HFL) , iFLYTEK Research , Beijing , China"},{"name":"Dong Wang","slug":"dong-wang","given":"Dong","family":"Wang","affiliation":"Joint Laboratory of HIT and iFLYTEK (HFL) , iFLYTEK Research , Beijing , China"},{"name":"Ting Liu","slug":"ting-liu","given":"Ting","family":"Liu","affiliation":"Research Center for Social Computing and Information Retrieval , Harbin Institute of Technology , China; Peng Cheng Laboratory , Shenzhen , China"}],"abstract":"In human conversations, due to their personalities in mind, people can easily carry out and maintain the conversations. Giving conversational context with persona information to a chatbot, how to exploit the information to generate diverse and sustainable conversations is still a non-trivial task. Previous work on persona-based conversational models successfully make use of predefined persona information and have shown great promise in delivering more realistic responses. And they all learn with the assumption that given a source input, there is only one target response. However, in human conversations, there are massive appropriate responses to a given input message. In this paper, we propose a memory-augmented architecture to exploit persona information from context and incorporate a conditional variational autoencoder model together to generate diverse and sustainable conversations. We evaluate the proposed model on a benchmark persona-chat dataset. Both automatic and human evaluations show that our model can deliver more diverse and more engaging persona-based responses than baseline approaches.","doi":"10.24963/ijcai.2019/721","url":"https://ijcai.org/proceedings/2019/721","pdf":"https://ijcai.org/proceedings/2019/0721.pdf","markdown":"https://ijcai.org/proceedings/2019/721.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/721","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":721,"pages":{"first":5190,"last":5196},"keywords":["Natural Language Processing: Natural Language Generation","Natural Language Processing: Dialogue","Humans and AI: Personalization and User Modeling"],"videos":[],"references":[{"position":1,"raw":"[Bowman et al., 2015] Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew M. Dai, Rafal Jozefowicz, and Samy Bengio. Generating sentences from a continuous space. Computer Science, 2015.","title":"Generating sentences from a continuous space","authors":"R Samuel, Luke Bowman, Oriol Vilnis, Andrew M Vinyals, Rafal Dai, Samy Jozefowicz, Bengio","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Jiang and de Rijke, 2018] Shaojie Jiang and Maarten de Ri- jke. Why are sequence-to-sequence models so dull? un- derstanding the low-diversity problem of chatbots. arXiv preprint arXiv:1809.01941, 2018.","title":"Shaojie Jiang and Maarten de Rijke. Why are sequence-to-sequence models so dull? understanding the low-diversity problem of chatbots","authors":"Jiang, De Rijke","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Kingma and Welling, 2013] Diederik P Kingma and Max Welling. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.","title":"Auto-encoding variational bayes","authors":"P Diederik, Max Kingma, Welling","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Kottur et al., 2017] Satwik Kottur, Xiaoyu Wang, and Vítor Carvalho. Exploring personalized neural conversational models. In IJCAI, pages 3728-3734, 2017.","title":"Exploring personalized neural conversational models","authors":"Kottur","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/521"},{"position":5,"raw":"[Li et al., 2015] Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. A diversity-promoting ob- jective function for neural conversation models. arXiv preprint arXiv:1510.03055, 2015.","title":"A diversity-promoting objective function for neural conversation models","authors":"Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, Bill Dolan","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Li et al., 2016a] Jiwei Li, Michel Galley, Chris Brockett, Georgios P Spithourakis, Jianfeng Gao, and Bill Dolan. A persona-based neural conversation model. arXiv preprint arXiv:1603.06155, 2016.","title":"A persona-based neural conversation model","authors":"Li","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Li et al., 2016b] Jiwei Li, Will Monroe, Alan Ritter, Michel Galley, Jianfeng Gao, and Dan Jurafsky. Deep reinforce- ment learning for dialogue generation. arXiv preprint arXiv:1606.01541, 2016.","title":"Deep reinforcement learning for dialogue generation","authors":"Li","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Liu et al., 2016] Chia Wei Liu, Ryan Lowe, Iulian V. Ser- ban, Michael Noseworthy, Laurent Charlin, and Joelle Pineau. How not to evaluate your dialogue system: An empirical study of unsupervised evaluation met- rics for dialogue response generation. arXiv preprint arXiv:1603.08023, 2016.","title":"How not to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation","authors":"Chia Wei Liu, Ryan Lowe, Iulian V Serban, Michael Noseworthy, Laurent Charlin, Joelle Pineau","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Naaman et al., 2010] Mor Naaman, Jeffrey Boase, and Chih-Hui Lai. Is it really about me?: message con- tent in social awareness streams. In Proceedings of the 2010 ACM conference on Computer supported coopera- tive work, pages 189-192. ACM, 2010.","title":"Is it really about me?: message content in social awareness streams","authors":"Mor Naaman, Jeffrey Boase, Chih-Hui Lai","year":"2010","venue":"Proceedings of the 2010 ACM conference on Computer supported cooperative work","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Qian et al., 2017] Qiao Qian, Minlie Huang, Haizhou Zhao, Jingfang Xu, and Xiaoyan Zhu. Assigning personal- ity/identity to a chatting machine for coherent conversation generation. arXiv preprint arXiv:1706.02861, 2017.","title":"Assigning personality/identity to a chatting machine for coherent conversation generation","authors":"Qiao Qian, Minlie Huang, Haizhou Zhao, Jingfang Xu, Xiaoyan Zhu","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Rajendran et al., 2018] Janarthanan Rajendran, Jatin Gan- hotra, Satinder Singh, and Lazaros Polymenakos. Learn- ing end-to-end goal-oriented dialog with multiple answers. arXiv preprint arXiv:1808.09996, 2018.","title":"Learning end-to-end goal-oriented dialog with multiple answers","authors":"Rajendran","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Schuster and Paliwal, 1997] Mike Schuster and Kuldip K Paliwal. Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11):2673-2681, 1997.","title":"Bidirectional recurrent neural networks","authors":"Mike Schuster, Kuldip K Paliwal","year":"1997","venue":"IEEE Transactions on Signal Processing","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Serban et al., 2016] Iulian Vlad Serban, Alessandro Sor- doni, Yoshua Bengio, Aaron C Courville, and Joelle Pineau. Building end-to-end dialogue systems using gen- erative hierarchical neural network models. In AAAI, vol- ume 16, pages 3776-3784, 2016.","title":"Building end-to-end dialogue systems using generative hierarchical neural network models","authors":"Iulian Vlad Serban, Alessandro Sordoni, Yoshua Bengio, Aaron C Courville, Joelle Pineau","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Shang et al., 2015] Lifeng Shang, Zhengdong Lu, and Hang Li. Neural responding machine for short-text conversation. arXiv preprint arXiv:1503.02364, 2015.","title":"Neural responding machine for short-text conversation","authors":"Lifeng Shang, Zhengdong Lu, Hang Li","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Shum et al., 2018] Heung-Yeung Shum, Xiao-dong He, and Di Li. From eliza to xiaoice: challenges and opportunities with social chatbots. Frontiers of Information Technology & Electronic Engineering, 19(1):10-26, 2018.","title":"From eliza to xiaoice: challenges and opportunities with social chatbots","authors":"Heung-Yeung Shum, Xiao-Dong He, Di Li","year":"2018","venue":"Frontiers of Information Technology & Electronic Engineering","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Sohn et al., 2015] Kihyuk Sohn, Honglak Lee, and Xinchen Yan. Learning structured output representation using deep conditional generative models. In NIPS, 2015.","title":"Learning structured output representation using deep conditional generative models","authors":"Sohn","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Sukhbaatar et al., 2015] Sainbayar Sukhbaatar, Jason We- ston, Rob Fergus, et al. End-to-end memory networks. In NIPS, pages 2440-2448, 2015.","title":"End-to-end memory networks","authors":"Sukhbaatar","year":"2015","venue":"Sainbayar Sukhbaatar","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sutskever et al., 2014] Ilya Sutskever, Oriol Vinyals, and Quoc V Le. Sequence to sequence learning with neural networks. In NIPS, pages 3104-3112, 2014.","title":"Quoc V Le. Sequence to sequence learning with neural networks","authors":"Sutskever","year":"2014","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Turing, 1950] A. M. Turing. Computing machinery and in- telligence. Mind, 59(236):433-460, 1950.","title":"Computing machinery and intelligence","authors":"A M Turing","year":"1950","venue":"Mind","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Vinyals and Le, 2015] Oriol Vinyals and Quoc Le. A neural conversational model. arXiv preprint arXiv:1506.05869, 2015.","title":"Oriol Vinyals and Quoc Le. A neural conversational model","authors":"Le Vinyals","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Xing et al., 2016] Chen Xing, Wei Wu, Yu Wu, Jie Liu, Yalou Huang, Ming Zhou, and Wei-Ying Ma. Topic augmented neural response generation with a joint at- tention mechanism. arxiv preprint. arXiv preprint arXiv:1606.08340, 2(2), 2016.","title":"Topic augmented neural response generation with a joint attention mechanism","authors":"Chen Xing, Wei Wu, Yu Wu, Jie Liu, Yalou Huang, Ming Zhou, Wei-Ying Ma","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Yan et al., 2016] Xinchen Yan, Jimei Yang, Kihyuk Sohn, and Honglak Lee. Attribute2image: Conditional image generation from visual attributes. In European Conference on Computer Vision, pages 776-791. Springer, 2016.","title":"Attribute2image: Conditional image generation from visual attributes","authors":"Yan","year":"2016","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yavuz et al., 2018] Semih Yavuz, Abhinav Rastogi, Guan- lin Chao, and Dilek Hakkani-Tür. Deepcopy: Grounded response generation with hierarchical pointer networks. NIPS, 2018.","title":"Deepcopy: Grounded response generation with hierarchical pointer networks","authors":"Semih Yavuz, Abhinav Rastogi, Guanlin Chao, Dilek Hakkani-Tür","year":"2018","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yu et al., 2016] Zhou Yu, Ziyu Xu, Alan W Black, and Alexander Rudnicky. Strategy and policy learning for non-task-oriented conversational systems. In 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 404-412, 2016.","title":"Strategy and policy learning for non-task-oriented conversational systems","authors":"Zhou Yu, Ziyu Xu, Alan W Black, Alexander Rudnicky","year":"2016","venue":"17th Annual Meeting of the Special Interest Group on Discourse and Dialogue","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhang et al., 2018] Saizheng Zhang, Emily Dinan, Jack Ur- banek, Arthur Szlam, Douwe Kiela, and Jason Weston. Personalizing dialogue agents: I have a dog, do you have pets too? In Proceedings of the 56th ACL, pages 2204- 2213, 2018.","title":"Personalizing dialogue agents: I have a dog, do you have pets too?","authors":"Zhang","year":"2018","venue":"Proceedings of the 56th ACL","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhao et al., 2017] Tiancheng Zhao, Ran Zhao, and Maxine Eskenazi. Learning discourse-level diversity for neural di- alog models using conditional variational autoencoders. In Proceedings of the 55th ACL, pages 654-664, 2017.","title":"Learning discourse-level diversity for neural dialog models using conditional variational autoencoders","authors":"Zhao","year":"2017","venue":"Proceedings of the 55th ACL","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}