ABSTRACT
Existing emotion-aware conversational models usually focus on controlling the response contents to align with a specific emotion class, whereas empathy is the ability to understand and concern the feelings and experience of others. Hence, it is critical to learn the causes that evoke the users' emotion for empathetic responding, a.k.a. emotion causes. To gather emotion causes in online environments, we leverage counseling strategies and develop an empathetic chatbot to utilize the causal emotion information. On a real-world online dataset, we verify the effectiveness of the proposed approach by comparing our chatbot with several SOTA methods using automatic metrics, expert-based human judgements as well as user-based online evaluation.
- Siqi Bao, H. He, Fan Wang, and Hua Wu. 2020. PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable. In ACL.Google Scholar
- Natalya N. Bazarova, Y. Choi, Victoria Schwanda Sosik, Dan Cosley, and J. Whitlock. 2015. Social Sharing of Emotions on Facebook: Channel Differences, Satisfaction, and Replies. Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Computing (2015).Google Scholar
- T. Bickmore and D. Schulman. 2007. Practical approaches to comforting users with relational agents. In CHI Extended Abstracts.Google Scholar
- Ying Chen, Wenjun Hou, Xiyao Cheng, and S. Li. 2018. Joint Learning for Emotion Classification and Emotion Cause Detection. In EMNLP.Google Scholar
- Lucette B. Comer and Tanya Drollinger. 2013. Active Empathetic Listening and Selling Success: A Conceptual Framework. Journal of Personal Selling and Sales Management, Vol. 19 (2013), 15--29.Google Scholar
- J. Decety. 2010. The Neurodevelopment of Empathy in Humans. Developmental Neuroscience, Vol. 32 (2010), 257 -- 267.Google ScholarCross Ref
- J. Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT.Google Scholar
- Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, M. Zhou, and H. Hon. 2019. Unified Language Model Pre-training for Natural Language Understanding and Generation. ArXiv, Vol. abs/1905.03197 (2019).Google Scholar
- Nancy Eisenberg and Natalie D. Eggum. 2009. Empathic responding: Sympathy and personal distress.Google Scholar
- E. Goffman. 1981. Forms of talk.Google Scholar
- Lin Gui, Ruifeng Xu, Qin Lu, Dongyin Wu, and Y. Zhou. 2016. Emotion Cause Extraction, A Challenging Task with Corpus Construction. In SMP.Google Scholar
- Lin Gui, L. Yuan, Ruifeng Xu, B. Liu, Qin Lu, and Y. Zhou. 2014. Emotion Cause Detection with Linguistic Construction in Chinese Weibo Text. In NLPCC.Google Scholar
- Chenyang Huang, Osmar R Zaiane, A. Trabelsi, and Nouha Dziri. 2018. Automatic Dialogue Generation with Expressed Emotions. In NAACL-HLT.Google Scholar
- L. Karp. 2015. Can empathy be taught? Reflections from a medical student active-listening workshop. Rhode Island medical journal, Vol. 98 6 (2015).Google Scholar
- J. Li, Michel Galley, Chris Brockett, Jianfeng Gao, and W. Dolan. 2016. A Diversity-Promoting Objective Function for Neural Conversation Models. ArXiv, Vol. abs/1510.03055 (2016).Google Scholar
- Jingyuan Li and X. Sun. 2018. A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation. In EMNLP.Google Scholar
- Piji Li. 2020. An Empirical Investigation of Pre-Trained Transformer Language Models for Open-Domain Dialogue Generation. ArXiv, Vol. abs/2003.04195 (2020).Google Scholar
- Qintong Li, Piji Li, Zhumin Chen, and Z. Ren. 2020. Towards Empathetic Dialogue Generation over Multi-type Knowledge. arXiv: Computation and Language (2020).Google Scholar
- I. Loshchilov and F. Hutter. 2017. Fixing Weight Decay Regularization in Adam. ArXiv, Vol. abs/1711.05101 (2017).Google Scholar
- Nurul Lubis, S. Sakti, Koichiro Yoshino, and S. Nakamura. 2019. Dialogue Model and Response Generation for Emotion Improvement Elicitation.Google Scholar
- Navonil Majumder, Pengfei Hong, S. Peng, Jiankun Lu, Deepanway Ghosal, Alexander Gelbukh, R. Mihalcea, and Soujanya Poria. 2020. MIME: MIMicking Emotions for Empathetic Response Generation. ArXiv, Vol. abs/2010.01454 (2020).Google Scholar
- Soujanya Poria, Navonil Majumder, Devamanyu Hazarika, Deepanway Ghosal, Rishabh Bhardwaj, Samson Yu Bai Jian, Romila Ghosh, Niyati Chhaya, Alexander Gelbukh, and R. Mihalcea. 2020. Recognizing Emotion Cause in Conversations. ArXiv, Vol. abs/2012.11820 (2020).Google Scholar
- Soujanya Poria, Navonil Majumder, R. Mihalcea, and E. Hovy. 2019. Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advances. IEEE Access, Vol. 7 (2019), 100943--100953.Google ScholarCross Ref
- A. Radford and Karthik Narasimhan. 2018. Improving Language Understanding by Generative Pre-Training.Google Scholar
- Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ Questions for Machine Comprehension of Text. In EMNLP.Google Scholar
- Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y-Lan Boureau. 2019. Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset. In ACL.Google Scholar
- Ashish Sharma, I. W. Lin, Adam S. Miner, David C. Atkins, and Tim Althoff. 2021. Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach. ArXiv, Vol. abs/2101.07714 (2021).Google Scholar
- Lei Shen and Yang Feng. 2020. CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation. In ACL.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, L. Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. ArXiv, Vol. abs/1706.03762 (2017).Google Scholar
- Yida Wang, Pei Ke, Yinhe Zheng, Kaili Huang, Yong Jiang, Xiaoyan Zhu, and Minlie Huang. 2020. A Large-Scale Chinese Short-Text Conversation Dataset. In NLPCC. https://arxiv.org/abs/2008.03946Google Scholar
- Anuradha Welivita and Pearl Pu. 2020. A Taxonomy of Empathetic Response Intents in Human Social Conversations. In Proceedings of the 28th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Barcelona, Spain (Online), 4886--4899. https://doi.org/10.18653/v1/2020.coling-main.429Google ScholarCross Ref
- Thomas Wolf, Victor Sanh, Julien Chaumond, and Clement Delangue. 2019. TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents. ArXiv, Vol. abs/1901.08149 (2019).Google Scholar
- Rui Xia and Zixiang Ding. 2019. Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts. In ACL.Google Scholar
- Yizhe Zhang, S. Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and W. Dolan. 2020. DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation. In ACL.Google Scholar
- Hao Zhou, Minlie Huang, T. Zhang, Xiaoyan Zhu, and Bing Liu. 2018. Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory. In AAAI.Google Scholar
Index Terms
- Towards an Online Empathetic Chatbot with Emotion Causes
Recommendations
SEEC and CHASE: An emotion-cause pair-oriented approach and conversational dataset with heterogeneous emotions for empathetic response generation
AbstractEmpathetic Response Generation (ERG) in dialog agents has gained tremendous attention in the recent past. Among various methods used to impart empathy in the generated response, the contemporary one is using the emotion cause. Previous works of ...
Incorporating emotion for response generation in multi-turn dialogues
AbstractGenerating semantically and emotionally context-consistent responses is key to intelligent dialogue systems. Previous works mainly refer to the context in the dialogue history to generate semantically related responses, ignoring the potential ...
Towards Empathetic Car Interfaces: Emotional Triggers while Driving
CHI EA '19: Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing SystemsMonitoring the emotions of drivers can play a critical role to reduce road accidents and enable novel driver-car interactions. To help understand the possibilities, this work systematically studies the in-road triggers that may lead to different ...
Comments