隨著人口進入老年化，年長者們的身心理問題受到重視，他們的孤獨感以及失落感需要我們更有耐心地傾聽，並且給予他們具有同理心的回應。為此，本論文根據年長者特定對話情境打造一個具同理心回應之對話系統，透過採取同理心的溝通技巧來確實地表達對於他們情緒以及語意上的了解，在傾聽之外也幫助對方了解自己。過去有學者曾提出過同理對話系統，但是在具有同理回應句的生成上，並未考慮使用者的個人經驗，未檢驗生成回應句的情緒是否符合使用者情緒，且並未參考心理學中的同理技巧來反映使用者的事件及情緒。
因此，本論文在年長者們常見的健康主題上，希望透過在對話中展現同理技巧，來做出更具有同理心的回應句，提供心理上的支持。由於展現同理心的語料缺乏，本論文參考了心理學中同理心相關定義訂定回應規範，收集了年長者特定情境下的對話語料，並將語料依照使用者情緒、使用者個人經驗和系統對話動作進行標記。對輸入的使用者句子，透過長詞優先比對法取得使用者的Slot-Value表，同時透過Slot-Value的取代將使用者句子轉換為樣板句。接著透過BERT模型取得使用者情緒以及預計採取的系統對話動作，並將得到的情緒、系統動作和個人經驗作為回應句生成條件，再透過考量了情緒分類的對抗式學習，生成反映使用者情緒的樣板句。最後，經Slot-Value表填詞以反映使用者事件。
本論文總共收集1740組健康相關對話，採用五次交叉驗證方法作為實驗結果評估。在同理心回應句生成實驗中，實驗結果顯示應用條件式對抗學習的方法在情緒反映上有86.4%的完成度，相較於Transformer模型以及條件式Transformer模型有些微的提升，在事件反映上採用生成樣板填詞的方式則有90.5%的完成度，在BLEU分數也有提升。

As the population ages, the mental health and physical health of the elderly become an increasingly crucial issue. Their sense of loneliness and loss require us to listen more patiently and give them empathetic responses. To this end, an empathetic dialogue system for the elderly is proposed. Through the use of empathy, the system can obtain a greater understanding of the user’s emotion and situation, which in turn assist the system to help the user to understand themselves. Past empathetic dialogue systems did not consider personal experience or verify the emotional appropriateness of the generated response. Neither did past systems employ empathetic techniques drawn from psychology to deal with user’s emotions and their situation.
Therefore, the proposed dialogue system aims to provide a more empathetic response in common health topics for the elderly. The creation of such a response is done by generating a template sentence and filling it in using a Slot-Value table. The proposed system utilizes BERT to decide on the system dialogue act and emotion of the user response. Using the decision made by BERT, a controlled generation of a template is performed with a transformer trained with adversarial training. Finally, Slot-Value table is used to fill the generated template. Due to the lack of empathetic dialogue dataset, 1740 turns dialogues from the elderly containing empathetic response as defined in psychology were collected. The collected data were labeled for the user’s emotion, experience, and system dialogue act. Each user input sentence was processed with maximum matching to extract the Slot-Value table, then the input sentence was converted into a template sentence by emptying out the slots. These template sentences were used for training the transformer.
The experimental results from 5-fold cross-validation showed the conditional adversarial training approach yielded an 86.4% accuracy in response emotion selection and 90.5% accuracy in event selection, which was slightly better than the transformer, and a proposed transformer with conditional input. On top of that, the BLEU score for the proposed conditional adversarial training approach was also higher.

[1] E. Devaney. "The State of Chatbots Report: How Chatbots Are Reshaping Online Experiences." https://www.drift.com/blog/chatbots-report/ (accessed Aug 14, 2019).
[2] M. Ochs, C. Pelachaud, and D. Sadek, "An empathic virtual dialog agent to improve human-machine interaction," in Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems-Volume 1, 2008: International Foundation for Autonomous Agents and Multiagent Systems, pp. 89-96.
[3] P. Fung et al., "Towards empathetic human-robot interactions," in International Conference on Intelligent Text Processing and Computational Linguistics, 2016: Springer, pp. 173-193.
[4] Y. Yang, X. Ma, and P. Fung, "Perceived emotional intelligence in virtual agents," in Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems, 2017: ACM, pp. 2255-2262.
[5] R. R. Carkhuff, Helping and human relations: A primer for lay and professional helpers. Holt, Rinehart and Winston New York, 1969.
[6] 黃惠惠, 助人歷程與技巧 (增訂版). 張老師, 1991.
[7] F. B. Siddique, O. Kampman, Y. Yang, A. Dey, and P. Fung, "Zara returns: Improved personality induction and adaptation by an empathetic virtual agent," Proceedings of ACL 2017, system demonstrations, pp. 121-126, 2017.
[8] G. I. Winata, O. Kampman, Y. Yang, A. Dey, and P. Fung, "Nora the Empathetic Psychologist," in INTERSPEECH, 2017, pp. 3437-3438.
[9] P. Fung, D. Bertero, P. Xu, J. H. Park, C.-S. Wu, and A. Madotto, "Empathetic Dialog Systems," in The International Conference on Language Resources and Evaluation. European Language Resources Association, 2018.
[10] E. Agirre, J. Bos, S. Manandhar, Y. Marton, and D. Yuret, "* SEM 2012: The First Joint Conference on Lexical and Computational Semantics–Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012)," in * SEM 2012: The First Joint Conference on Lexical and Computational Semantics–Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012), 2012, vol. 1.
[11] M. Purver and S. Battersby, "Experimenting with distant supervision for emotion classification," in Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, 2012: Association for Computational Linguistics, pp. 482-491.
[12] K. Roberts, M. A. Roach, J. Johnson, J. Guthrie, and S. M. Harabagiu, "EmpaTweet: Annotating and Detecting Emotions on Twitter," in Lrec, 2012, vol. 12: Citeseer, pp. 3806-3813.
[13] M. Hasan, E. Rundensteiner, and E. Agu, "Emotex: Detecting emotions in twitter messages," 2014.
[14] R. C. Balabantaray, M. Mohammad, and N. Sharma, "Multi-class twitter emotion classification: A new approach," International Journal of Applied Information Systems, vol. 4, no. 1, pp. 48-53, 2012.
[15] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "Bert: Pre-training of deep bidirectional transformers for language understanding," arXiv preprint arXiv:1810.04805, 2018.
[16] A. Agrawal and A. An, "Unsupervised emotion detection from text using semantic and syntactic relations," in Proceedings of the The 2012 IEEE/WIC/ACM International Joint Conferences on Web Intelligence and Intelligent Agent Technology-Volume 01, 2012: IEEE Computer Society, pp. 346-353.
[17] A. Vaswani et al., "Attention is all you need," in Advances in neural information processing systems, 2017, pp. 5998-6008.
[18] R. E. Frederking, "A rule-based conversation participant," in Proceedings of the 19th annual meeting on Association for Computational Linguistics, 1981: Association for Computational Linguistics, pp. 83-87.
[19] H. Chen, X. Liu, D. Yin, and J. Tang, "A survey on dialogue systems: Recent advances and new frontiers," ACM SIGKDD Explorations Newsletter, vol. 19, no. 2, pp. 25-35, 2017.
[20] I. Sutskever, O. Vinyals, and Q. V. Le, "Sequence to sequence learning with neural networks," in Advances in neural information processing systems, 2014, pp. 3104-3112.
[21] I. Goodfellow et al., "Generative adversarial nets," in Advances in neural information processing systems, 2014, pp. 2672-2680.
[22] T. Rocktäschel, E. Grefenstette, K. M. Hermann, T. Kočiský, and P. Blunsom, "Reasoning about entailment with neural attention," arXiv preprint arXiv:1509.06664, 2015.
[23] H. Rashkin, E. M. Smith, M. Li, and Y.-L. Boureau, "I know the feeling: Learning to converse with empathy," arXiv preprint arXiv:1811.00207, 2018.
[24] M. E. Peters et al., "Deep contextualized word representations," arXiv preprint arXiv:1802.05365, 2018.
[25] A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever, "Improving language understanding with unsupervised learning," Technical report, OpenAI, 2018.
[26] A. Odena, C. Olah, and J. Shlens, "Conditional image synthesis with auxiliary classifier gans," in Proceedings of the 34th International Conference on Machine Learning-Volume 70, 2017: JMLR. org, pp. 2642-2651.
[27] K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, "BLEU: a method for automatic evaluation of machine translation," in Proceedings of the 40th annual meeting on association for computational linguistics, 2002: Association for Computational Linguistics, pp. 311-318.