請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/60972完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 鄭士康(Shyh-Kang Jeng) | |
| dc.contributor.author | Chao-Peng Liu | en |
| dc.contributor.author | 劉兆鵬 | zh_TW |
| dc.date.accessioned | 2021-06-16T10:39:13Z | - |
| dc.date.available | 2020-07-17 | |
| dc.date.copyright | 2020-07-17 | |
| dc.date.issued | 2020 | |
| dc.date.submitted | 2020-07-02 | |
| dc.identifier.citation | [1] Snyder, C. R., Shane J. Lopez, and Jennifer T. Pedrotti, Positive Psychology: The Scientific and Practical Explorations of Human Strengths, Second ed. Los Angeles: SAGE, 267–75, Print, 2011. [2] G H M Pijnenborg, Spikman, J.M., Jeronimus B.F., Aleman, 'Insight in schizophrenia: associations with empathy', European Archives of Psychiatry and Clinical Neuroscience, 2013. [3] Hodges S.D., Klein, K.J., Regulating the costs of empathy: the price of being human. Journal of Socio-Economics, 2001. [4] Rogers K, Dziobek I, Hassenstab J, Wolf OT, Convit, Who cares? Revisiting empathy in Asperger syndrome, J Autism Dev Disord. 2007. 37 (4): 709–15. [5] Frans B.M. deWaal, 'Putting the Altruism Back into Altruism: The Evolution of Empathy', Annu. Rev. Psychol. 2008. 59 (1): 279–300. [6] Waal F. B. M., Putting the altruism back into altruism: The evolution of empathy. Annual Review of Psychology. 2008. 59 (1): 279–300. [7] Batson, C.D., These things called empathy: Eight related but distinct phenomena. In J. Decety and W. Ickes (Eds.), The Social Neuroscience of Empathy 2009. p. 3–15. [8] Jamie Fraser, Ioannis Papaioannou, Oliver Lemon, Spoken conversational ai in video games: Emotional dialogue management increases user engagement. In Proceedings of the 18th International Conference on Intelligent Virtual Agents, ACM, 2018. p. 179–184. [9] Bjarke Felbo, Alan Mislove, Anders Søgaard, Iyad Rahwan, Sune Lehmann, Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017. p. 1615–1625. [10] Saif Mohammad, Felipe Bravo-Marquez, Mohammad Salameh, Svetlana Kiritchenko, Semeval2018 task 1: Affect in tweets. In SemEval@NAACLHLT, 2018. [11] Umang Gupta, Ankush Chatterjee, Radhakrishnan Srikanth, Puneet Agrawal, A sentimentand-semantics-based approach for emotion detection in textual conversations. arXiv preprint arXiv:1707.06996, 2017. [12] Rashkin, H.; Smith, E. M.; Li, M.; and Boureau, Y.-L, Towards empathetic open-domain conversation models: A new benchmark and dataset. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019. 5370–5381. [13] Ortony, Andrew, Clore, G; Collins, The Cognitive Structure of Emotions, Cambridge Univ, 1988. [14] Jan Deriu, Maurice Gonzenbach, Fatih Uzdilli, Aurelien Lucchi, Valeria De Luca, Martin Jaggi, Swisscheese at semeval-2016 task 4: Sentiment classification using an ensemble of convolutional neural networks with distant supervision. Proceedings of SemEval, 2016. p. 1124–1128. [15] Duyu Tang, Furu Wei, Nan Yang, Ming Zhou, Ting Liu, and Bing Qin, Learning sentimentspecific word embedding for twitter sentiment classification. In 52th Annual Meeting of the Association for Computational Linguistics (ACL), 2014. p. 1555–1565. [16] Saif Mohammad, #emotional tweets. In The First Joint Conference on Lexical and Computational Semantics (*SEM), Association for Computational Linguistics, 2012. p. 246–255. [17] Ben Eisner, Tim Rocktaschel, Isabelle Augenstein, Matko Bosnjak, Sebastian Riedel, emoji2vec: Learning emoji representations from their description. In 4th International Workshop on Natural Language Processing for Social Media (SocialNLP), 2016. [18] Dumitru Erhan, Yoshua Bengio, Aaron Courville, Pierre-Antoine Manzagol, Pascal Vincent, Samy Bengio, Why does unsupervised pre-training help deep learning? Journal of Machine Learning Research (JMLR), 2010. 11: p. 625–660. [19] Sven Buechel and Udo Hahn, Emotion analysis as a regression problem - dimensional models and their implications on emotion representation and metrical evaluation. In 22nd European Conference on Artificial Intelligence (ECAI), 2016. [20] Sida Wang, Christopher D Manning, Baselines and bigrams: Simple, good sentiment and topic classification. In ACL, 2012. [21] Armand Joulin, Edouard Grave, Piotr Bojanowski, Tomas Mikolov, Bag of tricks for efficient text classification, arXiv preprint arXiv:1607.01759, 2016. [22] Luka Bradeško, Dunja Mladenić, A Survey of Chabot Systems through a Loebner Prize Competition, 2012. [23] Joseph Weizenbaum, ELIZA—a computer program for the study of natural language communication between man and machine. Communications of the ACM. 1966, Vol. 9 Issue 1, p. 36-45. [24] Leuski A., Traum D., NPCeditor: creating virtual human dialogue using information retrieval techniques. 2011. Ai Mag. 32(2): p. 42–56. [25] Leuski A., Patel R., Traum D., Kennedy, B.: Building effective question answering characters. In: Proceedings of the 7th SIGdial Workshop on Discourse andDialogue. Association for Computational Linguistics. 2009. p. 18–27. [26] Banchs R.E., Li H., IRIS: a chat-oriented dialogue system based on the vector space model. In: Proceedings of the ACL 2012 System Demonstrations, Association for Computational Linguistics. 2012. p. 37–42. [27] Ji, Z., Lu, Z., Li, H.: An information retrieval approach to short text conversation.arXiv preprint arXiv:1408.6988, 2014. [28] Yan R., Song Y., Wu H., Learning to respond with deep neural networks for retrieval-based human-computer conversation system. In: Proceedings of the 39thInternational ACM SIGIR Conference on Research and Development in Informa-tion Retrieval. 2016. p. 55–64. [29] Lowe R., Pow N., Serban I., Pineau J., The Ubuntu dialogue corpus: a largedataset for research in unstructured multi-turn dialogue systems. arXiv preprintarXiv:1506.08909, 2015. [30] Rui Yan, Yiping Song, Hua Wu, Learning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System. SIGIR '16: Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval. 2016. p. 55–64. [31] Xiangyang Zhou, Daxiang Dong, Hua Wu, Shiqi Zhao, R Yan, D Yu, Xuan Liu, H Tian, Multiview response selection for human-computer conversation. EMNLP16, 2016. [32] Wu Y., Li Z., Wu W., Zhou M., Response selection with topic clues for retrieval-based chatbots. Neurocomputing 316, 2018. p. 251–261. [33] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin, Attention Is All You Need. Neural Information Processing Systems Conference. 2017. [34] Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee. Scalable Sentiment for Sequence-to-sequence Chatbot Response with Performance Analysis. arXiv preprint arXiv:1804.02504. 2018. [35] Matthew Henderson, Rami Al-Rfou, Brian Strope, Yun-hsuan Sung, Laszlo Lukacs, Ruiqi Guo, Sanjiv Kumar, Balint Miklos, Ray Kurzweil. Efficient Natural Language Response Suggestion for Smart Reply. arXiv preprint arXiv:1705.00652. 2017. [36] Kyle Swanson, Lili Yu, Christopher Fox, Jeremy Wohlwend, Tao Lei, Building a Production Model for Retrieval-Based Chatbots, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2019. [37] Knight, K., Hatzivassiloglou, V., Two-level, many-paths generation. In: Proceed-ings of the 33rd Annual Meeting on Association for Computational Linguistics, Association for Computational Linguistics. 1995. pp.252–260. [38] Ritter, A., Cherry, C., Dolan, B., Unsupervised modeling of Twitter conversations. In: Human Language Technologies: The 2010 Annual Conference of the NorthAmerican Chapter of the Association for Computational Linguistics, Association for Computational Linguistics. 2010. p. 172–180. [39] Ritter, A., Cherry, C., Dolan, W.B., Data-driven response generation in social media. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics. 2011. p. 583–593. [40] Shang, L., Lu, Z., Li, H.: Neural responding machine for short-text conversation.arXiv preprint arXiv:1503.02364, 2015. [41] Shang, L., Sakai, T., Lu, Z., Li, H., Higashinaka, R., Miyao, Y., Overview of the NTCIR-12 short text conversation task. In: NTCIR, 2016. [42] Zhaojiang Lin, Peng Xu, Genta Indra Winata, Farhad Bin Siddique, Zihan Liu, Jamin Shin, Pascale Fung. CAiRE: An End-to-End Empathetic Chatbot. arXiv preprint arXiv: 1907.12108. 2019. [43] Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. Improving language understanding by generative pre-training. 2018. [44] Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever. Language models are unsupervised multitask learners. OpenAI Blog. 2019. 1(8). [45] Minh-Thang Luong, Hieu Pham, Christopher D. Manning, Effective Approaches to Attention-based Neural Machine Translation. arXiv:1508.04025v5. 2015. [46] Harsh Jhamtani, Varun Gangal, Eduard Hovy, Eric Nyberg, Shakespearizing modern language using copy-enriched sequence-to-sequence models. In Proceedings of the Workshop on Stylistic Variation, 2017. p. 10–19. [47] Yuta Kikuchi, Graham Neubig, Ryohei Sasano, Hiroya Takamura, and Manabu Okumura. Controlling output length in neural encoder-decoders. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2016. p. 1328–1338. [48] Tong Niu and Mohit Bansal, Polite dialogue generation without parallel data. Transactions of the Association for Computational Linguistics, 2018. 6: p.373–389. [49] Juncen Li, Robin Jia, He He, and Percy Liang. Delete, retrieve, generate: a simple approach to sentiment and style transfer. In NAACL-HLT. 2018. p. 1865–1874. [50] Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, Eric P. Xing. Toward controlled generation of text. In ICML. 2017. p. 1587–1596. [51] Ke Wang, Hang Hua, Xiaojun Wan, Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation, arXiv: 1905.12926v2, 2019. [52] Thomas Wolf, Victor Sanh, Julien Chaumond, Clement Delangue. TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents. NeurIPS 2018 CAI Workshop. 2018. [53] Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL2019. 2018. [54] Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, Jason Weston, 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 Association for Computational Linguistics. 2018b. vol. 1. p. 2204– 2213. [55] Richard S. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction. A Bradford Book, The MIT Press, Cambridge, Massachusetts, London, England. 2017. [56] John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, Oleg Klimov. Proximal Policy Optimization Algorithms. arXiv preprint arXiv:1707.06347v2. 2017. [57] Richard S Sutton, David A McAllester, Satinder P Singh, Yishay Mansour. Policy gradient methods for reinforcement learning with function approximation. Advances in neural information processing systems, 2000. p. 1057–1063. [58] J. A. Russell, A circumplex model of affect, Journal of Personality and Social Psychology. 1980. vol. 39, no. 6, p. 1161–1178. [59] Mollahosseini, A., Hasani, B., Mahoor, M.H., Affectnet: A database for facial expression, valence, and arousal computing in the wild. IEEE Transactions on Affective Computing. 2017. p. 1–1. [60] G. Paltoglou and M. Thelwall, Seeing stars of valence and arousal in blog posts, IEEE Transactions on Affective Computing. 2013. vol. 4, no. 1, pp. 116–123. [61] Jiun-Hao Jhan, Conversational and Empathetic Chatbot based on Reinforcement Learning, Master Thesis, National Taiwan University, 2020. Rogers K, Dziobek I, Hassenstab J, Wolf OT, Convit A, Who cares? Revisiting empathy in Asperger syndrome. J Autism Dev Disord. 2007. 37 (4): 709–15. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/60972 | - |
| dc.description.abstract | 近年來，由於人工智慧的發展，許多自動化的客戶服務系統逐漸多元化。人們逐漸將生活中所要完成的事務，仰賴於人機互動裝置系統，例如：聊天機器人。然而，當人們溝通時，總會思考對話者的處境以及心理狀態，提供較適當的回覆，使得人與人之間，能夠互相扶持及關懷。但是，現在的電腦系統，互動上卻無法給人們，如與真人交流的真實感受，因為目前的機器人尚未理解何謂同理心，導致機器給予人們的回應都限制於特定任務。本論文提出一能夠理解對話者情緒，並能流暢回應對方、符合談話主題、且具有同情心回應的文字聊天機器人系統。透過增強式學習算法，我們的系統能夠相當程度地模擬人們真實對話的過程，經由對話者的回應，學習如何選擇最適當的回覆。在文字情感辨識中，我們結合不同標籤域，包含離散情緒標籤以及連續性情緒關係，提升整體的辨識效果，並勝過許多目前情感辨識的架構。我們還使用多任務學習準則，結合情感資訊來建立對話系統，使我們的聊天機器人能夠根據對應情感，給予適當的回應。本研究是目前學界中，首先使用模擬人類學習的對話過程，來訓練聊天機器人的系統。透過實驗，我們的系統於定性 (Qualitative)和定量(Quantitative)的表現，都優於現有其他系統。 | zh_TW |
| dc.description.abstract | With the rapid development of technology, many automated customer service, and medical care are gradually increasing. More and more people start using computer interactive services to complete their daily tasks, e.g. chatbots. However, interaction experience between computers and humans is not as good as that between humans, since the empathy revealed between people is not experienced in Human-Machine Interaction (HMI). When people interacts with each other, they often try to imagine the situations of the other and give a more appropriate response so that the interlocutor can get more psychological assistance and feel more supportive by each other. In this paper, we propose a chatting system to care about others’ mental state and to be with the abilities to give fluent, coherent, and empathetic responses to users. By simulating real conversations, our system can obtain the feedback from the speakers, and determining the most appropriate way to respond through reinforcement learning. In addition, we incorporated labels of different domains, such as the discrete and the continuous emotional labels, to improve the overall performance of emotional classification with text data, outperforming several existing approaches on emotional classified benchmark dataset. Moreover, we also adopted multi-tasks learning guidance on conditional sentence generation from which we can generate a fluent and coherent responses as well as a specific emotional response. Through experiments, all our models perform better than the baseline model quantitatively. Besides, with several examples of responses generated by our system chatting with real people, we believe that our system can provide fluent, coherent, and empathetic responses in real life. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T10:39:13Z (GMT). No. of bitstreams: 1 U0001-0107202016171000.pdf: 4859950 bytes, checksum: 95d3ebe22122ad390ffc422fb47385c9 (MD5) Previous issue date: 2020 | en |
| dc.description.tableofcontents | 誌謝 i 中文摘要 ii Abstract iii Contents iv LIST OF FIGURES vii LIST OF TABLE ix Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Problem Statement 3 1.3 Literature Survey 4 1.3.1 Overview of Empathy 4 1.3.2 Emotion Data 5 1.3.3 Emotion Classification 6 1.3.4 Overview of Chatbot 8 1.3.5 Ruled-based Chatbot 9 1.3.6 Retrieval-based Chatbot 10 1.3.7 Generation-based Chatbot 12 1.3.8 Conditional Sentence Generation 14 1.3.9 Conditional Sentence Generation 15 1.4 Contributions 16 1.5 Chapter Outline 17 Chapter 2 Background Knowledge 18 2.1 Valence-Arousal Coordinate 18 2.2 Contextualized Embedding 19 2.2.1 Transformer 20 2.2.2 Bidirectional Encoded Representation from Transformers(BERT) 21 2.2.3 OpenAI Generative Pre-training(GPT) 23 2.3 Deep Reinforcement Learning 24 Chapter 3 System Design 26 3.1 Dataset 26 3.1.1 DailyDialog Dataset 26 3.1.2 EmpatheticDialogues Dataset 27 3.2 System Overview 29 3.3 Emotion Controller 30 3.3.1 Emotion Detector 30 3.3.2 Emotion Predictor 32 3.4 Dialogue Manager 33 3.4.1 Generation-based Chatbot 33 3.5 Fixed Chatbot Agent 35 3.6 Empathy Amplifier 36 Chapter 4 Experiment Setup 39 4.1 Experimental Models Setup 39 4.2 Objective Experiments 40 4.3 Human Ratings Setups 41 Chapter 5 Results and Discussion 42 5.1 Performance of Emotion Classification 42 5.2 Performance of Emotional Sentence Generation 43 5.3 Objective Evaluation Results 45 5.4 Deep Reinforcement Learning Results 47 5.5 Human Ratings Results 49 5.6 Example of Model Responses 51 Chapter 6 Conclusion 54 Reference 55 | |
| dc.language.iso | en | |
| dc.subject | 同理心 | zh_TW |
| dc.subject | 情感辨識 | zh_TW |
| dc.subject | 聊天機器人 | zh_TW |
| dc.subject | 自然語言處理 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 深度強化式學習 | zh_TW |
| dc.subject | Chatbot | en |
| dc.subject | Emotional Classification | en |
| dc.subject | Empathy | en |
| dc.subject | Deep Reinforcement Learning | en |
| dc.subject | Deep Learning | en |
| dc.subject | Natural Language Processing | en |
| dc.title | 基於深度強化式學習情感理解之富同情心的對話生成聊天機器人 | zh_TW |
| dc.title | Empathetic Generative-based Chatbot with Emotion Understanding via Reinforcement Learning | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 108-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 李琳山(Lin-Shan Lee),李宏毅(Hung-yi Lee),陳信希(Hsin-Hsi Chen) | |
| dc.subject.keyword | 同理心,情感辨識,聊天機器人,自然語言處理,深度學習,深度強化式學習, | zh_TW |
| dc.subject.keyword | Empathy,Emotional Classification,Chatbot,Natural Language Processing,Deep Learning,Deep Reinforcement Learning, | en |
| dc.relation.page | 59 | |
| dc.identifier.doi | 10.6342/NTU202001246 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2020-07-03 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-0107202016171000.pdf 未授權公開取用 | 4.75 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。