本篇論文著重在移情對話生成任務上。先前研究關於移情對話生成的方法 [1,2]主要集中在檢測和利用用戶的情緒來產生移情反應。本研究將使用額外的常識知識圖譜做為機器人對常識性的背景知識。我們針對非預訓練和預訓練模型各使用不同的方式增強多樣性，在非預訓練模型上我們將 AdaLabel[3] 應用在 CEM 模型[4]上，而對於預訓練模型使用 BART 模型結合多種常識知識讓模型能生成更有資訊的移情回應。研究結果顯示所提出的兩個模型在EMPATHETICDIALOGUES 和 DailyDialog 資料集上都優於基線模型，並且在個案研究中可以看到模型產生更多信息和同理心的回應。

To improve students’ expression and language ability in education, listening and reading English short stories can be used to allow students to extend from talking about the content of the stories to their personal experiences and feelings in daily life, but this process requires a lot of teacher and time, so We plan to build a Story Chatbot, in addition to story-related Q&A, can also respond with empathy to daily conversation. Previous approaches on empathetic response generation have mainly focused on detecting and exploiting users emotions to generate empathetic responses. In this study, the additional commonsense knowledge graph is used as the background knowledge of commonsense for robots, and in order to be practically applied in schools, it is necessary to improve the generation diversity of the model. We use different ways to enhance diversity for non-pre-trained and pre-trained models. For non-pre-trained models, we apply AdaLabel [3] to CEM model [4], and for pretrained models, we use the BART model combined with a variety of common sense knowledge to allow the model to generate more Informative empathetic responses. The results show that the two proposed models outperform the baseline models on both the EMPATHETICDIALOGUES and DailyDialog datasets, and in the case study model can be seen to generate more informative and empathetic responses.

[1] Navonil Majumder, Pengfei Hong, Shanshan Peng, Jiankun Lu, Deepanway Ghosal, Alexander Gelbukh, Rada Mihalcea, and Soujanya Poria. Mime: Mimicking emotions for empathetic response generation. In EMNLP, pages 8968–8979, 01 2020.

[2] Zhaojiang Lin, Andrea Madotto, Jamin Shin, Peng Xu, and Pascale Fung. MoEL: Mixture of empathetic listeners. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 121–132, Hong Kong, China, November 2019. Association for Computational Linguistics.

[3] Yida Wang, Yinhe Zheng, Yong Jiang, and Minlie Huang. Diversifying dialog generation via adaptive label smoothing. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, 2021.

[4] Sahand Sabour, Chujie Zheng, and Minlie Huang. Cem: Commonsense-awareempathetic response generation. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10):11229–11237, Jun. 2022.

[5] Zheng Zhang, Ying Xu, Yanhao Wang, Bingsheng Yao, Daniel Ritchie, Tongshuang Wu, Mo Yu, Dakuo Wang, and Toby Jia-Jun Li. Storybuddy: A humanai collaborative chatbot for parent-child interactive storytelling with flexible parental involvement. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, CHI ’22, New York, NY, USA, 2022. Association for Computing Machinery.

[6] H. Liu and P. Singh. Conceptnet — a practical commonsense reasoning tool-kit. BT Technology Journal, 22(4):211–226, 2004.

[7] Maarten Sap, Ronan Le Bras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith, and Yejin Choi. ATOMIC: an atlas of machine commonsense for if-then reasoning. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019,
pages 3027–3035. AAAI Press, 2019.

[8] Qintong Li, Piji Li, Zhaochun Ren, Pengjie Ren, and Zhumin Chen. Knowledge bridging for empathetic dialogue generation. AAAI, 2022.

[9] Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. BART: Denoising sequence-to-sequence pre-training for natural language generation,
translation, and comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7871–7880, Online, July 2020. Association for Computational Linguistics.

[10] Chen-Chung Liu, Mo-Gang Liao, Chia-Hui Chang, and Hung-Ming Lin. An analysis of children interaction with an ai chatbot and its impact on their interest in reading. Computers & Education, 189:104576, 2022.

[11] Hongshen Chen, Xiaorui Liu, Dawei Yin, and Jiliang Tang. A survey on dialogue systems: Recent advances and new frontiers. SIGKDD Explor. Newsl., 19(2):2535, nov 2017.

[12] Chongyang Tao, Jiazhan Feng, Rui Yan, Wei Wu, and Daxin Jiang. A survey on response selection for retrieval-based dialogues. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI, volume 21, pages 4619–4626, 2021.

[13] Chinnadhurai Sankar, Sandeep Subramanian, Christopher Joseph Pal, A. P. Sarath Chandar, and Yoshua Bengio. Do neural dialog systems use the conversation history effectively? an empirical study. In ACL, 2019.

[14] Kleopatra Mageira, Dimitra Pittou, Andreas Papasalouros, Konstantinos Kotis, Paraskevi Zangogianni, and Athanasios Daradoumis. Educational ai chatbots for content and language integrated learning. Applied Sciences, 12(7), 2022.

[15] Robyn Speer, Joshua Chin, and Catherine Havasi. Conceptnet 5.5: An open multilingual graph of general knowledge. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI’17, page 44444451. AAAI Press, 2017.

[16] Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, and Yejin Choi. COMET: Commonsense transformers for automatic knowledge graph construction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4762–4779, Florence, Italy, July 2019. Association for Computational Linguistics.

[17] Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever, et al. Improving language understanding by generative pre-training. OpenAI, 2018.

[18] Bodhisattwa Prasad Majumder, Harsh Jhamtani, Taylor Berg-Kirkpatrick, and Julian McAuley. Like hiking? you probably enjoy nature: Persona-grounded dialog with commonsense expansions. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9194–9206, Online, November 2020. Association for Computational Linguistics.

[19] Deepanway Ghosal, Navonil Majumder, Alexander Gelbukh, Rada Mihalcea, and Soujanya Poria. COSMIC: COmmonSense knowledge for eMotion identification in conversations. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2470–2481, Online, November 2020. Association for Computational Linguistics.

[20] Lixing Zhu, Gabriele Pergola, Lin Gui, Deyu Zhou, and Yulan He. Topicdriven and knowledge-aware transformer for dialogue emotion detection. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1571–1582, Online, August 2021. Association for Computational Linguistics.

[21] Iulian V. Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, and Joelle Pineau. Building end-to-end dialogue systems using generative hierarchical neural network models. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, AAAI’16, page 37763783. AAAI Press, 2016.

[22] Hao Zhou, Tom Young, Minlie Huang, Haizhou Zhao, Jingfang Xu, and Xiaoyan Zhu. Commonsense knowledge aware conversation generation with graph attention. In IJCAI, pages 4623–4629, 2018.

[23] Houyu Zhang, Zhenghao Liu, Chenyan Xiong, and Zhiyuan Liu. Grounded conversation generation as guided traverses in commonsense knowledge graphs. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2031–2043, Online, July 2020. Association for Computational Linguistics.

[24] Sixing Wu, Ying Li, Dawei Zhang, Yang Zhou, and Zhonghai Wu. Topicka: Generating commonsense knowledge-aware dialogue responses towards the recommended topic fact. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pages 3766–3772, 2021.

[25] Ke Wang and Xiaojun Wan. Sentigan: Generating sentimental texts via mixture adversarial networks. In IJCAI, pages 4446–4452, 2018.

[26] Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, and Bing Liu. Emotional chatting machine: Emotional conversation generation with internal and external memory. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32, 2018.

[27] Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y-Lan Boureau. Towards empathetic open-domain conversation models: a new benchmark and dataset. In ACL, 2019.

[28] Pengfei Li, Peixiang Zhong, Kezhi Mao, Dongzhe Wang, Xuefeng Yang, Yunfeng Liu, Jianxiong Yin, and Simon See. ACT: an attentive convolutional transformer for efficient text classification. In Thirty-Fifth AAAI Conference
on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pages 13261–13269. AAAI Press, 2021.

[29] Antoine Bordes, Nicolas Usunier, Alberto Garcia-Durán, Jason Weston, and Oksana Yakhnenko. Translating embeddings for modeling multi-relational data. In Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2, NIPS’13, page 27872795, Red Hook, NY, USA, 2013. Curran Associates Inc.

[30] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017.

[31] Saif Mohammad. Obtaining reliable human ratings of valence, arousal, and dominance for 20,000 English words. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 174–184, Melbourne, Australia, July 2018. Association for Computational Linguistics.

[32] Ye Liu, Wolfgang Maier, Wolfgang Minker, and Stefan Ultes. Empathetic dialogue generation with pre-trained roberta-gpt2 and external knowledge. arXiv preprint arXiv:2109.03004, 2021.

[33] Maarten Grootendorst. Keybert: Minimal keyword extraction with bert. 2020. URL: https://github. com/MaartenGr/KeyBERT, 2020.