在對話生成中，高自然度的回應對有效的人機互動至關重要，這些回應能顯著提升使用者對於對話系統的互動體驗。在進行個人化對話生成時，要達成此目標更加的困難，因為回應需要既流暢且連貫，又要與使用者的個人特質或角色描述保持一致。在本研究中我們提出了一種名為 MUDI（Multiple Disourse Relations Graph Learning）的新方法，旨在有效建模與整合個人化對話生成中對話上下文的語篇關係與角色資訊。首先，為了讓模型學習對話中的語篇連貫關係，我們透過大型語言模型協助標註對話資料中的語篇關係， 並受到先前研究的啟發，我們將對話資料轉為對話圖的形式，接著透過提出的對話增強圖神經網路 DialogueGAT，作為編碼器來捕捉對話結構內隱含的語篇連貫關係。 另外我們將角色描述也透過圖編碼器轉變為全連接的角色圖形式，以捕捉角色句子間的語意關係。最後我們藉由基於注意力機制的特徵融合方式將來自對話圖與角色圖的資訊進行融合，以產生個人化的語篇增強對話表示。此外我們同時透過文字編碼器在語意與段落層面捕捉對話上下文與角色描述的隱含關係。而在生成個人化回應的階段，我們首先採用基於提示的條件對話生成機制，通過精心設計的提示來引導生成個性化回應的過程，以及引入了連貫性增強的注意力機制，結合可學習嵌入 和文字表示以增強解碼器在預測下一個詞語時考量語篇關係的能力，使其在生成文字的過程中能多加考慮那些隱含連貫性資訊的詞彙。實驗結果與實際案例探討表明，我們提出的方法 MUDI 顯著改善了個人化對話生成的回應品質，有效整合語篇關係與角色資訊，使生成回應更加連貫與遵循角色設定，並且更加自然，能產生更像人類的對話回應。

In dialogue generation, the naturalness of responses is key for effective human-machine interaction, significantly enhancing user experience. Personalized dialogue generation poses even greater challenges, as the responses must be coherent and consistent with the user's personal traits or persona descriptions. In this study, we propose a novel method named MUDI (Multiple Discourse Relations Graph Learning) aimed at effectively modeling and integrating discourse relations and persona information within the context of personalized dialogue generation. We initially utilize Large Language Models to assist in annotating discourse relations and to transform dialogue data into structured dialogue graphs. We employ our newly proposed DialogueGAT as the graph encoder, which captures implicit discourse relations within this structure. Persona descriptions are also encoded into fully-connected persona graphs, facilitating the capture of semantic relationships between persona elements. An Attention-Based Feature Fusion method integrates data from both graphs, creating a personalized, coherence-aware dialogue representation. In the personalized response generation phase, a Prompt-based mechanism and a Coherence-Aware Attention strategy are implemented to enhance the decoder's consideration of discourse relations. Our experiments and case studies demonstrate significant improvements in the quality of personalized responses, making them more coherent, aligned with persona, and natural, thus resembling human-like dialogue exchanges.

[1] Rajeev Agarwal. Towards a PURE spoken dialogue system for information access. In Interactive Spoken Dialog Systems: Bringing Speech and NLP Together in Real Applications, pages 90–97, 1997.
[2] AI@Meta. Llama 3 model card. 2024.
[3] Rami Al-Rfou, Marc Pickett, Javier Snaider, Yun-Hsuan Sung, Brian Strope, and Ray Kurzweil. Conversational contextual cues: The case of personalization and history for response ranking. arXiv preprint arXiv:1606.00372, 2016.
[4] Nicholas Asher, Julie Hunter, Mathieu Morey, Benamara Farah, and Stergos Afan- tenos. Discourse structure and dialogue acts in multiparty dialogue: the STAC corpus. In Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Sara Goggi, Marko Grobel- nik, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, and Stelios Piperidis, editors, Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2721–2727, Portorož, Slovenia, May 2016. European Language Resources Association (ELRA).
[5] Harald Aust and Martin Oerder. Dialogue control in automatic inquiry systems. In Proc. ESCA Workshop on Spoken Dialogue Systems, pages 121–124, 1995.
[6] Siqi Bao, Huang He, Fan Wang, Hua Wu, and Haifeng Wang. PLATO: Pre-trained dialogue generation model with discrete latent variable. In Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel Tetreault, editors, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 85–96, Online, July 2020. Asso- ciation for Computational Linguistics.
[7] Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhen Guo, Zhibin Liu, and Xinchao Xu. PLATO-2: Towards building an open-domain chatbot via curriculum learning. In Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli, editors, Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2513–2525, Online, August 2021. Association for Computational Linguistics.
[8] Regina Barzilay and Mirella Lapata. Modeling local coherence: An entity-based approach. In Kevin Knight, Hwee Tou Ng, and Kemal Oflazer, editors, Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05), pages 141–148, Ann Arbor, Michigan, June 2005. Association for Computational Linguistics.
[9] Regina Barzilay and Lillian Lee. Catching the drift: Probabilistic content models, with applications to generation and summarization. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Compu- tational Linguistics: HLT-NAACL 2004, pages 113–120, Boston, Massachusetts, USA, May 2 - May 7 2004. Association for Computational Linguistics.
[10] Shaked Brody, Uri Alon, and Eran Yahav. How attentive are graph attention networks? In International Conference on Learning Representations, 2022.
[11] Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. Language models are few-shot learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS' 20, Red Hook, NY, USA, 2020. Curran Associates Inc.
[12] Shuyang Cao and Lu Wang. HIBRIDS: Attention with Hierarchical Biases for Structure-aware Long Document Summarization. In Smaranda Muresan, Preslav Nakov, and Aline Villavicencio, editors, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 786–807, Dublin, Ireland, May 2022. Association for Computational Linguistics.
[13] Maximillian Chen, Xiao Yu, Weiyan Shi, Urvi Awasthi, and Zhou Yu. Controllable mixed-initiative dialogue generation through prompting. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 951–966, Toronto, Canada, July 2023. Association for Computational Linguistics.
[14] Ruijun Chen, Jin Wang, Liang-Chih Yu, and Xuejie Zhang. Learning to memorize entailment and discourse relations for persona-consistent dialogues. In Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence, AAAI'23/IAAI'23/EAAI'23. AAAI Press, 2023.
[15] Arman Cohan, Franck Dernoncourt, DooSoonKim, Trung Bui, Seokhwan Kim, Walter Chang, and Nazli Goharian. A discourse-aware attention model for abstractive summarization of long documents. In Marilyn Walker, Heng Ji, and Amanda Stent, editors, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 615–621, New Orleans, Louisiana, June 2018. Association for Computational Linguistics.
[16] Y. Cui, M. Jia, T. Lin, Y. Song, and S. Belongie. Class-balanced loss based on effective number of samples. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9260–9269, Los Alamitos, CA, USA, jun 2019. IEEE Computer Society.
[17] Denecke and Matthias. Rapid prototyping for spoken dialogue systems. In COLING 2002: The 19th International Conference on Computational Linguistics, 2002.
[18] Ameet Deshpande, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, and Karthik Narasimhan. Toxicity in chatgpt: Analyzing persona-assigned language models. In Houda Bouamor, Juan Pino, and Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1236–1270, Singapore, December 2023. Association for Computational Linguistics.
[19] Emily Dinan, Varvara Logacheva, Valentin Malykh, Alexander Miller, Kurt Shuster, Jack Urbanek, Douwe Kiela, Arthur Szlam, Iulian Serban, Ryan Lowe, Shrimai Prab- humoye, Alan W. Black, Alexander Rudnicky, Jason Williams, Joelle Pineau, Mikhail Burtsev, and Jason Weston. The second conversational intelligence challenge (con- vai2). In Sergio Escalera and Ralf Herbrich, editors, The NeurIPS’18 Competition, pages 187–208, Cham, 2020. Springer International Publishing.
[20] Yue Dong, Andrei Mircea, and Jackie Chi Kit Cheung. Discourse-aware unsupervised summarization for long scientific documents. In Paola Merlo, Jorg Tiedemann, and Reut Tsarfaty, editors, Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1089–1102, Online, April 2021. Association for Computational Linguistics.
[21] Nouha Dziri, Ehsan Kamalloo, Kory Mathewson, and Osmar Zaiane. Augmenting neural response generation with context-aware topical attention. In Yun-Nung Chen, Tania Bedrax-Weiss, Dilek Hakkani-Tur, Anuj Kumar, Mike Lewis, Thang-Minh Luong, Pei- Hao Su, and Tsung-Hsien Wen, editors, Proceedings of the First Workshop on NLP for Conversational AI, pages 18–31, Florence, Italy, August 2019. Association for Computational Linguistics.
[22] Xiachong Feng, Xiaocheng Feng, and Xinwei Geng. Dialogue discourse-aware graph model and data augmentation for meeting summarization. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21), pages 3808– 3814, 08 2021.
[23] Sarik Ghazarian, Nuan Wen, Aram Galstyan, and Nanyun Peng. DEAM: Dialogue coherence evaluation using AMR-based semantic manipulations. In Smaranda Muresan, Preslav Nakov, and Aline Villavicencio, editors, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 771–785, Dublin, Ireland, May 2022. Association for Computational Linguistics.
[24] Deepanway Ghosal, Navonil Majumder, Soujanya Poria, NiyatiChhaya, and Alexander Gelbukh. DialogueGCN: A graph convolutional neural network for emotion recognition in conversation. In Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan, editors, 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 154–164, Hong Kong, China, November 2019. Association for Computational Linguistics.
[25] Milan Gritta, Gerasimos Lampouras, and Ignacio Iacobacci. Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management. Transactions of the Association for Computational Linguistics, 9:36–52, 02 2021.
[26] Jerry R. Hobbs. Coherence and coreference. Cognitive Science, 3(1):67–90, 1979.
[27] Jerry R. Hobbs. On the coherence and structure of discourse. 1985.
[28] Qiushi Huang, Yu Zhang, Tom Ko, Xubo Liu, Bo Wu, Wenwu Wang, and H Tang. Personalized dialogue generation with persona-adaptive attention. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 12916–12923, 2023.
[29] Yoonna Jang, Jungwoo Lim, Yuna Hur, Dongsuk Oh, Suhyune Son, Yeonsoo Lee, Donghoon Shin, Seungryong Kim, and Heuiseok Lim. Call for customized conversation: Customized conversation grounding persona and knowledge. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 10803–10812, 2022.
[30] Shaojie Jiang and Maarten de Rijke. Why are sequence-to-sequence models so dull? understanding the low-diversity problem of chatbots. In Aleksandr Chuklin, Jeff Dal- ton, Julia Kiseleva, Alexey Borisov, and Mikhail Burtsev, editors, Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI, pages 81–86, Brussels, Belgium, October 2018. Association for Computational Linguistics.
[31] Thomas N Kipf and Max Welling. Variational graph auto-encoders. NIPS Workshop on Bayesian Deep Learning, 2016.
[32] Jing Yang Lee, Kong Aik LEE, and W. S. Gan. Dlvgen: A dual latent variable approach to personalized dialogue generation. In International Conference on Agents and Artificial Intelligence, 2021.
[33] Brian Lester, Rami Al-Rfou, and Noah Constant. The power of scale for parameter- efficient prompt tuning. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih, editors, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3045–3059, Online and Punta Cana, Dominican Republic, November 2021. Association for Computational Linguistics.
[34] Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mo- hamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel Tetreault, editors, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7871–7880, Online, July 2020. Association for Computational Linguistics.
[35] Jiaqi Li, Ming Liu, Zihao Zheng, Heng Zhang, Bing Qin, Min-Yen Kan, and Ting Liu. Dadgraph: A discourse-aware dialogue graph neural network for multiparty dialogue machine reading comprehension. 2021 International Joint Conference on Neural Net- works (IJCNN), pages 1–8, 2021.
[36] Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. A diversity- promoting objective function for neural conversation models. In Kevin Knight, Ani Nenkova, and Owen Rambow, editors, Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 110–119, San Diego, California, June 2016. Association for Computational Linguistics.
[37] Jiwei Li, Michel Galley, Chris Brockett, Georgios Spithourakis, Jianfeng Gao, and Bill Dolan. A persona-based neural conversation model. In Katrin Erk and Noah A. Smith, editors, Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 994–1003, Berlin, Germany, August 2016. Association for Computational Linguistics.
[38] Jiwei Li and Eduard Hovy. A model of coherence based on distributed sentence representation. In Alessandro Moschitti, Bo Pang, and Walter Daelemans, editors, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2039–2048, Doha, Qatar, October 2014. Association for Computational Linguistics.
[39] Lei Li, Yongfeng Zhang, and Li Chen. Generate Neural Template Explanations for Recommendation. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, CIKM ’20, page 755–764, New York, NY, USA, 2020. Association for Computing Machinery.
[40] Chin-Yew Lin. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain, July 2004. Association for Computational Linguistics.
[41] Pingsheng Liu, Zhengjie Huang,XiechiZhang,LinlinWang,GerarddeMelo,XinLin, Liang Pang, and Liang He. A disentangled-attention based framework with persona- aware prompt learning for dialogue generation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(11):13255–13263, Jun. 2023.
[42] Qian Liu, Yihong Chen, Bei Chen, Jian-Guang Lou, Zixuan Chen, Bin Zhou, and Dongmei Zhang. You impress me: Dialogue generation via mutual persona perception. In Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel Tetreault, editors, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1417–1427, Online, July 2020. Association for Computational Linguistics.
[43] Zhenyi Lu, Wei Wei, Xiaoye Qu, Xian-Ling Mao, Dangyang Chen, and Jixiong Chen. Miracle: Towards personalized dialogue generation with latent-space multiple personal attribute control. In Houda Bouamor, Juan Pino, and Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5933–5957, Singapore, December 2023. Association for Computational Linguistics.
[44] Andrea Madotto, Zhaojiang Lin, Chien-Sheng Wu, and Pascale Fung. Personalizing dialogue agents via meta-learning. In Anna Korhonen, David Traum, and Lluís Màrquez, editors, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5454–5459, Florence, Italy, July 2019. Association for Computational Linguistics.
[45] Daniel Marcu. From discourse structures to text summaries. In Intelligent Scalable Text Summarization, 1997.
[46] Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. Bleu: a method for automatic evaluation of machine translation. In Pierre Isabelle, Eugene Charniak, and Dekang Lin, editors, Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA, July 2002. Association for Computational Linguistics.
[47] Ramakanth Pasunuru, Celikyilmaz Asli, Michel Galley, Chenyan Xiong, Yizhe Zhang, Mohit Bansal, and Jianfeng Gao. Data augmentation for abstractive query-focused multi-document summarization. Proceedings of the AAAI Conference on Artificial Intelligence, 35:13666–13674, 05 2021.
[48] Nils Reimers and Iryna Gurevych. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 11 2019.
[49] Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. The graph neural network model. IEEE Transactions on Neural Networks, 20(1):61–80, 2009.
[50] Egbert Schlungbaum and Thomas Elwert. Dialogue graphs - a formal and visual specification technique for dialogue modelling. In Proceedings of the BCS-FACS Workshop on Formal Aspects of the Human Computer Interface (FAC), 1996.
[51] Iulian Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron Courville, and Yoshua Bengio. A hierarchical latent variable encoder-decoder model for generating dialogues. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1), Feb. 2017.
[52] Xiaoyu Shen, Hui Su, Yanran Li, Wenjie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa, and Guoping Long. A conditional variational framework for dialog generation. In Regina Barzilay and Min-Yen Kan, editors, Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 504–509, Vancouver, Canada, July 2017. Association for Computational Linguistics.
[53] Haoyu Song, Yan Wang, Kaiyan Zhang, Wei-Nan Zhang, and Ting Liu. BoB: BERT over BERT for training persona-based dialogue models from limited personalized data. In Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli, editors, 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 Pa- pers), pages 167–177, Online, August 2021. Association for Computational Linguistics.
[54] Haoyu Song, Wei-Nan Zhang, Yiming Cui, Dong Wang, and Ting Liu. Exploiting persona information for diverse generation of conversational responses. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pages 5190–5196. International Joint Conferences on Artificial Intelligence Organization, 7 2019.
[55] Haoyu Song, Wei-Nan Zhang, Jingwen Hu, and Ting Liu. Generating persona consistent dialogues by exploiting natural language inference. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):8878–8885, Apr. 2020.
[56] Yihong Tang, Bo Wang, Miao Fang, Dongming Zhao, Kun Huang, Ruifang He, and Yuexian Hou. Enhancing personalized dialogue generation with contrastive latent variables: Combining sparse and dense persona. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5456–5468, Toronto, Canada, July 2023. Association for Computational Linguistics.
[57] Pontus Wärnestål. Modeling a dialogue strategy for personalized movie recommendations. 2005.
[58] Martin John Warren. Features of naturalness in conversation. 2006.
[59] Adina Williams, Nikita Nangia, and Samuel Bowman. A broad-coverage challenge corpus for sentence understanding through inference. In Marilyn Walker, Heng Ji, and Amanda Stent, editors, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1112–1122, New Orleans, Louisiana, June 2018. Association for Computational Linguistics.
[60] Thomas Wolf, Victor Sanh, Julien Chaumond, and Clement Delangue. Transfertransfo: A transfer learning approach for neural network based conversational agents. arXiv preprint arXiv:1901.08149, 2019.
[61] Lirong Wu, Haitao Lin, Cheng Tan, Zhangyang Gao, and Stan Z. Li. Self-supervised learning on graphs: Contrastive, generative, or predictive. IEEE Trans. on Knowl. and Data Eng., 35(4):4216–4235, apr 2023.
[62] Jun Xu, Zeyang Lei, Haifeng Wang, Zheng-Yu Niu, Hua Wu, and Wanxiang Che. Enhancing dialog coherence with event graph grounded content planning. In Christian Bessiere, editor, Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, pages 3941–3947. International Joint Conferences on Artificial Intelligence Organization, 7 2020. Main track.
[63] Yan Yan, Bo-Wen Zhang, Peng-hao Min, Guan-wen Ding, and Jun-yuan Liu. Dialgnn: Heterogeneous graph neural networks for dialogue classification. Neural Processing Letters, 56(2):143, Apr 2024.
[64] Zheng Ye, Liucun Lu, Lishan Huang, Liang Lin, and Xiaodan Liang. Towards quantifiable dialogue coherence evaluation. In Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli, editors, 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 2718–2729, Online, August 2021. Association for Computational Linguistics.
[65] Weizhe Yuan, Graham Neubig, and Pengfei Liu. Bartscore: Evaluating generated text as text generation. In M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wort- man Vaughan, editors, Advances in Neural Information Processing Systems, volume 34, pages 27263–27277. Curran Associates, Inc., 2021.
[66] Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. Personalizing dialogue agents: I have a dog, do you have pets too? In Iryna Gurevych and Yusuke Miyao, editors, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2204–2213, Melbourne, Australia, July 2018. Association for Computational Linguistics.
[67] Tianyi Zhang*, Varsha Kishore*, Felix Wu*, Kilian Q. Weinberger, and Yoav Artzi. Bertscore: Evaluating text generation with bert. In International Conference on Learn- ing Representations, 2020.
[68] Yizhe Zhang, Michel Galley, Jianfeng Gao, Zhe Gan, Xiujun Li, Chris Brockett, and Bill Dolan. Generating informative and diverse conversational responses via adversarial information maximization. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc., 2018.
[69] Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and Bill Dolan. Dialogpt: Large-scale generative pre- training for conversational response generation. In ACL, system demonstration, 2020.
[70] Tiancheng Zhao, Ran Zhao, and Maxine Eskenazi. Learning discourse-level diversity for neural dialog models using conditional variational autoencoders. In Regina Barzilay and Min-Yen Kan, editors, Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 654–664, Vancouver, Canada, July 2017. Association for Computational Linguistics.
[71] Junkai Zhou, Liang Pang, Huawei Shen, and Xueqi Cheng. SimOAP: Improve coherence and consistency in persona-based dialogue generation via over-sampling and post-evaluation. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9945–9959, Toronto, Canada, July 2023. Association for Computational Linguistics.