@article{ni2023recent,
  title={Recent advances in deep learning based dialogue systems: A systematic survey},
  author={Ni, Jinjie and Young, Tom and Pandelea, Vlad and Xue, Fuzhao and Cambria, Erik},
  journal={Artificial intelligence review},
  volume={56},
  number={4},
  pages={3055--3155},
  year={2023},
  publisher={Springer}
}

@article{zhang2020recent,
  title={Recent advances and challenges in task-oriented dialog systems},
  author={Zhang, Zheng and Takanobu, Ryuichi and Zhu, Qi and Huang, MinLie and Zhu, XiaoYan},
  journal={Science China Technological Sciences},
  volume={63},
  number={10},
  pages={2011--2027},
  year={2020},
  publisher={Springer}
}

@inproceedings{dai2020learning,
  title={Learning low-resource end-to-end goal-oriented dialog for fast and reliable system deployment},
  author={Dai, Yinpei and Li, Hangyu and Tang, Chengguang and Li, Yongbin and Sun, Jian and Zhu, Xiaodan},
  booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
  pages={609--618},
  year={2020}
}

@article{saha2021hierarchical,
  title={A hierarchical approach for efficient multi-intent dialogue policy learning},
  author={Saha, Tulika and Gupta, Dhawal and Saha, Sriparna and Bhattacharyya, Pushpak},
  journal={Multimedia Tools and Applications},
  volume={80},
  pages={35025--35050},
  year={2021},
  publisher={Springer}
}

@article{li2020guided,
  title={Guided dialog policy learning without adversarial learning in the loop},
  author={Li, Ziming and Lee, Sungjin and Peng, Baolin and Li, Jinchao and Kiseleva, Julia and de Rijke, Maarten and Shayandeh, Shahin and Gao, Jianfeng},
  journal={arXiv preprint arXiv:2004.03267},
  year={2020}
}

@inproceedings{song2021emotional,
  title={An emotional comfort framework for improving user satisfaction in E-commerce customer service chatbots},
  author={Song, Shuangyong and Wang, Chao and Chen, Haiqing and Chen, Huan},
  booktitle={Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers},
  pages={130--137},
  year={2021}
}

@article{seo2019rewards,
  title={Rewards prediction-based credit assignment for reinforcement learning with sparse binary rewards},
  author={Seo, Minah and Vecchietti, Luiz Felipe and Lee, Sangkeum and Har, Dongsoo},
  journal={IEEE Access},
  volume={7},
  pages={118776--118791},
  year={2019},
  publisher={IEEE}
}

@article{zhong2020towards,
  title={Towards persona-based empathetic conversational models},
  author={Zhong, Peixiang and Zhang, Chen and Wang, Hao and Liu, Yong and Miao, Chunyan},
  journal={arXiv preprint arXiv:2004.12316},
  year={2020}
}

@article{ma2020survey,
  title={A survey on empathetic dialogue systems},
  author={Ma, Yukun and Nguyen, Khanh Linh and Xing, Frank Z and Cambria, Erik},
  journal={Information Fusion},
  volume={64},
  pages={50--70},
  year={2020},
  publisher={Elsevier}
}

@article{xie2021empathetic,
  title={Empathetic dialog generation with fine-grained intents},
  author={Xie, Yubo and Pu, Pearl},
  journal={arXiv preprint arXiv:2105.06829},
  year={2021}
}

@inproceedings{saha2022emotion,
  title={Emotion-aware and intent-controlled empathetic response generation using hierarchical transformer network},
  author={Saha, Tulika and Ananiadou, Sophia},
  booktitle={2022 International Joint Conference on Neural Networks (IJCNN)},
  pages={1--8},
  year={2022},
  organization={IEEE}
}

@inproceedings{bui2006toward,
  title={Toward affective dialogue modeling using partially observable Markov decision processes},
  author={Bui, Trung H and Zwiers, Job and Poel, Mannes and Nijholt, Anton},
  booktitle={Proceedings of workshop emotion and computing, 29th annual German conference on artificial intelligence},
  pages={47--50},
  year={2006}
}

@article{bui2007pomdp,
  title={A pomdp approach to affective dialogue modeling},
  author={Bui, Trung H and Poel, Mannes and Nijholt, Anton and Zwiers, Job},
  journal={NATO SECURITY THROUGH SCIENCE SERIES E HUMAN AND SOCIETAL DYNAMICS},
  volume={18},
  pages={349},
  year={2007},
  publisher={IOS PRESS}
}

@article{bui2010affective,
  title={Affective Dialogue Management Using Factored POMDPs.},
  author={Bui, Trung H and Zwiers, Job and Poel, Mannes and Nijholt, Anton},
  journal={Interactive Collaborative Information Systems},
  volume={281},
  pages={209--238},
  year={2010}
}

@article{shi2018sentiment,
  title={Sentiment adaptive end-to-end dialog systems},
  author={Shi, Weiyan and Yu, Zhou},
  journal={arXiv preprint arXiv:1804.10731},
  year={2018}
}

@inproceedings{shin2020generating,
  title={Generating empathetic responses by looking ahead the user’s sentiment},
  author={Shin, Jamin and Xu, Peng and Madotto, Andrea and Fung, Pascale},
  booktitle={ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={7989--7993},
  year={2020},
  organization={IEEE}
}

@article{gao2016multi,
  title={Multi-channel human-computer dialogue system for natural interaction},
  author={Gao, Yanli and Tao, Jianhua and Yang, Minghao and Zhang, Dawei and Chao, linlin and Li, Hao and Che, Hao and Li, Ya and Liu, Bin},
  journal={Computer Science},
  volume={26},
  number={S2},
  pages={177--188},
  year={2016}
}

@article{ren2016novel,
  title={A novel factored POMDP model for affective dialogue management},
  author={Ren, Fuji and Wang, Yu and Quan, Changqin},
  journal={Journal of Intelligent \& Fuzzy Systems},
  volume={31},
  number={1},
  pages={127--136},
  year={2016},
  publisher={IOS Press}
}

@article{wang2018new,
  title={A new factored POMDP model framework for affective tutoring systems},
  author={Wang, Yu and Ren, Fuji and Quan, Changqin},
  journal={IEEJ Transactions on Electrical and Electronic Engineering},
  volume={13},
  number={11},
  pages={1603--1611},
  year={2018},
  publisher={Wiley Online Library}
}

@article{ren2015tfsm,
  title={TFSM-based dialogue management model framework for affective dialogue systems},
  author={Ren, Fuji and Wang, Yu and Quan, Changqin},
  journal={IEEJ Transactions on Electrical and Electronic Engineering},
  volume={10},
  number={4},
  pages={404--410},
  year={2015},
  publisher={Wiley Online Library}
}

@article{song2020sentiment,
  title={Sentiment analysis for intelligent customer service chatbots},
  author={Song, Y and Wang, C and Chen, C and Zhou, W and Chen, H},
  journal={Journal of Chinese Information Processing},
  volume={34},
  number={02},
  pages={80--95},
  year={2020}
}

@article{li2017end,
  title={End-to-end task-completion neural dialogue systems},
  author={Li, Xiujun and Chen, Yun-Nung and Li, Lihong and Gao, Jianfeng and Celikyilmaz, Asli},
  journal={arXiv preprint arXiv:1703.01008},
  year={2017}
}

@article{feng2021emowoz,
  title={EmoWOZ: A large-scale corpus and labelling scheme for emotion recognition in task-oriented dialogue systems},
  author={Feng, Shutong and Lubis, Nurul and Geishauser, Christian and Lin, Hsien-chin and Heck, Michael and van Niekerk, Carel and Ga{\v{s}}i{\'c}, Milica},
  journal={arXiv preprint arXiv:2109.04919},
  year={2021}
}

@inproceedings{wang2016dueling,
  title={Dueling network architectures for deep reinforcement learning},
  author={Wang, Ziyu and Schaul, Tom and Hessel, Matteo and Hasselt, Hado and Lanctot, Marc and Freitas, Nando},
  booktitle={International conference on machine learning},
  pages={1995--2003},
  year={2016},
  organization={PMLR}
}

@article{williams2016end,
  title={End-to-end lstm-based dialog control optimized with supervised and reinforcement learning},
  author={Williams, Jason D and Zweig, Geoffrey},
  journal={arXiv preprint arXiv:1606.01269},
  year={2016}
}

@inproceedings{lipton2018bbq,
  title={Bbq-networks: Efficient exploration in deep reinforcement learning for task-oriented dialogue systems},
  author={Lipton, Zachary and Li, Xiujun and Gao, Jianfeng and Li, Lihong and Ahmed, Faisal and Deng, Li},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={32},
  number={1},
  year={2018}
}

@article{budzianowski2018multiwoz,
  title={MultiWOZ--a large-scale multi-domain wizard-of-oz dataset for task-oriented dialogue modelling},
  author={Budzianowski, Pawe{\l} and Wen, Tsung-Hsien and Tseng, Bo-Hsiang and Casanueva, Inigo and Ultes, Stefan and Ramadan, Osman and Ga{\v{s}}i{\'c}, Milica},
  journal={arXiv preprint arXiv:1810.00278},
  year={2018}
}

@article{papangelis2019collaborative,
  title={Collaborative multi-agent dialogue model training via reinforcement learning},
  author={Papangelis, Alexandros and Wang, Yi-Chia and Molino, Piero and Tur, Gokhan},
  journal={arXiv preprint arXiv:1907.05507},
  year={2019}
}

@article{takanobu2019guided,
  title={Guided dialog policy learning: Reward estimation for multi-domain task-oriented dialog},
  author={Takanobu, Ryuichi and Zhu, Hanlin and Huang, Minlie},
  journal={arXiv preprint arXiv:1908.10719},
  year={2019}
}

@article{su2021multi,
  title={Multi-task pre-training for plug-and-play task-oriented dialogue system},
  author={Su, Yixuan and Shu, Lei and Mansimov, Elman and Gupta, Arshit and Cai, Deng and Lai, Yi-An and Zhang, Yi},
  journal={arXiv preprint arXiv:2109.14739},
  year={2021}
}