Annual Conference of KIPS (한국정보처리학회:학술대회논문집)

  • 2024.10a
  • /
  • Pages.545-548
  • /
  • 2024
  • /
  • 2005-0011(pISSN)
  • /
  • 2671-7298(eISSN)
Korea Information Processing Society (한국정보처리학회)
권호 표지

A Review of Text Generation Models for Empathic Responses

  • Kim Ngan Phan (Department of AI Convergence, Chonnam National University) ;
  • Hyung-Jeong Yang (Department of AI Convergence, Chonnam National University) ;
  • Jieun Shin (Department of AI Convergence, Chonnam National University) ;
  • Seungwon Kim (Department of AI Convergence, Chonnam National University) ;
  • Soo-Hyung Kim (Department of AI Convergence, Chonnam National University)
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Empathetic response generation is a challenging concern in the field of natural language processing. Recent studies are trying to generate empathic responses to humans in dialogues. The published EmpatheticDialogues dataset is a solid foundation for the task of generating empathic responses. Many researchers have experimented with the EmpatheticDialogues dataset, which has many potential variations of transformer architectures. In this paper, we survey several previous approaches to the task of generating empathic responses with the aim of indicating the potential of future deep-learning models.

Keywords

Acknowledgement

This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) under the Artificial Intelligence Convergence Innovation Human Resources Development (IITP-2023-RS-2023-00256629) grant funded by the Korea government (MSIT), the ITRC (Information Technology Research Center) support program (IITP-2024-RS-2024-00437718) supervised by IITP, and the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (RS- 2023-00219107).

References

  1. Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y-Lan Boureau. 2019. Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5370-5381, Florence, Italy. Association for Computational Linguistics.
  2. Vaswani, A. "Attention is all you need." Advances in Neural Information Processing Systems (2017).
  3. Navonil Majumder, Pengfei Hong, Shanshan Peng, Jiankun Lu, Deepanway Ghosal, Alexander Gelbukh, Rada Mihalcea, and Soujanya Poria. 2020. MIME: MIMicking Emotions for Empathetic Response Generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8968-8979, Online. Association for Computational Linguistics.
  4. Sabour, Sahand, Chujie Zheng, and Minlie Huang. "Cem: Commonsense-aware empathetic response generation." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 36. No. 10. 2022. 
  5. Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, and Yejin Choi. 2019. 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. Association for Computational Linguistics.
  6. Lanrui Wang, Jiangnan Li, Zheng Lin, Fandong Meng, Chenxu Yang, Weiping Wang, and Jie Zhou. 2022. Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4634-4645, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  7. Jiashuo Wang, Yi Cheng, and Wenjie Li. 2022. CARE: Causality Reasoning for Empathetic Responses by Conditional Graph Generation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 729-741, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  8. Li, Bobo, et al. "Integrating discourse features and response assessment for advancing empathetic dialogue." Information Processing & Management 61.5 (2024): 103803.Li, Bobo, et al. "Integrating discourse features and response assessment for advancing empathetic dialogue." Information Processing & Management 61.5 (2024): 103803.
  9. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. 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. Association for Computational Linguistics.
  10. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016. A Diversity-Promoting Objective Function for Neural Conversation Models. In 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. Association for Computational Linguistics.
  11. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311-318, Philadelphia, Pennsylvania, USA. Association for Computational Linguistics.