Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

E-CORE: Emotion Correlation Enhanced Empathetic Dialogue Generation (2311.15016v1)

Published 25 Nov 2023 in cs.CL and cs.AI

Abstract: Achieving empathy is a crucial step toward humanized dialogue systems. Current approaches for empathetic dialogue generation mainly perceive an emotional label to generate an empathetic response conditioned on it, which simply treat emotions independently, but ignore the intrinsic emotion correlation in dialogues, resulting in inaccurate emotion perception and unsuitable response generation. In this paper, we propose a novel emotion correlation enhanced empathetic dialogue generation framework, which comprehensively realizes emotion correlation learning, utilization, and supervising. Specifically, a multi-resolution emotion graph is devised to capture context-based emotion interactions from different resolutions, further modeling emotion correlation. Then we propose an emotion correlation enhanced decoder, with a novel correlation-aware aggregation and soft/hard strategy, respectively improving the emotion perception and response generation. Experimental results on the benchmark dataset demonstrate the superiority of our model in both empathetic perception and expression.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Simulated annealing for emotional dialogue systems. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pages 2984–2988.
  2. More the merrier: Towards multi-emotion and intensity controllable response generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 12821–12829.
  3. Delivering cognitive behavior therapy to young adults with symptoms of depression and anxiety using a fully automated conversational agent (woebot): a randomized controlled trial. JMIR mental health, 4(2):e7785.
  4. Improving empathetic response generation by recognizing emotion cause in conversations. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 807–819.
  5. Clayton Hutto and Eric Gilbert. 2014. Vader: A parsimonious rule-based model for sentiment analysis of social media text. In Proceedings of the international AAAI conference on web and social media, volume 8, pages 216–225.
  6. Tatsuya Ide and Daisuke Kawahara. 2021. Multi-task learning of generation and classification for emotion-aware dialogue response generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, NAACL-HLT 2021.
  7. Perspective-taking and pragmatics for generating empathetic responses focused on emotion causes. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021,.
  8. Emp-rft: Empathetic response generation via recognizing feature transitions between utterances. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022.
  9. D. Kingma and J. Ba. 2014. Adam: A method for stochastic optimization. Computer Science.
  10. A diversity-promoting objective function for neural conversation models. Computer Science.
  11. Deep reinforcement learning for dialogue generation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016.
  12. Dual-view conditional variational auto-encoder for emotional dialogue generation. Transactions on Asian and Low-Resource Language Information Processing, 21(3):1–18.
  13. Empdg: Multiresolution interactive empathetic dialogue generation. In Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020,.
  14. Towards empathetic dialogue generation over multi-type knowledge. arXiv preprint arXiv:2009.09708.
  15. Empathetic dialogue generation via knowledge enhancing and emotion dependency modeling. In Findings of the Association for Computational Linguistics: EMNLP.
  16. Knowledge bridging for empathetic dialogue generation. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI, pages 10993–11001.
  17. Infusing multi-source knowledge with heterogeneous graph neural network for emotional conversation generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 13343–13352.
  18. Moel: Mixture of empathetic listeners. In EMNLP-IJCNLP 2019.
  19. How not to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016.
  20. Mime: Mimicking emotions for empathetic response generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020,.
  21. A descriptive study of emotional process during competition: Nature, frequency, direction, duration and co-occurrence of discrete emotions. Psychology of Sport and Exercise, 13(2):142–151.
  22. Nebuly-AI. 2023. Chatllama. https://serp.ai/tools/chat-llama. Accessed 16 June 2023.
  23. OpenAI. 2022. Chatgpt. https://openai.com/blog/chatgpt. Accessed 16 June 2023.
  24. Nobuyuki Otsu. 1979. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1):62–66.
  25. Automatic differentiation in pytorch.
  26. Glove: Global vectors for word representation. In Conference on Empirical Methods in Natural Language Processing (EMNLP).
  27. Towards empathetic open-domain conversation models: a new benchmark and dataset. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019.
  28. Cem: Commonsense-aware empathetic response generation. In Conference on Artificial Intelligence, AAAI.
  29. Klaus R Scherer. 2013. Measuring the meaning of emotion words: A domain-specific componential approach.
  30. Fabrizio Sebastiani and Andrea Esuli. 2006. Sentiwordnet: A publicly available lexical resource for opinion mining. In Proceedings of the 5th international conference on language resources and evaluation, pages 417–422. European Language Resources Association (ELRA) Genoa, Italy.
  31. Hierarchical neural network generative models for movie dialogues. Computer Science.
  32. Constructing emotion consensus and utilizing unpaired data for empathetic dialogue generation. Findings of the Association for Computational Linguistics: EMNLP 2021.
  33. Generating empathetic responses by looking ahead the user’s sentiment. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 7989–7993. IEEE.
  34. Tania Singer and Claus Lamm. 2009. The social neuroscience of empathy. Annals of the New York Academy of Sciences, 1156(1):81–96.
  35. Adam Smith. 2006. Cognitive empathy and emotional empathy in human behavior and evolution. The Psychological Record, 56(1):3–21.
  36. Generating responses with a specific emotion in dialog. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3685–3695.
  37. Skep: Sentiment knowledge enhanced pre-training for sentiment analysis. Association for Computational Linguistics, ACL.
  38. Misc: A mixed strategy-aware model integrating comet for emotional support conversation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022.
  39. The co-occurrence of emotions in daily life: A multilevel approach. Journal of Research in Personality, 39(3):325–335.
  40. Attention is all you need. In NIPS.
  41. Cass: Towards building a social-support chatbot for online health community. Proceedings of the ACM on Human-Computer Interaction, 5(CSCW1):1–31.
  42. Multi-turn dialogue generation in e-commerce platform with the context of historical dialogue. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1981–1990.
  43. Dialogpt: Large-scale generative pre-training for conversational response generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, ACL 2020.
  44. Knowledge-enriched transformer for emotion detection in textual conversations. arXiv preprint arXiv:1909.10681.
  45. Multi-party empathetic dialogue generation: A new task for dialog systems. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 298–307.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Fengyi Fu (3 papers)
  2. Lei Zhang (1689 papers)
  3. Quan Wang (130 papers)
  4. Zhendong Mao (55 papers)
Citations (6)
View on Semantic Scholar