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

An Iterative Associative Memory Model for Empathetic Response Generation (2402.17959v2)

Published 28 Feb 2024 in cs.CL and cs.HC

Abstract: Empathetic response generation aims to comprehend the cognitive and emotional states in dialogue utterances and generate proper responses. Psychological theories posit that comprehending emotional and cognitive states necessitates iteratively capturing and understanding associated words across dialogue utterances. However, existing approaches regard dialogue utterances as either a long sequence or independent utterances for comprehension, which are prone to overlook the associated words between them. To address this issue, we propose an Iterative Associative Memory Model (IAMM) for empathetic response generation. Specifically, we employ a novel second-order interaction attention mechanism to iteratively capture vital associated words between dialogue utterances and situations, dialogue history, and a memory module (for storing associated words), thereby accurately and nuancedly comprehending the utterances. We conduct experiments on the Empathetic-Dialogue dataset. Both automatic and human evaluations validate the efficacy of the model. Variant experiments on LLMs also demonstrate that attending to associated words improves empathetic comprehension 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 (39)
  1. Sergey Brin and Lawrence Page. 1998. The anatomy of a large-scale hypertextual web search engine. Computer networks and ISDN systems, 30(1-7):107–117.
  2. Improving empathetic dialogue generation by dynamically infusing commonsense knowledge. arXiv preprint arXiv:2306.04657.
  3. Llm-empowered chatbots for psychiatrist and patient simulation: Application and evaluation. arXiv preprint arXiv:2305.13614.
  4. Glm: General language model pretraining with autoregressive blank infilling. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 320–335.
  5. Joseph L Fleiss and Jacob Cohen. 1973. The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability. Educational and psychological measurement, 33(3):613–619.
  6. Improving empathetic response generation by recognizing emotion cause in conversations. In Findings of EMNLP, pages 807–819.
  7. Simon Garrod and Anthony Sanford. 2012. Referential processes in reading: Focusing on roles and individuals. In Comprehension processes in reading, pages 465–486. Routledge.
  8. Do readers mentally represent characters’ emotional states? Cognition & Emotion, 6(2):89–111.
  9. The representation of characters’ emotional responses: Do readers infer specific emotions? Cognition and Emotion, 17(3):413–428.
  10. (comet-) atomic 2020: On symbolic and neural commonsense knowledge graphs. In AAAI, volume 35, pages 6384–6392.
  11. Perspective-taking and pragmatics for generating empathetic responses focused on emotion causes. In EMNLP.
  12. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:abs/1412.6980.
  13. A diversity-promoting objective function for neural conversation models. arXiv:abs/1510.03055.
  14. Empdg: Multiresolution interactive empathetic dialogue generation. arXiv:abs/1911.08698.
  15. Knowledge bridging for empathetic dialogue generation. In AAAI.
  16. Infusing multi-source knowledge with heterogeneous graph neural network for emotional conversation generation. In AAAI, volume 35, pages 13343–13352.
  17. Moel: Mixture of empathetic listeners. In EMNLP-IJCNLP, page 121–132.
  18. Towards emotional support dialog systems. arXiv:abs/2106.01144.
  19. Mime: Mimicking emotions for empathetic response generation. In EMNLP, page 8968–8979.
  20. Danielle S McNamara and Joe Magliano. 2009. Toward a comprehensive model of comprehension. Psychology of learning and motivation, 51:297–384.
  21. Is chatgpt a general-purpose natural language processing task solver? arXiv preprint arXiv:2302.06476.
  22. Towards empathetic open-domain conversation models: A new benchmark and dataset. In ACL, page 5370–5381.
  23. Cem: Commonsense-aware empathetic response generation. In Proceedings of the AAAI Conference on Artificial Intelligence, Virginia, USA. AAAI Press.
  24. Get to the point: Summarization with pointer-generator networks. arXiv preprint arXiv:1704.04368.
  25. Is chatgpt good at search? investigating large language models as re-ranking agent. arXiv preprint arXiv:2304.09542.
  26. The science of detecting llm-generated texts. arXiv preprint arXiv:2303.07205.
  27. Strategies of discourse comprehension.
  28. On the robustness of chatgpt: An adversarial and out-of-distribution perspective. arXiv preprint arXiv:2302.12095.
  29. Empathetic dialogue generation via sensitive emotion recognition and sensible knowledge selection. arXiv preprint arXiv:2210.11715.
  30. A large-scale dataset for empathetic response generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1251–1264.
  31. Twitterrank: finding topic-sensitive influential twitterers. In Proceedings of the third ACM international conference on Web search and data mining, pages 261–270.
  32. Exploiting emotion-semantic correlations for empathetic response generation. In The 2023 Conference on Empirical Methods in Natural Language Processing.
  33. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414.
  34. Don’t lose yourself! empathetic response generation via explicit self-other awareness. arXiv preprint arXiv:2210.03884.
  35. Comae: A multi-factor hierarchical framework for empathetic response generation. In ACL.
  36. Lmsys-chat-1m: A large-scale real-world llm conversation dataset. arXiv preprint arXiv:2309.11998.
  37. Towards persona-based empathetic conversational models. arXiv:abs/2004.12316.
  38. CASE: Aligning coarse-to-fine cognition and affection for empathetic response generation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8223–8237, Toronto, Canada. Association for Computational Linguistics.
  39. Rolf A Zwaan and Gabriel A Radvansky. 1998. Situation models in language comprehension and memory. Psychological bulletin, 123(2):162.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Zhou Yang (82 papers)
  2. Zhaochun Ren (117 papers)
  3. Yufeng Wang (43 papers)
  4. Chao Chen (661 papers)
  5. Haizhou Sun (5 papers)
  6. Xiaofei Zhu (16 papers)
  7. Xiangwen Liao (8 papers)
Citations (3)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets