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

Persona-Coded Poly-Encoder: Persona-Guided Multi-Stream Conversational Sentence Scoring (2309.16770v2)

Published 28 Sep 2023 in cs.CL, cs.AI, and cs.LG

Abstract: Recent advances in machine learning and deep learning have led to the widespread use of Conversational AI in many practical applications. However, it is still very challenging to leverage auxiliary information that can provide conversational context or personalized tuning to improve the quality of conversations. For example, there has only been limited research on using an individuals persona information to improve conversation quality, and even state-of-the-art conversational AI techniques are unable to effectively leverage signals from heterogeneous sources of auxiliary data, such as multi-modal interaction data, demographics, SDOH data, etc. In this paper, we present a novel Persona-Coded Poly-Encoder method that leverages persona information in a multi-stream encoding scheme to improve the quality of response generation for conversations. To show the efficacy of the proposed method, we evaluate our method on two different persona-based conversational datasets, and compared against two state-of-the-art methods. Our experimental results and analysis demonstrate that our method can improve conversation quality over the baseline method Poly-Encoder by 3.32% and 2.94% in terms of BLEU score and HR@1, respectively. More significantly, our method offers a path to better utilization of multi-modal data in conversational tasks. Lastly, our study outlines several challenges and future research directions for advancing personalized conversational AI technology.

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 (31)
  1. I. Sutskever, O. Vinyals, and Q. V. Le, “Sequence to sequence learning with neural networks,” in Advances in neural information processing systems, 2014, pp. 3104–3112.
  2. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” in Advances in neural information processing systems, 2017, pp. 5998–6008.
  3. A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever et al., “Language models are unsupervised multitask learners,” OpenAI blog, vol. 1, no. 8, p. 9, 2019.
  4. T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al., “Language models are few-shot learners,” arXiv preprint arXiv:2005.14165, 2020.
  5. J. Li, M. Galley, C. Brockett, G. P. Spithourakis, J. Gao, and B. Dolan, “A persona-based neural conversation model,” arXiv preprint arXiv:1603.06155, 2016.
  6. S. Zhang, E. Dinan, J. Urbanek, A. Szlam, D. Kiela, and J. Weston, “Personalizing dialogue agents: I have a dog, do you have pets too?” arXiv preprint arXiv:1801.07243, 2018.
  7. N. Mostafazadeh, C. Brockett, B. Dolan, M. Galley, J. Gao, G. P. Spithourakis, and L. Vanderwende, “Image-grounded conversations: Multimodal context for natural question and response generation,” arXiv preprint arXiv:1701.08251, 2017.
  8. M. Ghazvininejad, C. Brockett, M.-W. Chang, B. Dolan, J. Gao, W.-t. Yih, and M. Galley, “A knowledge-grounded neural conversation model,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, 2018.
  9. Y. Zhang, M. Galley, J. Gao, Z. Gan, X. Li, C. Brockett, and B. Dolan, “Generating informative and diverse conversational responses via adversarial information maximization,” Advances in Neural Information Processing Systems, vol. 31, 2018.
  10. Y. Zhang, S. Sun, M. Galley, Y.-C. Chen, C. Brockett, X. Gao, J. Gao, J. Liu, and B. Dolan, “Dialogpt: Large-scale generative pre-training for conversational response generation,” arXiv:1911.00536, 2019.
  11. OpenAI, “Chatgpt: Optimizing language models for dialogue,” Nov 2022. [Online]. Available: https://openai.com/blog/chatgpt/
  12. T. Wolf, V. Sanh, J. Chaumond, and C. Delangue, “Transfertransfo: A transfer learning approach for neural network based conversational agents,” arXiv preprint arXiv:1901.08149, 2019.
  13. S. Humeau, K. Shuster, M.-A. Lachaux, and J. Weston, “Poly-encoders: Transformer architectures and pre-training strategies for fast and accurate multi-sentence scoring,” arXiv preprint arXiv:1905.01969, 2019.
  14. Y. Luan, J. Eisenstein, K. Toutanova, and M. Collins, “Sparse, dense, and attentional representations for text retrieval,” Transactions of the Association for Computational Linguistics, vol. 9, pp. 329–345, 2021.
  15. O. Khattab and M. Zaharia, “Colbert: Efficient and effective passage search via contextualized late interaction over bert,” in Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, 2020, pp. 39–48.
  16. R. Cooper, “What’s precision nudging™ all about?” Oct 2020. [Online]. Available: https://lirio.com/blog/whats-precision-nudging-all-about/
  17. H. Rashkin, E. M. Smith, M. Li, and Y.-L. Boureau, “Towards empathetic open-domain conversation models: A new benchmark and dataset,” arXiv preprint arXiv:1811.00207, 2018.
  18. P. Zhong, C. Zhang, H. Wang, Y. Liu, and C. Miao, “Towards persona-based empathetic conversational models,” arXiv preprint arXiv:2004.12316, 2020.
  19. H. Song, W.-N. Zhang, Y. Cui, D. Wang, and T. Liu, “Exploiting persona information for diverse generation of conversational responses,” arXiv preprint arXiv:1905.12188, 2019.
  20. J. Liu, C. Symons, and R. R. Vatsavai, “Persona-based conversational ai: State of the art and challenges,” In Press, 2022.
  21. E. Dinan, V. Logacheva, V. Malykh, A. Miller, K. Shuster, J. Urbanek, D. Kiela, A. Szlam, I. Serban, R. Lowe et al., “The second conversational intelligence challenge (convai2),” in The NeurIPS’18 Competition.   Springer, 2020, pp. 187–208.
  22. J.-C. Gu, T. Li, Z.-H. Ling, Q. Liu, Z. Su, Y.-P. Ruan, and X. Zhu, “Deep contextualized utterance representations for response selection and dialogue analysis,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 2443–2455, 2021.
  23. P.-E. Mazaré, S. Humeau, M. Raison, and A. Bordes, “Training millions of personalized dialogue agents,” arXiv:1809.01984, 2018.
  24. A. Ritter, C. Cherry, and B. Dolan, “Unsupervised modeling of twitter conversations,” in Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2010, pp. 172–180.
  25. X. Wang, W. Shi, R. Kim, Y. Oh, S. Yang, J. Zhang, and Z. Yu, “Persuasion for good: Towards a personalized persuasive dialogue system for social good,” in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019, pp. 5635–5649.
  26. Q. Chen and W. Wang, “Sequential neural networks for noetic end-to-end response selection,” Computer Speech & Language, vol. 62, p. 101072, 2020.
  27. K. K. Gadiraju, B. Ramachandra, Z. Chen, and R. R. Vatsavai, “Multimodal deep learning based crop classification using multispectral and multitemporal satellite imagery,” in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020, pp. 3234–3242.
  28. K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, “Bleu: a method for automatic evaluation of machine translation,” in Proceedings of the 40th annual meeting of the Association for Computational Linguistics, 2002, pp. 311–318.
  29. T. Hofmann, “Probabilistic latent semantic analysis,” arXiv preprint arXiv:1301.6705, 2013.
  30. E. Hermann, “Artificial intelligence and mass personalization of communication content—an ethical and literacy perspective,” New Media & Society, vol. 24, no. 5, pp. 1258–1277, 2022.
  31. B. Libai, Y. Bart, S. Gensler, C. F. Hofacker, A. Kaplan, K. Kötterheinrich, and E. B. Kroll, “Brave new world? on ai and the management of customer relationships,” Journal of Interactive Marketing, vol. 51, pp. 44–56, 2020.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Junfeng Liu (33 papers)
  2. Christopher Symons (2 papers)
  3. Ranga Raju Vatsavai (11 papers)