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

UniRQR: A Unified Model for Retrieval Decision, Query, and Response Generation in Internet-Based Knowledge Dialogue Systems (2401.06811v1)

Published 11 Jan 2024 in cs.IR, cs.AI, and cs.CL

Abstract: Knowledge-based dialogue systems with internet retrieval have recently attracted considerable attention from researchers. The dialogue systems overcome a major limitation of traditional knowledge dialogue systems, where the timeliness of knowledge cannot be assured, hence providing greater practical application value. Knowledge-based dialogue systems with internet retrieval can be typically segmented into three tasks: Retrieval Decision, Query Generation, and Response Generation. However, many of studies assumed that all conversations require external knowledge to continue, neglecting the critical step of determining when retrieval is necessary. This assumption often leads to an over-dependence on external knowledge, even when it may not be required. Our work addresses this oversight by employing a single unified model facilitated by prompt and multi-task learning approaches. This model not only decides whether retrieval is necessary but also generates retrieval queries and responses. By integrating these functions, our system leverages the full potential of pre-trained models and reduces the complexity and costs associated with deploying multiple models. We conducted extensive experiments to investigate the mutual enhancement among the three tasks in our system. What is more, the experiment results on the Wizint and Dusinc datasets not only demonstrate that our unified model surpasses the baseline performance for individual tasks, but also reveal that it achieves comparable results when contrasted with SOTA systems that deploy separate, specialized models for each task.

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 (29)
  1. Pretrained language models for dialogue generation with multiple input sources. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 909–917, 2020.
  2. Unsupervised knowledge selection for dialogue generation. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1230–1244, 2021.
  3. Towards information-rich, logical dialogue systems with knowledge-enhanced neural models. Neurocomputing, 2021.
  4. Dynamically retrieving knowledge via query generation for informative dialogue generation. Neurocomputing, 569:127036, 2024.
  5. 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, pages 119–125, 2021.
  6. Achieving reliable human assessment of open-domain dialogue systems. arXiv preprint arXiv:2203.05899, 2022.
  7. Is continuous prompt a combination of discrete prompts? towards a novel view for interpreting continuous prompts. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7804–7819, 2023.
  8. Open-domain dialogue generation: What we can do, cannot do, and should do next. In Proceedings of the 4th Workshop on NLP for Conversational AI, pages 148–165, 2022.
  9. Internet-augmented dialogue generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8460–8478, 2022.
  10. 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, 2020.
  11. Knowledge graph based natural language generation with adapted pointer-generator networks. Neurocomputing, 382(2–3), 2019.
  12. Knowledge bridging for empathetic dialogue generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 10993–11001, 2022.
  13. Generating informative conversational response using recurrent knowledge-interaction and knowledge-copy. In Proceedings of the 58th annual meeting of the association for computational linguistics, pages 41–52, 2020.
  14. Generating emotional response by conditional variational auto-encoder in open-domain dialogue system. Neurocomputing, 460:106–116, 2021.
  15. A disentangled-attention based framework with persona-aware prompt learning for dialogue generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 13255–13263, 2023.
  16. Focused attention improves document-grounded generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4274–4287, 2021.
  17. Recipes for building an open-domain chatbot. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 300–325, 2021.
  18. Multitask prompted training enables zero-shot task generalization. In ICLR 2022-Tenth International Conference on Learning Representations, 2022.
  19. Cpt: A pre-trained unbalanced transformer for both chinese language understanding and generation. arXiv preprint arXiv:2109.05729, 2021.
  20. Language models that seek for knowledge: Modular search & generation for dialogue and prompt completion. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 373–393, 2022.
  21. Enhancing dialogue generation via dynamic graph knowledge aggregation. arXiv preprint arXiv:2306.16195, 2023.
  22. Emotion-and-knowledge grounded response generation in an open-domain dialogue setting. Knowledge-Based Systems, page 111173, 2023.
  23. Improving the applicability of knowledge-enhanced dialogue generation systems by using heterogeneous knowledge from multiple sources. In Proceedings of the Fifteenth ACM International Conference on WEB Search and Data Mining, pages 1149–1157, 2022.
  24. Adaptive bridge between training and inference for dialogue generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2541–2550, 2021.
  25. Personalized dynamic attention multi-task learning model for document retrieval and query generation. Expert Systems with Applications, 213:119026, 2023.
  26. Knowledge-grounded dialogue generation with term-level de-noising. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2972–2983, 2021.
  27. Kdconv: A chinese multi-domain dialogue dataset towards multi-turn knowledge-driven conversation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7098–7108, 2020.
  28. Sinc: Service information augmented open-domain conversation. arXiv preprint arXiv:2206.14000, 2022.
  29. Dual context-guided continuous prompt tuning for few-shot learning. In Findings of the Association for Computational Linguistics: ACL 2022, pages 79–84, 2022.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Zhongtian Hu (10 papers)
  2. Yangqi Chen (2 papers)
  3. Meng Zhao (48 papers)
  4. Ronghan Li (16 papers)
  5. Lifang Wang (9 papers)