Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
38 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

Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System (2310.08877v2)

Published 13 Oct 2023 in cs.CL

Abstract: Developing an efficient retriever to retrieve knowledge from a large-scale knowledge base (KB) is critical for task-oriented dialogue systems to effectively handle localized and specialized tasks. However, widely used generative models such as T5 and ChatGPT often struggle to differentiate subtle differences among the retrieved KB records when generating responses, resulting in suboptimal quality of generated responses. In this paper, we propose the application of maximal marginal likelihood to train a perceptive retriever by utilizing signals from response generation for supervision. In addition, our approach goes beyond considering solely retrieved entities and incorporates various meta knowledge to guide the generator, thus improving the utilization of knowledge. We evaluate our approach on three task-oriented dialogue datasets using T5 and ChatGPT as the backbone models. The results demonstrate that when combined with meta knowledge, the response generator can effectively leverage high-quality knowledge records from the retriever and enhance the quality of generated responses. The codes and models of this paper are available at https://github.com/shenwzh3/MK-TOD.

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 (30)
  1. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
  2. MultiWOZ 2.1: A consolidated multi-domain dialogue dataset with state corrections and state tracking baselines. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 422–428, Marseille, France. European Language Resources Association.
  3. Key-value retrieval networks for task-oriented dialogue. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 37–49, Saarbrücken, Germany. Association for Computational Linguistics.
  4. Fg2seq: Effectively encoding knowledge for end-to-end task-oriented dialog. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 8029–8033. IEEE.
  5. Task-oriented dialog generation with enhanced entity representation. In INTERSPEECH, pages 3905–3909.
  6. Word-based dialog state tracking with recurrent neural networks. In Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pages 292–299.
  7. A simple language model for task-oriented dialogue. In Advances in Neural Information Processing Systems, volume 33, pages 20179–20191. Curran Associates, Inc.
  8. Autoregressive entity generation for end-to-end task-oriented dialog. In Proceedings of the 29th International Conference on Computational Linguistics, pages 323–332.
  9. Gautier Izacard and Edouard Grave. 2021. Leveraging passage retrieval with generative models for open domain question answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 874–880, Online. Association for Computational Linguistics.
  10. Gautier Izacard and Edouard Grave. 2022. Distilling knowledge from reader to retriever for question answering. arXiv preprint arXiv:2012.04584.
  11. Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781.
  12. Retrieval-augmented generation for knowledge-intensive nlp tasks. In Advances in Neural Information Processing Systems, volume 33, pages 9459–9474. Curran Associates, Inc.
  13. Learning knowledge bases with parameters for task-oriented dialogue systems. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2372–2394.
  14. Mem2Seq: Effectively incorporating knowledge bases into end-to-end task-oriented dialog systems. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1468–1478, Melbourne, Australia. Association for Computational Linguistics.
  15. OpenAI. 2022. Chatgpt: Conversational ai language model. Website. https://openai.com/chatgpt.
  16. 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.
  17. Entity-consistent end-to-end task-oriented dialogue system with KB retriever. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 133–142, Hong Kong, China. Association for Computational Linguistics.
  18. Dynamic fusion network for multi-domain end-to-end task-oriented dialog. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6344–6354, Online. Association for Computational Linguistics.
  19. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21:1–67.
  20. Constraint based knowledge base distillation in end-to-end task oriented dialogs. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 5051–5061.
  21. RocketQAv2: A joint training method for dense passage retrieval and passage re-ranking. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2825–2835, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  22. Dialokg: Knowledge-structure aware task-oriented dialogue generation. arXiv preprint arXiv:2204.09149.
  23. Replug: Retrieval-augmented black-box language models. arXiv preprint arXiv:2301.12652.
  24. End-to-end training of multi-document reader and retriever for open-domain question answering. In Advances in Neural Information Processing Systems, volume 34, pages 25968–25981. Curran Associates, Inc.
  25. Q-tod: A query-driven task-oriented dialogue system. arXiv preprint arXiv:2210.07564.
  26. Multi-grained knowledge retrieval for end-to-end task-oriented dialog. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11196–11210, Toronto, Canada. Association for Computational Linguistics.
  27. A network-based end-to-end trainable task-oriented dialogue system. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 438–449, Valencia, Spain. Association for Computational Linguistics.
  28. Global-to-local memory pointer networks for task-oriented dialogue. In International Conference on Learning Representations.
  29. Graphmemdialog: Optimizing end-to-end task-oriented dialog systems using graph memory networks. In the AAAI Conference on Artificial Intelligence, pages 11504–11512.
  30. Unifiedskg: Unifying and multi-tasking structured knowledge grounding with text-to-text language models. arXiv preprint arXiv:2201.05966.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Weizhou Shen (18 papers)
  2. Yingqi Gao (5 papers)
  3. Canbin Huang (4 papers)
  4. Fanqi Wan (20 papers)
  5. Xiaojun Quan (52 papers)
  6. Wei Bi (62 papers)
Citations (7)
View on Semantic Scholar