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

UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Tracking (2310.10492v2)

Published 16 Oct 2023 in cs.CL

Abstract: Previous zero-shot dialogue state tracking (DST) methods only apply transfer learning, ignoring unlabelled data in the target domain. We transform zero-shot DST into few-shot DST by utilising such unlabelled data via joint and self-training methods. Our method incorporates auxiliary tasks that generate slot types as inverse prompts for main tasks, creating slot values during joint training. Cycle consistency between these two tasks enables the generation and selection of quality samples in unknown target domains for subsequent fine-tuning. This approach also facilitates automatic label creation, thereby optimizing the training and fine-tuning of DST models. We demonstrate this method's effectiveness on general LLMs in zero-shot scenarios, improving average joint goal accuracy by 8% across all domains in MultiWOZ.

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 (32)
  1. Recent neural methods on dialogue state tracking for task-oriented dialogue systems: A survey. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 239–251. Association for Computational Linguistics.
  2. Language models are few-shot learners. In Advances in Neural Information Processing Systems, volume 33, pages 1877–1901. Curran Associates, Inc.
  3. MultiWOZ - a large-scale multi-domain Wizard-of-Oz dataset for task-oriented dialogue modelling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 5016–5026, Brussels, Belgium. Association for Computational Linguistics.
  4. 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.
  5. Show, don’t tell: Demonstrations outperform descriptions for schema-guided task-oriented dialogue. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4541–4549, Seattle, United States. Association for Computational Linguistics.
  6. Trippy: A triple copy strategy for value independent neural dialog state tracking. arXiv preprint arXiv:2005.02877.
  7. The second dialog state tracking challenge. In Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pages 263–272, Philadelphia, PA, U.S.A. Association for Computational Linguistics.
  8. A simple language model for task-oriented dialogue. CoRR, abs/2005.00796.
  9. In-context learning for few-shot dialogue state tracking. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2627–2643, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  10. Discovering dialogue slots with weak supervision. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2430–2442. Association for Computational Linguistics.
  11. Dialogue state tracking with a language model using schema-driven prompting. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4937–4949, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  12. Tracking Must Go On : Dialogue State Tracking with Verified Self-Training. In Proc. INTERSPEECH 2023, pages 4678–4682.
  13. Zero-shot generalization in dialog state tracking through generative question answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1063–1074, Online. Association for Computational Linguistics.
  14. Zero-shot dialogue state tracking via cross-task transfer. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7890–7900, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  15. Leveraging slot descriptions for zero-shot cross-domain dialogue StateTracking. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5640–5648, Online. Association for Computational Linguistics.
  16. Neural belief tracker: Data-driven dialogue state tracking. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1777–1788, Vancouver, Canada. Association for Computational Linguistics.
  17. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21(1).
  18. Towards scalable multi-domain conversational agents: The schema-guided dialogue dataset. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 8689–8696.
  19. Towards universal dialogue state tracking. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2780–2786, Brussels, Belgium. Association for Computational Linguistics.
  20. Convolutional neural networks for multi-topic dialog state tracking. Dialogues with Social Robots: Enablements, Analyses, and Evaluation, pages 451–463.
  21. Dialogue summaries as dialogue states (DS2), template-guided summarization for few-shot dialogue state tracking. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3824–3846, Dublin, Ireland. Association for Computational Linguistics.
  22. Multi-task pre-training for plug-and-play task-oriented dialogue system. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4661–4676, Dublin, Ireland. Association for Computational Linguistics.
  23. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
  24. Self-supervised learning from a multi-view perspective.
  25. Slot dependency modeling for zero-shot cross-domain dialogue state tracking. In Proceedings of the 29th International Conference on Computational Linguistics, pages 510–520, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
  26. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations.
  27. TOD-BERT: Pre-trained natural language understanding for task-oriented dialogue. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 917–929, Online. Association for Computational Linguistics.
  28. Improving limited labeled dialogue state tracking with self-supervision. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4462–4472, Online. Association for Computational Linguistics.
  29. Transferable multi-domain state generator for task-oriented dialogue systems. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 808–819, Florence, Italy. Association for Computational Linguistics.
  30. A dual prompt learning framework for few-shot dialogue state tracking. In Proceedings of the ACM Web Conference 2023, WWW ’23, page 1468–1477, New York, NY, USA. Association for Computing Machinery.
  31. A survey on multi-task learning. IEEE Transactions on Knowledge and Data Engineering, 34(12):5586–5609.
  32. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Computer Vision (ICCV), 2017 IEEE International Conference on.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Chuang Li (43 papers)
  2. Yan Zhang (954 papers)
  3. Min-Yen Kan (92 papers)
  4. Haizhou Li (285 papers)
Citations (1)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets