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

Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues (2307.01664v1)

Published 4 Jul 2023 in cs.CL

Abstract: Spoken dialogue systems (SDSs) have been separately developed under two different categories, task-oriented and chit-chat. The former focuses on achieving functional goals and the latter aims at creating engaging social conversations without special goals. Creating a unified conversational model that can engage in both chit-chat and task-oriented dialogue is a promising research topic in recent years. However, the potential ``initiative'' that occurs when there is a change between dialogue modes in one dialogue has rarely been explored. In this work, we investigate two kinds of dialogue scenarios, one starts from chit-chat implicitly involving task-related topics and finally switching to task-oriented requests; the other starts from task-oriented interaction and eventually changes to casual chat after all requested information is provided. We contribute two efficient prompt models which can proactively generate a transition sentence to trigger system-initiated transitions in a unified dialogue model. One is a discrete prompt model trained with two discrete tokens, the other one is a continuous prompt model using continuous prompt embeddings automatically generated by a classifier. We furthermore show that the continuous prompt model can also be used to guide the proactive transitions between particular domains in a multi-domain task-oriented setting.

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 (35)
  1. Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and/or summarization. 65–72.
  2. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877–1901.
  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. 5016–5026.
  4. SalesBot: Transitioning from Chit-Chat to Task-Oriented Dialogues. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 6143–6158.
  5. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780.
  6. The Curious Case of Neural Text Degeneration. In International Conference on Learning Representations.
  7. The Power of Scale for Parameter-Efficient Prompt Tuning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 3045–3059.
  8. A Diversity-Promoting Objective Function for Neural Conversation Models. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 110–119.
  9. Personalized Prompt Learning for Explainable Recommendation. arXiv preprint arXiv:2202.07371 (2022).
  10. The Adapter-Bot: All-In-One Controllable Conversational Model. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 16081–16083.
  11. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. arXiv preprint arXiv:2107.13586 (2021).
  12. GPT Understands, Too. arXiv e-prints (2021), arXiv–2103.
  13. Context Matters in Semantically Controlled Language Generation for Task-oriented Dialogue Systems. In Proceedings of the 18th International Conference on Natural Language Processing (ICON). NLP Association of India (NLPAI), National Institute of Technology Silchar, Silchar, India, 139–151. https://aclanthology.org/2021.icon-main.18
  14. Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge. In Conversational AI for Natural Human-Centric Interaction, Svetlana Stoyanchev, Stefan Ultes, and Haizhou Li (Eds.). Springer Nature Singapore, Singapore, 67–81.
  15. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019).
  16. On System-Initiated Transitions in a Unified Natural Language Generation Model for Dialogue Systems. In Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue - Poster Abstracts. SEMDIAL, Dublin, Ireland. http://semdial.org/anthology/Z22-Liu_semdial_0034.pdf
  17. Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017).
  18. Finding Appropriate Interaction Strategies for Proactive Dialogue Systems—An Open Quest. In Proc. of the 2nd European and the 5th Nordic Symposium on Multimodal Communication 2014 (Tartu, Estonia). LiU Electronic Press, 73–80. http://www.ep.liu.se/ecp/110/010/ecp15110010.pdf
  19. David G Novick and Stephen Sutton. 1997. What is mixed-initiative interaction. In Proceedings of the AAAI spring symposium on computational models for mixed initiative interaction, Vol. 2. 12.
  20. BLEU: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311–318.
  21. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9.
  22. Addressing loneliness and isolation in older adults: Proactive affective agents provide better support. In 2013 Humaine Association conference on affective computing and intelligent interaction. IEEE, 61–66.
  23. Leveraging pre-trained checkpoints for sequence generation tasks. Transactions of the Association for Computational Linguistics 8 (2020), 264–280.
  24. OTTers: One-turn topic transitions for open-domain dialogue. In Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 2492–2504.
  25. The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2453–2470.
  26. Ronnie W Smith. 1994. Spoken variable initiative dialog: An adaptable natural-language interface. IEEE Expert 9, 1 (1994), 45–50.
  27. Ronnie W Smith and Steven A Gordon. 1997. Effects of variable initiative on linguistic behavior in human-computer spoken natural language dialogue. Computational Linguistics 23, 1 (1997), 141–168.
  28. Adding Chit-Chat to Enhance Task-Oriented Dialogues. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 1570–1583.
  29. Marilyn Walker and Steve Whittaker. 1990. Mixed Initiative in Dialogue: An Investigation into Discourse Segmentation. In 28th Annual Meeting of the Association for Computational Linguistics. 70–78.
  30. AugNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation. 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). 1183–1195.
  31. MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation. CoRR abs/2104.00773 (2021). arXiv:2104.00773 https://arxiv.org/abs/2104.00773
  32. Fusing Task-oriented and Open-domain Dialogues in Conversational Agents. (2022).
  33. BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations.
  34. Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue. 27–36.
  35. UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues. arXiv e-prints (2021), arXiv–2110.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Ye Liu (153 papers)
  2. Stefan Ultes (32 papers)
  3. Wolfgang Minker (18 papers)
  4. Wolfgang Maier (7 papers)
Citations (3)
View on Semantic Scholar