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

Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue (2403.06063v1)

Published 10 Mar 2024 in cs.CL and cs.AI

Abstract: Target-oriented proactive dialogue systems aim to lead conversations from a dialogue context toward a pre-determined target, such as making recommendations on designated items or introducing new specific topics. To this end, it is critical for such dialogue systems to plan reasonable actions to drive the conversation proactively, and meanwhile, to plan appropriate topics to move the conversation forward to the target topic smoothly. In this work, we mainly focus on effective dialogue planning for target-oriented dialogue generation. Inspired by decision-making theories in cognitive science, we propose a novel target-constrained bidirectional planning (TRIP) approach, which plans an appropriate dialogue path by looking ahead and looking back. By formulating the planning as a generation task, our TRIP bidirectionally generates a dialogue path consisting of a sequence of <action, topic> pairs using two Transformer decoders. They are expected to supervise each other and converge on consistent actions and topics by minimizing the decision gap and contrastive generation of targets. Moreover, we propose a target-constrained decoding algorithm with a bidirectional agreement to better control the planning process. Subsequently, we adopt the planned dialogue paths to guide dialogue generation in a pipeline manner, where we explore two variants: prompt-based generation and plan-controlled generation. Extensive experiments are conducted on two challenging dialogue datasets, which are re-purposed for exploring target-oriented dialogue. Our automatic and human evaluations demonstrate that the proposed methods significantly outperform various baseline models.

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 (75)
  1. Plug and Play Language Models: A Simple Approach to Controlled Text Generation. In International Conference on Learning Representations (ICLR).
  2. A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23. International Joint Conferences on Artificial Intelligence Organization, 6583–6591.
  3. A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems. ACM Transactions on Information Systems (TOIS) 41, 3 (2023), 1–25.
  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 (NAACL-HLT). Association for Computational Linguistics, Minneapolis, Minnesota, 4171–4186.
  5. Joseph L Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological bulletin 76, 5 (1971), 378.
  6. DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies: Demonstrations. Association for Computational Linguistics, Online, 26–34.
  7. Retrieval-based goal-oriented dialogue generation. arXiv preprint arXiv:1909.13717 (2019).
  8. Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation. In Findings of the Association for Computational Linguistics: NAACL 2022. Association for Computational Linguistics, Seattle, United States, 1301–1317.
  9. INSPIRED: Toward Sociable Recommendation Dialog Systems. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, Online, 8142–8152.
  10. PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL). 2288–2305.
  11. DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP). 6408–6423.
  12. Xinyu Hua and Lu Wang. 2019. Sentence-Level Content Planning and Style Specification for Neural Text Generation. 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). 591–602.
  13. Xinyu Hua and Lu Wang. 2020. PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 781–793.
  14. Challenges in building intelligent open-domain dialog systems. ACM Transactions on Information Systems (TOIS) 38, 3 (2020), 1–32.
  15. Formalizing planning and information search in naturalistic decision-making. Nature Neuroscience 24, 8 (2021), 1051–1064.
  16. Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue. 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). Association for Computational Linguistics, Hong Kong, China, 1951–1961.
  17. Yoon Kim. 2014. Convolutional Neural Networks for Sentence Classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, Doha, Qatar, 1746–1751.
  18. Diederik P Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980 (2014).
  19. Contrastive Learning with Adversarial Perturbations for Conditional Text Generation. In ICLR.
  20. Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems. In Proceedings of the 13th International Conference on Web Search and Data Mining (WSDM). 304–312.
  21. 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. 7871–7880.
  22. 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 (NAACL-HLT). Association for Computational Linguistics, San Diego, California, 110–119.
  23. Towards Deep Conversational Recommendations. In Proceedings of the 32nd International Conference on Neural Information Processing Systems. 9748–9758.
  24. DEUX: An Attribute-Guided Framework for Sociable Recommendation Dialog Systems. arXiv preprint arXiv:2105.00825 (2021).
  25. Learning Neural Templates for Recommender Dialogue System. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 7821–7833.
  26. Target-guided Knowledge-aware Recommendation Dialogue System: An Empirical Investigation. In 3rd Edition of Knowledge-aware and Conversational Recommender Systems (KaRS) & 5th Edition of Recommendation in Complex Environments (ComplexRec) Joint Workshop @ RecSys 2021.
  27. COLA: Improving Conversational Recommender Systems by Collaborative Augmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37. 4462–4470.
  28. Pretraining the Noisy Channel Model for Task-Oriented Dialogue. Transactions of the Association for Computational Linguistics 9 (2021), 657–674.
  29. DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 4335–4347.
  30. Towards Conversational Recommendation over Multi-Type Dialogs. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL). Association for Computational Linguistics, Online, 1036–1049.
  31. CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational Recommendation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 1839–1851.
  32. Few-Shot Bot: Prompt-Based Learning for Dialogue Systems. arXiv preprint arXiv:2110.08118 (2021).
  33. 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 (ACL). 1468–1478.
  34. Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). 2267–2277.
  35. Vinod Nair and Geoffrey E Hinton. 2010. Rectified linear units improve restricted boltzmann machines. In ICML.
  36. OpenAI. 2022. Introducing ChatGPT. https://openai.com/blog/chatgpt.
  37. Bleu: a Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL). Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, 311–318.
  38. Matt Post and David Vilar. 2018. Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 1314–1324.
  39. Data-to-text generation with content selection and planning. In Proceedings of the AAAI conference on artificial intelligence, Vol. 33. 6908–6915.
  40. Dynamic knowledge routing network for target-guided open-domain conversation. In Proceedings of the AAAI Conference on Artificial Intelligence. 8657–8664.
  41. Language Models Are Unsupervised Multitask Learners. OpenAI Blog 1, 8 (2019), 9.
  42. OTTers: One-turn Topic Transitions for Open-Domain Dialogue. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP). Association for Computational Linguistics, Online, 2492–2504.
  43. Claude Elwood Shannon. 1948. A mathematical theory of communication. The Bell system technical journal 27, 3 (1948), 379–423.
  44. Long and Diverse Text Generation with Planning-based Hierarchical Variational Model. 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). 3257–3268.
  45. Context-Aware Language Modeling for Goal-Oriented Dialogue Systems. In Findings of the Association for Computational Linguistics: NAACL 2022. 2351–2366.
  46. Plan-then-Generate: Controlled Data-to-Text Generation via Planning. In Findings of the Association for Computational Linguistics: EMNLP 2021. 895–909.
  47. Yueming Sun and Yi Zhang. 2018. Conversational Recommender System. In Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval. 235–244.
  48. Target-Guided Open-Domain Conversation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL). Association for Computational Linguistics, Florence, Italy, 5624–5634.
  49. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023).
  50. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023).
  51. Evangelos Triantaphyllou. 2000. Multi-criteria decision making methods. In Multi-criteria decision making methods: A comparative study. Springer, 5–21.
  52. Large Language Models Still Can’t Plan (A Benchmark for LLMs on Planning and Reasoning about Change). In NeurIPS 2022 Foundation Models for Decision Making Workshop.
  53. On the planning abilities of large language models (a critical investigation with a proposed benchmark). arXiv preprint arXiv:2302.06706 (2023).
  54. Attention Is All You Need. In Advances in Neural Information Processing Systems. 5998–6008.
  55. Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems. arXiv preprint arXiv:2208.03516 (2022).
  56. A target-driven planning approach for goal-directed dialog systems. IEEE Transactions on Neural Networks and Learning Systems (2023).
  57. Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems. In Proceedings of the 28th International Conference on Computational Linguistics, Donia Scott, Nuria Bel, and Chengqing Zong (Eds.). International Committee on Computational Linguistics, Barcelona, Spain (Online), 4100–4110.
  58. Improving knowledge-aware dialogue generation via knowledge base question answering. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 9169–9176.
  59. A Large-scale Chinese Short-text Conversation Dataset. In CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC). Springer, 91–103.
  60. Transformers: State-of-the-Art Natural Language Processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP): System Demonstrations. Association for Computational Linguistics, Online, 38–45.
  61. Global-to-local Memory Pointer Networks for Task-oriented Dialogue. In 7th International Conference on Learning Representations (ICLR).
  62. Proactive Human-Machine Conversation with Explicit Conversation Goal. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL). Association for Computational Linguistics, Florence, Italy, 3794–3804.
  63. User Memory Reasoning for Conversational Recommendation. In Proceedings of the 28th International Conference on Computational Linguistics (COLING). International Committee on Computational Linguistics, Barcelona, Spain (Online), 5288–5308.
  64. Knowledge Graph Grounded Goal Planning for Open-domain Conversation Generation. In Proceedings of the AAAI Conference on Artificial Intelligence. 9338–9345.
  65. Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL). Association for Computational Linguistics, Online, 1835–1845.
  66. Adapting User Preference to Online Feedback in Multi-round Conversational Recommendation. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining (WSDM). 364–372.
  67. Denis Yarats and Mike Lewis. 2018. Hierarchical text generation and planning for strategic dialogue. In International Conference on Machine Learning (ICML). 5591–5599.
  68. KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals. In Findings of the Association for Computational Linguistics: EMNLP 2021. Association for Computational Linguistics, Punta Cana, Dominican Republic, 1092–1101.
  69. KECRS: Towards Knowledge-Enriched Conversational Recommendation System. arXiv preprint arXiv:2105.08261 (2021).
  70. DIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL): System Demonstrations. Association for Computational Linguistics, Online, 270–278.
  71. Chujie Zheng and Minlie Huang. 2021. Exploring prompt-based few-shot learning for grounded dialog generation. arXiv preprint arXiv:2109.06513 (2021).
  72. Keyword-Guided Neural Conversational Model. In Proceedings of the AAAI Conference on Artificial Intelligence. 14568–14576.
  73. Improving conversational recommender systems via knowledge graph based semantic fusion. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1006–1014.
  74. Towards Topic-Guided Conversational Recommender System. In Proceedings of the 28th International Conference on Computational Linguistics (COLING). International Committee on Computational Linguistics, Barcelona, Spain (Online), 4128–4139.
  75. Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History. In International Conference on Learning Representations (ICLR).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Jian Wang (966 papers)
  2. Dongding Lin (6 papers)
  3. Wenjie Li (183 papers)