mlsanityData to 7 Oct 2026

Few-shot Natural Language Generation for Task-Oriented Dialog

arXiv 2002.12328 ↗First posted 27 Feb 2020cs.CLcited by 89

Not on the map. Why?

Abstract (arXiv)

As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts a dialog act represented in a semantic form into a response in natural language. The success of traditional template-based or statistical models typically relies on heavily annotated data, which is infeasible for new domains. Therefore, it is pivotal for an NLG system to generalize well with limited labelled data in real applications. To this end, we present FewShotWoz, the first NLG benchmark to simulate the few-shot learning setting in task-oriented dialog systems. Further, we develop the SC-GPT model. It is pre-trained on a large set of annotated NLG corpus to acquire the controllable generation ability, and fine-tuned with only a few domain-specific labels to adapt to new domains. Experiments on FewShotWoz and the large Multi-Domain-WOZ datasets show that the proposed SC-GPT significantly outperforms existing methods, measured by various automatic metrics and human evaluations.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 28; 2023: 13; 2024: 7; 2025: 5; 2026: 4.

89 papers.

Sort:

By area:

  1. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  2. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 128
  3. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
  4. 2022Language Models with Image Descriptors are Strong Few-Shot Video-Language Learnerscited by 117
  5. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  6. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 97
  7. 2021Dialogue State Tracking with a Language Model using Schema-Driven Promptingcited by 94
  8. 2022MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversationcited by 84
  9. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  10. 2021Mitigating Political Bias in Language Models Through Reinforced Calibrationcited by 73
  11. 2022Description-Driven Task-Oriented Dialog Modelingcited by 50
  12. 2021Shades of BLEU, Flavours of Success: The Case of MultiWOZcited by 48
38 more
  1. 2022Neural Approaches to Conversational Information Retrievalcited by 41
  2. 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
  3. 2021Conversational Question Answering: A Surveycited by 31
  4. 2021CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systemscited by 30
  5. 2021Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translationcited by 29
  6. 2021Speech-language Pre-training for End-to-end Spoken Language Understandingcited by 27
  7. 2022Evaluating Mixed-initiative Conversational Search Systems via User Simulationcited by 24
  8. 2021Pretraining the Noisy Channel Model for Task-Oriented Dialoguecited by 23
  9. 2021Neural Data-to-Text Generation with LM-based Text Augmentationcited by 22
  10. 2022GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformerscited by 22
  11. 2022ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Formatcited by 22
  12. 2022Generative Transformers for Design Concept Generationcited by 21
  13. 2021Improving Compositional Generalization with Self-Training for Data-to-Text Generationcited by 19
  14. 2021TODSum: Task-Oriented Dialogue Summarization with State Trackingcited by 19
  15. 2022Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropizationcited by 19
  16. 2021Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systemscited by 18
  17. 2021Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue Systemcited by 18
  18. 2021AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentationcited by 17
  19. 2021Generative Pre-Trained Transformer for Design Concept Generation: An Explorationcited by 17
  20. 2022Learning Dialogue Representations from Consecutive Utterancescited by 17
  21. 2021Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systemscited by 16
  22. 2021Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setupcited by 16
  23. 2022A Mixture-of-Expert Approach to RL-based Dialogue Managementcited by 16
  24. 2022Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systemscited by 15
  25. 2022Dynamic Dialogue Policy for Continual Reinforcement Learningcited by 12
  26. 2025Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challengescited by 12
  27. 2021Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labelingcited by 11
  28. 2021Generative Conversational Networkscited by 11
  29. 2021Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLGcited by 11
  30. 2021Style Control for Schema-Guided Natural Language Generationcited by 10
  31. 2021Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnosticscited by 9
  32. 2021Generating Personalized Dialogue via Multi-Task Meta-Learningcited by 8
  33. 2021Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledgecited by 8
  34. 2022ProtoSound: A Personalized and Scalable Sound Recognition System for Deaf and Hard-of-Hearing Userscited by 8
  35. 2025ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systemscited by 7
  36. 2023PromptAttack: Probing Dialogue State Trackers with Adversarial Promptscited by 6
  37. 2021Automatically Exposing Problems with Neural Dialog Modelscited by 5
  38. 2021Integrating Pretrained Language Model for Dialogue Policy Learningcited by 5

50 most cited of 89 All 89 (JSON)