mlsanityData to 7 Oct 2026

Continual Learning for Natural Language Generation in Task-oriented Dialog Systems

arXiv 2010.00910 ↗First posted 2 Oct 2020cs.CL cs.LGcited by 47

Not on the map. Why?

Abstract (arXiv)

Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domains. To better fit real-life applications where new data come in a stream, we study NLG in a "continual learning" setting to expand its knowledge to new domains or functionalities incrementally. The major challenge towards this goal is catastrophic forgetting, meaning that a continually trained model tends to forget the knowledge it has learned before. To this end, we propose a method called ARPER (Adaptively Regularized Prioritized Exemplar Replay) by replaying prioritized historical exemplars, together with an adaptive regularization technique based on ElasticWeight Consolidation. Extensive experiments to continually learn new domains and intents are conducted on MultiWoZ-2.0 to benchmark ARPER with a wide range of techniques. Empirical results demonstrate that ARPER significantly outperforms other methods by effectively mitigating the detrimental catastrophic forgetting issue.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 12; 2023: 11; 2024: 10; 2025: 5; 2026: 4.

47 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
  3. 2022Fine-tuned Language Models are Continual Learnerscited by 152
  4. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 60
  5. 2024InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructionscited by 54
  6. 2022Continual Prompt Tuning for Dialog State Trackingcited by 44
  7. 2021Co-Transport for Class-Incremental Learningcited by 38
  8. 2022Deepfake Text Detection: Limitations and Opportunitiescited by 37
  9. 2023Audio-Visual Class-Incremental Learningcited by 33
  10. 2022Continual Sequence Generation with Adaptive Compositional Modulescited by 31
  11. 2021CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systemscited by 30
  12. 2023Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomycited by 24
35 more
  1. 2021Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systemscited by 18
  2. 2022Dynamic Dialogue Policy for Continual Reinforcement Learningcited by 12
  3. 2023Class-Incremental Learning based on Label Generationcited by 11
  4. 2023Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Modelcited by 10
  5. 2023Lifelong Sequence Generation with Dynamic Module Expansion and Adaptationcited by 10
  6. 2021Total Recall: a Customized Continual Learning Method for Neural Semantic Parserscited by 9
  7. 2025Continual Learning for Generative AI: From LLMs to MLLMs and Beyondcited by 9
  8. 2022Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialoguecited by 8
  9. 2025Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgettingcited by 8
  10. 2022Learn from Yesterday: A Semi-Supervised Continual Learning Method for Supervision-Limited Text-to-SQL Task Streamscited by 7
  11. 2023Continual Learning with Dirichlet Generative-based Rehearsalcited by 7
  12. 2024Continual Audio-Visual Sound Separationcited by 7
  13. 2022An Investigation of the Combination of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understandingcited by 5
  14. 2023Domain Incremental Lifelong Learning in an Open Worldcited by 5
  15. 2023Parameterizing Context: Unleashing the Power of Parameter-Efficient Fine-Tuning and In-Context Tuning for Continual Table Semantic Parsingcited by 5
  16. 2024Navigating the Landscape of Large Language Models: A Comprehensive Review and Analysis of Paradigms and Fine-Tuning Strategiescited by 5
  17. 2025Self-Evolving LLMs via Continual Instruction Tuningcited by 4
  18. 2026Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptationcited by 4
  19. 2024Towards Robustness and Diversity: Continual Learning in Dialog Generation with Text-Mixup and Batch Nuclear-Norm Maximizationcited by 3
  20. 2024Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue Systemcited by 3
  21. 2022Unified Question Generation with Continual Lifelong Learningcited by 2
  22. 2023Prompt Pool based Class-Incremental Continual Learning for Dialog State Trackingcited by 2
  23. 2024Gradual Learning: Optimizing Fine-Tuning with Partially Mastered Knowledge in Large Language Modelscited by 2
  24. 2024Continuous Risk Predictioncited by 2
  25. 2026MedCL-Bench: Benchmarking stability-efficiency trade-offs and scaling in biomedical continual learningcited by 2
  26. 2022Semi-Supervised Lifelong Language Learningcited by 1
  27. 2023Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systemscited by 1
  28. 2024Can Similarity-Based Domain-Ordering Reduce Catastrophic Forgetting for Intent Recognition?cited by 1
  29. 2026Sparse Adapter Fusion for Continual Learning in NLPcited by 1
  30. 2022Ask Question First for Enhancing Lifelong Language Learningcited by 0
  31. 2022Continuous QA Learning with Structured Promptscited by 0
  32. 2024Continual Learning of Numerous Tasks from Long-tail Distributionscited by 0
  33. 2025Dynamic Mixture-of-Experts for Incremental Graph Learningcited by 0
  34. 2025Towards Automated Error Discovery: A Study in Conversational AIcited by 0
  35. 2026Impact of enriched meaning representations for language generation in dialogue tasks: A comprehensive exploration of the relevance of tasks, corpora and metricscited by 0