mlsanityData to 7 Oct 2026

Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems

arXiv 1905.05644 ↗First posted 14 May 2019cs.CL cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

Natural language generation (NLG) is an essential component of task-oriented dialogue systems. Despite the recent success of neural approaches for NLG, they are typically developed for particular domains with rich annotated training examples. In this paper, we study NLG in a low-resource setting to generate sentences in new scenarios with handful training examples. We formulate the problem from a meta-learning perspective, and propose a generalized optimization-based approach (Meta-NLG) based on the well-recognized model-agnostic meta-learning (MAML) algorithm. Meta-NLG defines a set of meta tasks, and directly incorporates the objective of adapting to new low-resource NLG tasks into the meta-learning optimization process. Extensive experiments are conducted on a large multi-domain dataset (MultiWoz) with diverse linguistic variations. We show that Meta-NLG significantly outperforms other training procedures in various low-resource configurations. We analyze the results, and demonstrate that Meta-NLG adapts extremely fast and well to low-resource situations.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 6; 2023: 9; 2024: 2.

25 papers.

Sort:

By area:

  1. 2023PLACES: Prompting Language Models for Social Conversation Synthesiscited by 72
  2. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  3. 2021CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systemscited by 30
  4. 2022A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learningcited by 30
  5. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  6. 2021Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Maskingcited by 22
  7. 2023Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generationcited by 21
  8. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
  9. 2022Boosting Natural Language Generation from Instructions with Meta-Learningcited by 15
  10. 2021Generative Conversational Networkscited by 11
  11. 2023Meta-Learning with a Geometry-Adaptive Preconditionercited by 11
  12. 2021Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relationscited by 10
13 more
  1. 2022Continued Pretraining for Better Zero- and Few-Shot Promptabilitycited by 10
  2. 2021Generating Personalized Dialogue via Multi-Task Meta-Learningcited by 8
  3. 2022Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitationcited by 8
  4. 2024A New First-Order Meta-Learning Algorithm with Convergence Guaranteescited by 4
  5. 2022Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regressioncited by 2
  6. 2023Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorizationcited by 2
  7. 2023Adapting Knowledge for Few-shot Table-to-Text Generationcited by 2
  8. 2021Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learningcited by 1
  9. 2023Algorithm Design for Online Meta-Learning with Task Boundary Detectioncited by 1
  10. 2023A Unified Framework for Slot based Response Generation in a Multimodal Dialogue Systemcited by 1
  11. 2021Learning to Learn End-to-End Goal-Oriented Dialog From Related Dialog Taskscited by 0
  12. 2021Reinforcement Learning for Few-Shot Text Generation Adaptationcited by 0
  13. 2023A meta learning scheme for fast accent domain expansion in Mandarin speech recognitioncited by 0