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

arXiv: https://arxiv.org/abs/1905.05644 · HTML: https://mlsanity.com/paper/1905.05644/

## Key facts

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

## Built on by (most cited first, 25 of 25)

- [PLACES: Prompting Language Models for Social Conversation Synthesis](https://mlsanity.com/paper/2302.03269/) (2023)
- [Advances and Challenges in Meta-Learning: A Technical Review](https://mlsanity.com/paper/2307.04722/) (2023)
- [CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems](https://mlsanity.com/paper/2109.04645/) (2021)
- [A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning](https://mlsanity.com/paper/2202.13675/) (2022)
- [Meta Learning for Natural Language Processing: A Survey](https://mlsanity.com/paper/2205.01500/) (2022)
- [Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking](https://mlsanity.com/paper/2107.08173/) (2021)
- [Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation](https://mlsanity.com/paper/2310.08395/) (2023)
- [Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy](https://mlsanity.com/paper/2406.16087/) (2024)
- [Boosting Natural Language Generation from Instructions with Meta-Learning](https://mlsanity.com/paper/2210.11617/) (2022)
- [Generative Conversational Networks](https://mlsanity.com/paper/2106.08484/) (2021)
- [Meta-Learning with a Geometry-Adaptive Preconditioner](https://mlsanity.com/paper/2304.01552/) (2023)
- [Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations](https://mlsanity.com/paper/2106.12384/) (2021)
- [Continued Pretraining for Better Zero- and Few-Shot Promptability](https://mlsanity.com/paper/2210.10258/) (2022)
- [Generating Personalized Dialogue via Multi-Task Meta-Learning](https://mlsanity.com/paper/2108.03377/) (2021)
- [Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation](https://mlsanity.com/paper/2203.11670/) (2022)
- [A New First-Order Meta-Learning Algorithm with Convergence Guarantees](https://mlsanity.com/paper/2409.03682/) (2024)
- [Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regression](https://mlsanity.com/paper/2209.13410/) (2022)
- [Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorization](https://mlsanity.com/paper/2302.04415/) (2023)
- [Adapting Knowledge for Few-shot Table-to-Text Generation](https://mlsanity.com/paper/2302.12468/) (2023)
- [Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning](https://mlsanity.com/paper/2110.08254/) (2021)
- [Algorithm Design for Online Meta-Learning with Task Boundary Detection](https://mlsanity.com/paper/2302.00857/) (2023)
- [A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System](https://mlsanity.com/paper/2305.17433/) (2023)
- [Learning to Learn End-to-End Goal-Oriented Dialog From Related Dialog Tasks](https://mlsanity.com/paper/2110.15724/) (2021)
- [Reinforcement Learning for Few-Shot Text Generation Adaptation](https://mlsanity.com/paper/2111.11030/) (2021)
- [A meta learning scheme for fast accent domain expansion in Mandarin speech recognition](https://mlsanity.com/paper/2307.12262/) (2023)

## 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.