# Few-Shot Structured Policy Learning for Multi-Domain and Multi-Task Dialogues

arXiv: https://arxiv.org/abs/2302.11199 · HTML: https://mlsanity.com/paper/2302.11199/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 22 Feb 2023.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Few-Shot Learning with Graph Neural Networks](https://mlsanity.com/paper/1711.04043/) (2017)
- [MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines](https://mlsanity.com/paper/2007.12720/) (2020)
- [Neural Approaches to Conversational AI](https://mlsanity.com/paper/1809.08267/) (2018)
- [Hierarchical Imitation and Reinforcement Learning](https://mlsanity.com/paper/1803.00590/) (2018)
- [MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation](https://mlsanity.com/paper/2104.00773/) (2021)
- [ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems](https://mlsanity.com/paper/2002.04793/) (2020)
- [MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation](https://mlsanity.com/paper/2010.05594/) (2020)
- [Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation](https://mlsanity.com/paper/2005.07362/) (2020)
- [Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management](https://mlsanity.com/paper/2009.10326/) (2020)
- [Feudal Reinforcement Learning for Dialogue Management in Large Domains](https://mlsanity.com/paper/1803.03232/) (2018)
- [Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1706.06210/) (2017)

## Built on by (most cited first, 1 of 1)

- [Neural Models and Language Model Prompting for the Multidimensional Evaluation of Open-Ended Conversations](https://mlsanity.com/paper/2509.00841/) (2025)

## Abstract (arXiv)

Reinforcement learning has been widely adopted to model dialogue managers in task-oriented dialogues. However, the user simulator provided by state-of-the-art dialogue frameworks are only rough approximations of human behaviour. The ability to learn from a small number of human interactions is hence crucial, especially on multi-domain and multi-task environments where the action space is large. We therefore propose to use structured policies to improve sample efficiency when learning on these kinds of environments. We also evaluate the impact of learning from human vs simulated experts. Among the different levels of structure that we tested, the graph neural networks (GNNs) show a remarkable superiority by reaching a success rate above 80% with only 50 dialogues, when learning from simulated experts. They also show superiority when learning from human experts, although a performance drop was observed, indicating a possible difficulty in capturing the variability of human strategies. We therefore suggest to concentrate future research efforts on bridging the gap between human data, simulators and automatic evaluators in dialogue frameworks.