# Dialogue Strategy Adaptation to New Action Sets Using Multi-dimensional Modelling

arXiv: https://arxiv.org/abs/2204.07082 · HTML: https://mlsanity.com/paper/2204.07082/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 14 Apr 2022.

## Builds on (most cited first, 6 of 6)

- [Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systems](https://mlsanity.com/paper/1805.06966/) (2018)
- [AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning](https://mlsanity.com/paper/1905.11259/) (2019)
- [Dialogue manager domain adaptation using Gaussian process reinforcement learning](https://mlsanity.com/paper/1609.02846/) (2016)
- [Action State Update Approach to Dialogue Management](https://mlsanity.com/paper/2011.04637/) (2020)
- [Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling](https://mlsanity.com/paper/1804.00146/) (2018)
- [User Evaluation of a Multi-dimensional Statistical Dialogue System](https://mlsanity.com/paper/1909.02965/) (2019)

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

- [Adversarial learning of neural user simulators for dialogue policy optimisation](https://mlsanity.com/paper/2306.00858/) (2023)

## Abstract (arXiv)

A major bottleneck for building statistical spoken dialogue systems for new domains and applications is the need for large amounts of training data. To address this problem, we adopt the multi-dimensional approach to dialogue management and evaluate its potential for transfer learning. Specifically, we exploit pre-trained task-independent policies to speed up training for an extended task-specific action set, in which the single summary action for requesting a slot is replaced by multiple slot-specific request actions. Policy optimisation and evaluation experiments using an agenda-based user simulator show that with limited training data, much better performance levels can be achieved when using the proposed multi-dimensional adaptation method. We confirm this improvement in a crowd-sourced human user evaluation of our spoken dialogue system, comparing partially trained policies. The multi-dimensional system (with adaptation on limited training data in the target scenario) outperforms the one-dimensional baseline (without adaptation on the same amount of training data) by 7% perceived success rate.