# Multi-domain Dialog State Tracking using Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1506.07190 · HTML: https://mlsanity.com/paper/1506.07190/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2015.

## Built on by (most cited first, 14 of 14)

- [Multi-Task Learning in Natural Language Processing: An Overview](https://mlsanity.com/paper/2109.09138/) (2021)
- [Slot Self-Attentive Dialogue State Tracking](https://mlsanity.com/paper/2101.09374/) (2021)
- [Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems](https://mlsanity.com/paper/2204.00763/) (2022)
- [A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigms](https://mlsanity.com/paper/2209.06367/) (2022)
- [Diable: Efficient Dialogue State Tracking as Operations on Tables](https://mlsanity.com/paper/2305.17020/) (2023)
- [Intelligent Assistant Language Understanding On Device](https://mlsanity.com/paper/2308.03905/) (2023)
- [Ranking Micro-Influencers: a Novel Multi-Task Learning and Interpretable Framework](https://mlsanity.com/paper/2107.13943/) (2021)
- [An empirical assessment of deep learning approaches to task-oriented dialog management](https://mlsanity.com/paper/2108.03478/) (2021)
- [PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent](https://mlsanity.com/paper/2202.00531/) (2022)
- [A Survey on Conversational Search and Applications in Biomedicine](https://mlsanity.com/paper/2211.15328/) (2022)
- [Utilizing Out-Domain Datasets to Enhance Multi-Task Citation Analysis](https://mlsanity.com/paper/2202.10884/) (2022)
- [Recent Progress in Conversational AI](https://mlsanity.com/paper/2204.09719/) (2022)
- [Design Perspectives of Multitask Deep Learning Models and Applications](https://mlsanity.com/paper/2209.13444/) (2022)
- [Candidate Attended Dialogue State Tracking Using BERT](https://mlsanity.com/paper/2607.16021/) (2026)

## Abstract (arXiv)

Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined domain in mind. This paper shows that dialog data drawn from different dialog domains can be used to train a general belief tracking model which can operate across all of these domains, exhibiting superior performance to each of the domain-specific models. We propose a training procedure which uses out-of-domain data to initialise belief tracking models for entirely new domains. This procedure leads to improvements in belief tracking performance regardless of the amount of in-domain data available for training the model.