# Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules

arXiv: https://arxiv.org/abs/2009.13275 · HTML: https://mlsanity.com/paper/2009.13275/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2020.

## Built on by (most cited first, 4 of 4)

- [A Survey on Neural-symbolic Learning Systems](https://mlsanity.com/paper/2111.08164/) (2021)
- [Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review](https://mlsanity.com/paper/2202.12205/) (2022)
- [Every time I fire a conversational designer, the performance of the dialog system goes down](https://mlsanity.com/paper/2109.13029/) (2021)
- [Zero-shot Classification using Hyperdimensional Computing](https://mlsanity.com/paper/2401.16876/) (2024)

## Abstract (arXiv)

In this work, we present a framework for incorporating descriptive logical rules in state-of-the-art neural networks, enabling them to learn how to handle unseen labels without the introduction of any new training data. The rules are integrated into existing networks without modifying their architecture, through an additional term in the network's loss function that penalizes states of the network that do not obey the designed rules. As a case of study, the framework is applied to an existing neural-based Dialog State Tracker. Our experiments demonstrate that the inclusion of logical rules allows the prediction of unseen labels, without deteriorating the predictive capacity of the original system.