# Dialog State Tracking with Reinforced Data Augmentation

arXiv: https://arxiv.org/abs/1908.07795 · HTML: https://mlsanity.com/paper/1908.07795/

## Key facts

- Cited by 10 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 21 Aug 2019.

## Built on by (most cited first, 10 of 10)

- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [Data Augmentation Approaches in Natural Language Processing: A Survey](https://mlsanity.com/paper/2110.01852/) (2021)
- [Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking](https://mlsanity.com/paper/2106.00291/) (2021)
- [N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking](https://mlsanity.com/paper/2103.00293/) (2021)
- [Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking](https://mlsanity.com/paper/2302.05932/) (2023)
- [Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Tracking](https://mlsanity.com/paper/2405.12468/) (2024)
- [Data Augmentation for Conversational AI](https://mlsanity.com/paper/2309.04739/) (2023)
- [Controllable User Dialogue Act Augmentation for Dialogue State Tracking](https://mlsanity.com/paper/2207.12757/) (2022)
- [More Robust Schema-Guided Dialogue State Tracking via Tree-Based Paraphrase Ranking](https://mlsanity.com/paper/2303.09905/) (2023)
- [Comparing Data Augmentation Methods for End-to-End Task-Oriented Dialog Systems](https://mlsanity.com/paper/2406.06127/) (2024)

## Abstract (arXiv)

Neural dialog state trackers are generally limited due to the lack of quantity and diversity of annotated training data. In this paper, we address this difficulty by proposing a reinforcement learning (RL) based framework for data augmentation that can generate high-quality data to improve the neural state tracker. Specifically, we introduce a novel contextual bandit generator to learn fine-grained augmentation policies that can generate new effective instances by choosing suitable replacements for the specific context. Moreover, by alternately learning between the generator and the state tracker, we can keep refining the generative policies to generate more high-quality training data for neural state tracker. Experimental results on the WoZ and MultiWoZ (restaurant) datasets demonstrate that the proposed framework significantly improves the performance over the state-of-the-art models, especially with limited training data.