Dialog State Tracking with Reinforced Data Augmentation

By Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Qun Liu. 2019

25 citations recorded by the source corpus.

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 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.

Subfields: Artificial Intelligence, Reinforcement Learning, Dialogue & Conversational AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yichi Zhang
2. Zhou Yu
3. Fei Huang
4. Silin Gao
5. Zhijian Ou
6. Xiao-Dan Zhu
7. Luo Si
8. Hangyu Li

In Reinforcement Learning

1. Zhou Yu
2. Xiao-Dan Zhu
3. Wanxiang Che
4. Yichi Zhang

In Dialogue & Conversational AI

1. Zhou Yu

Citations in the corpus

• Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking (2021, background): “There are also many works (Hou et al., 2018; Yoo et al., 2020; Yin et al., 2020) on dialog augmentation.”
• Paraphrase Augmented Task-Oriented Dialog Generation (2020, methodology): “• TextSub denotes the text span replacement method proposed by Yin et al. (2019).”
• Data Augmentation Approaches in Natural Language Processing: A Survey (2021, methodology): “[76] use two kinds of rules including symmetric consistency and transitive consistency, as well as logic-guided DA methods to generate DA samples.”