Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking
This work addresses the challenge of efficiently training DST models for task-oriented dialogs, offering an incremental improvement by leveraging curriculum and schema structures.
The paper tackles the problem of dialog state tracking (DST) by proposing a schema-aware curriculum learning framework that improves performance over existing models, achieving new state-of-the-art results on WOZ2.0 and MultiWOZ2.1 datasets.
Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset. In this paper, we propose to use curriculum learning (CL) to better leverage both the curriculum structure and schema structure for task-oriented dialogs. Specifically, we propose a model-agnostic framework called Schema-aware Curriculum Learning for Dialog State Tracking (SaCLog), which consists of a preview module that pre-trains a DST model with schema information, a curriculum module that optimizes the model with CL, and a review module that augments mispredicted data to reinforce the CL training. We show that our proposed approach improves DST performance over both a transformer-based and RNN-based DST model (TripPy and TRADE) and achieves new state-of-the-art results on WOZ2.0 and MultiWOZ2.1.