Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking
Yinpei Dai, Hangyu Li, Yongbin Li, Jian Sun, Fei Huang, Luo Si, Xiaodan Zhu
Abstract
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.
BibTeX
@inproceedings{dai-etal-2021-preview,
title = "Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking",
author = "Dai, Yinpei and
Li, Hangyu and
Li, Yongbin and
Sun, Jian and
Huang, Fei and
Si, Luo and
Zhu, Xiaodan",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.111/",
doi = "10.18653/v1/2021.acl-short.111",
pages = "879--885"
}