Recent advances in neural approaches greatly improve task-oriented dialogue (TOD) systems which assist users to accomplish their goals. However, such systems rely on costly manually labeled dialogs which are not available in practical scenarios. In this paper, we present our models for Track 2 of the SereTOD 2022 challenge, which is the first challenge of building semi-supervised and reinforced TOD systems on a large-scale real-world Chinese TOD dataset MobileCS. We build a knowledge-grounded dialog model to formulate dialog history and local KB as input and predict the system response. And we perform semi-supervised pre-training both on the labeled and unlabeled data. Our system achieves the first place both in the automatic evaluation and human interaction, especially with higher BLEU (+7.64) and Success (+13.6\%) than the second place.
@article{arxiv.2210.08873,
title = {Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems},
author = {Weihao Zeng and Keqing He and Zechen Wang and Dayuan Fu and Guanting Dong and Ruotong Geng and Pei Wang and Jingang Wang and Chaobo Sun and Wei Wu and Weiran Xu},
journal= {arXiv preprint arXiv:2210.08873},
year = {2022}
}