The training of spoken language understanding (SLU) models often faces the problem of data scarcity. In this paper, we put forward a data augmentation method using pretrained language models to boost the variability and accuracy of generated utterances. Furthermore, we investigate and propose solutions to two previously overlooked semi-supervised learning scenarios of data scarcity in SLU: i) Rich-in-Ontology: ontology information with numerous valid dialogue acts is given; ii) Rich-in-Utterance: a large number of unlabelled utterances are available. Empirical results show that our method can produce synthetic training data that boosts the performance of language understanding models in various scenarios.
@article{arxiv.2004.13952,
title = {Data Augmentation for Spoken Language Understanding via Pretrained Language Models},
author = {Baolin Peng and Chenguang Zhu and Michael Zeng and Jianfeng Gao},
journal= {arXiv preprint arXiv:2004.13952},
year = {2021}
}