Natural language generation from structured data mainly focuses on surface-level descriptions, suffering from uncontrollable content selection and low fidelity. Previous works leverage logical forms to facilitate logical knowledge-conditioned text generation. Though achieving remarkable progress, they are data-hungry, which makes the adoption for real-world applications challenging with limited data. To this end, this paper proposes a unified framework for logical knowledge-conditioned text generation in the few-shot setting. With only a few seeds logical forms (e.g., 20/100 shot), our approach leverages self-training and samples pseudo logical forms based on content and structure consistency. Experimental results demonstrate that our approach can obtain better few-shot performance than baselines.
@article{arxiv.2112.01404,
title = {LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training},
author = {Shumin Deng and Jiacheng Yang and Hongbin Ye and Chuanqi Tan and Mosha Chen and Songfang Huang and Fei Huang and Huajun Chen and Ningyu Zhang},
journal= {arXiv preprint arXiv:2112.01404},
year = {2023}
}
Comments
Accepted by IEEE/ACM Transactions on Audio Speech and Language Processing