LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training

Autor:	Deng, Shumin, Yang, Jiacheng, Ye, Hongbin, Tan, Chuanqi, Chen, Mosha, Huang, Songfang, Huang, Fei, Chen, Huajun, Zhang, Ningyu
Rok vydání:	2021
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Information Retrieval Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted by IEEE/ACM Transactions on Audio Speech and Language Processing
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2112.01404 Zobrazit plný text záznamu View this record from Arxiv