LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training
arXiv:2112.01404
Abstract
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.
Accepted by IEEE/ACM Transactions on Audio Speech and Language Processing
References in corpus (6)
- Dual Learning for Machine Translation
- KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
- Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
- SentiPrompt: Sentiment Knowledge Enhanced Prompt-Tuning for Aspect-Based Sentiment Analysis
- Self-training Improves Pre-training for Natural Language Understanding
- Uncertainty-aware Self-training for Text Classification with Few Labels