Ontology-enhanced Prompt-tuning for Few-shot Learning

Abstract

Few-shot Learning (FSL) is aimed to make predictions based on a limited number of samples. Structured data such as knowledge graphs and ontology libraries has been leveraged to benefit the few-shot setting in various tasks. However, the priors adopted by the existing methods suffer from challenging knowledge missing, knowledge noise, and knowledge heterogeneity, which hinder the performance for few-shot learning. In this study, we explore knowledge injection for FSL with pre-trained language models and propose ontology-enhanced prompt-tuning (OntoPrompt). Specifically, we develop the ontology transformation based on the external knowledge graph to address the knowledge missing issue, which fulfills and converts structure knowledge to text. We further introduce span-sensitive knowledge injection via a visible matrix to select informative knowledge to handle the knowledge noise issue. To bridge the gap between knowledge and text, we propose a collective training algorithm to optimize representations jointly. We evaluate our proposed OntoPrompt in three tasks, including relation extraction, event extraction, and knowledge graph completion, with eight datasets. Experimental results demonstrate that our approach can obtain better few-shot performance than baselines.

Accepted by WWW2022

References in corpus (8)

• KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
• PPT: Pre-trained Prompt Tuning for Few-shot Learning
• GDPNet: Refining Latent Multi-View Graph for Relation Extraction
• Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners
• Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification
• Prompt-Learning for Fine-Grained Entity Typing
• Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey
• Learning to Ask for Data-Efficient Event Argument Extraction

Cited by in corpus (6)

• Unifying Large Language Models and Knowledge Graphs: A Roadmap
• From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer
• Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning
• Visual Attention Prompted Prediction and Learning
• APT-Pipe: A Prompt-Tuning Tool for Social Data Annotation using ChatGPT
• A Knowledge-Injected Curriculum Pretraining Framework for Question Answering