Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction
arXiv:2010.16059
Abstract
Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings. However, people can grasp new knowledge by learning a few instances. To this end, we take the first step to study the few-shot relational triple extraction, which has not been well understood. Unlike previous single-task few-shot problems, relational triple extraction is more challenging as the entities and relations have implicit correlations. In this paper, We propose a novel multi-prototype embedding network model to jointly extract the composition of relational triples, namely, entity pairs and corresponding relations. To be specific, we design a hybrid prototypical learning mechanism that bridges text and knowledge concerning both entities and relations. Thus, implicit correlations between entities and relations are injected. Additionally, we propose a prototype-aware regularization to learn more representative prototypes. Experimental results demonstrate that the proposed method can improve the performance of the few-shot triple extraction.
accepted at COLING 2020
References in corpus (7)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Few-shot classification in Named Entity Recognition Task
- Finding Influential Instances for Distantly Supervised Relation Extraction
- Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward
- The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis
- Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network
- On Robustness and Bias Analysis of BERT-based Relation Extraction