Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction
This addresses the challenge of extracting relational triples with limited data, which is incremental as it builds on existing few-shot learning approaches for a more complex task.
The paper tackles the problem of few-shot relational triple extraction, where current methods require large labeled datasets, and proposes a multi-prototype embedding network that bridges text and knowledge to improve performance in this setting.
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.