Abstract
Zero-shot relation triplet extraction (ZeroRTE) aims to extract relation triplets from unstructured texts, while the relation sets at the training and testing stages are disjoint. Previous state-of-the-art method handles this challenging task by leveraging pretrained language models to generate data as additional training samples, which increases the training cost and severely constrains the model performance. We tackle this task from a new perspective and propose a novel method named PCRED for ZeroRTE with Potential Candidate Relation selection and Entity boundary Detection. The model adopts a relation-first paradigm, which firstly recognizes unseen relations through candidate relation selection. By this approach, the semantics of relations are naturally infused in the context. Entities are extracted based on the context and the semantics of relations subsequently. We evaluate our model on two ZeroRTE datasets. The experiment result shows that our method consistently outperforms previous works. Besides, our model does not rely on any additional data, which boasts the advantages of simplicity and effectiveness. Our code is available at https://anonymous.4open.science/r/PCRED.
Abstract (translated)
URL
https://arxiv.org/abs/2211.14477
