PCRED: Zero-shot Relation Triplet Extraction with Potential Candidate Relation Selection and Entity Boundary Detection
This addresses the problem of extracting relation triplets from text in zero-shot settings for natural language processing applications, offering a more efficient approach than prior methods.
The paper tackles zero-shot relation triplet extraction by proposing PCRED, a method that selects candidate relations and detects entity boundaries without additional training data, achieving state-of-the-art performance on two datasets.
Zero-shot relation triplet extraction (ZeroRTE) aims to extract relation triplets from unstructured texts under the zero-shot setting, where 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. To address the above issues, we propose a novel method named PCRED for ZeroRTE with Potential Candidate Relation Selection and Entity Boundary Detection. The remarkable characteristic of PCRED is that it does not rely on additional data and still achieves promising performance. The model adopts a relation-first paradigm, recognizing unseen relations through candidate relation selection. With 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 results show that our method consistently outperforms previous works. Our code will be available at https://anonymous.4open.science/r/PCRED.