Joint Extraction of Entities and Relations Based on Multi-Scale Information Enhancement

Extracting relational triples from unstructured text is essential for information extraction and knowledge graph construction, but it remains challenging in complex scenarios involving overlapping entities and diverse relational patterns. To address this issue, this paper proposes an Information-Enhanced Multi-Scale Fusion Convolutional Neural Network (EnInfo-Mulscal FCNN) for joint entity–relation extraction. The model uses BERT to obtain contextual representations, predicts candidate relations through multi-label classification, incorporates relation-aware features into entity recognition, and introduces a multi-scale fusion convolutional module and an attention-based entity filtering mechanism to enhance subject–object correspondence modeling. Experiments on the NYT-star and WebNLG datasets demonstrate the effectiveness of the proposed method. Experiments show that EnInfo-Mulscal FCNN achieves precision, recall, and F1-score values of 87.2%, 75.1%, and 80.7% on NYT-star and 86.3%, 88.3%, and 87.3% on WebNLG, respectively. Compared with ETL-span, our model improves the F1-score by 2.7% on NYT-star and 4.2% on WebNLG. Compared with PRE-span, our model improves the F1-score by 4.3%, demonstrating its effectiveness in relational triple extraction. These results indicate that the proposed method improves relational triple extraction by enhancing information in the relation identification, entity recognition, and entity filtering stages, thereby improving triple generation in complex text scenarios.