首页|A Cascade Dual-Decoder Model for Joint Entity and Relation Extraction

A Cascade Dual-Decoder Model for Joint Entity and Relation Extraction

扫码查看
原文链接
  • NETL
  • NSTL
  • IEEE
In knowledge graph construction, a challenging issue is how to extract complex (e.g., overlapping) entities and relationships from a small amount of unstructured historical data. The traditional pipeline methods are to divide the extraction into two separate subtasks, which misses the potential interactio between the two subtasks and may lead to error propagation. In this work, we propose an effective cascade dual-decoder method to extract overlapping relational triples, which includes a text-specific relation decoder and a relation-corresponded entity decoder. Our approach is straightforward and it includes a text-specific relation decoder and a relation-corresponded entity decoder. The text-specific relation decoder detects relations from a sentence at the text level. That is, it does this according to the semantic information of the whole sentence. For each extracted relation, which is with trainable embedding, the relation-corresponded entity decoder detects the corresponding head and tail entities using a span-based tagging scheme. In this way, the overlapping triple problem can be tackled naturally. We conducted experiments on a real-world open-pit mine dataset and two public datasets to verify the method's generalizability. The experimental results demonstrate the effectiveness and competitiveness of our proposed method and achieve better F1 scores under strict evaluation metrics.

Feature extractionDecodingTailData miningComputational modelingSemanticsTagging

Jian Cheng、Tian Zhang、Shuang Zhang、Huimin Ren、Guo Yu、Xiliang Zhang、Shangce Gao、Lianbo Ma

展开 >

Research Institute of Mine Artificial Intelligence in Chinese Institute of Coal Science, State Key Laboratory of Intelligent Coal Mining and Strata Control, and Tiandi Science and Technology Company Ltd., Beijing, China

College of Software, Northeastern University, Shenyang, China

Institute of Intelligent Manufacturing, Nanjing Tech University, Nanjing, China

School of Intelligent Manufacturing and Control Engineering, Shanghai Polytechnic University, Shanghai, China

Faculty of Engineering, University of Toyama, Toyama-Shi, Japan

College of Software, Northeastern University, Shenyang, China|Foshan Graduate School of Innovation, Northeastern University, Shenyang, China

展开 >

2025

10.1109/TETCI.2024.3406440

IEEE Transactions on Emerging Topics in Computational Intelligence

IEEE Transactions on Emerging Topics in Computational Intelligence

ISSN：
年,卷(期)：2025.9(2)
  • 50