NEDORT: a novel and efficient approach to the data overlap problem in relational triples

• Published in: Complex & intelligent systems Vol. 9; no. 5; pp. 5235 - 5250
• Main Authors: Zhang, Zhanjun, Hu, Xiaoru, Zhang, Haoyu, Liu, Jie
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.10.2023; Springer Nature B.V; Springer
• Subjects: Biaffine; Complexity; Computational Intelligence; Data Structures and Information Theory; Design optimization; Differential amplified Multi-head attention; Engineering; Intelligent systems; Matrix representation; Methods; Multilayers; Original Article; Overlapping data; Relation triple extraction; Spatial distribution; U-Net network; Relation triple extraction; Overlapping data; Differential amplified Multi-head attention; Biaffine; U-Net network
• ISSN: 2199-4536; 2198-6053
• DOI: 10.1007/s40747-023-01004-8

Relation triple extraction is a combination of named entity recognition and relation prediction. Early works ignore the problem of data overlap when extracting triples, resulting in poor extraction performance. Subsequent works improve the capability of the model to extract overlapping triples through generative and extractive methods. These works achieve considerable performance but still suffer from some defects, such as poor extraction capability for individual triplets and inappropriate spatial distribution of the data. To solve the above problems, we perform sequence-to-matrix transformation and propose the NEDORT model. NEDORT predicts all subjects in the sentence and then completes the extraction of relation–object pairs. There are overlapping parts between relation–object pairs, so we conduct the conversion of sequence to matrix. We design the Differential Amplified Multi-head Attention method to extract subjects. This method highlights the locations of entities and captures sequence features from multiple dimensions. When performing the extraction of relation–object pairs, we fuse subject and sequence information through the Biaffine method and generate relation–sequence matrices. In addition, we design a multi-layer U-Net network to optimize the matrix representation and improve the extraction performance of the model. Experimental results on two public datasets show that our model outperforms other baseline models on triples of all categories