Phrase Information Enhanced and Relation Guided Relation Extraction
Expert Systems · 2026-07 · 43 (7)
DOI: 10.1111/exsy.70323 ↗Kurz gefasst
Fachartikel in der Zeitschrift Expert Systems, online erschienen am 04.06.2026. Verfasst von Tiantian Chen und 3 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
Relation extraction, as a crucial component of knowledge engineering, is essential to the automated construction of knowledge‐based expert systems. The existing methods ignore the important phrase information, and other useful information in the sentence is not fully utilised. To address these problems, we propose the phrase information enhanced and relation guided relation extraction, named PIERG. This method uses a multi‐scale convolutional neural network, which is sensitive to local context, to obtain multi‐granularity phrase features, and applies the gating mechanism to filter out the noise information in a sentence and find out the key phrase features that trigger relation types. In addition, an attentional network enhanced by entity pairs and piecewise information is designed to learn more useful information related to relation types. Finally, by calculating the correlation score between the decomposed relation labels and the head entity, the tail entity and the final sentence vector representation, the relation types can be more effectively located. The experiments demonstrate that PIERG can achieve better extraction results than most previous methods. Therefore, PIERG can serve as an effective technical pathway for automated knowledge acquisition and knowledge base filling in expert systems, substantially reducing manual effort in structured knowledge engineering.
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Chen, T., Wang, M., Zhao, Z., & Wang, N. (2026). Phrase Information Enhanced and Relation Guided Relation Extraction. Expert Systems, 43(7). https://doi.org/10.1111/exsy.70323
Vancouver
Chen T, Wang M, Zhao Z, Wang N. Phrase Information Enhanced and Relation Guided Relation Extraction. Expert Systems. 2026;43(7). doi:10.1111/exsy.70323
BibTeX
@article{Chen2026,
author = {Chen, Tiantian and Wang, Meiling and Zhao, Zihao and Wang, Nianbin},
title = {Phrase Information Enhanced and Relation Guided Relation Extraction},
journal = {Expert Systems},
year = {2026},
volume = {43},
number = {7},
doi = {10.1111/exsy.70323}
}
EUVIMED