Skip to main navigation Skip to search Skip to main content

Improving attention network to realize joint extraction for the construction of equipment knowledge graph

  • Xi'an Jiaotong University

Research output: Contribution to journal › Article › peer-review

20 Scopus citations

Abstract

In the context of promoting autonomous decision, intelligent interaction, and concept recognition of the equipment, constructing an equipment Knowledge Graph (KG) is the key technology to facilitate this. In this article, we propose a method that combines design rules and automatic extraction to construct equipment KG from equipment manuals. We define that equipment KG is scheme-based and depicts scheme in the form of KG triples (a.k.a design rules, scheme layer of KG, or concept KG). Our contributions include designing an initial concept KG for the equipment domain and improving the BERT (Bidirectional Encoder Representations from Transformers) model to jointly extract knowledge from texts to enrich the KG. The BERT model was improved from internal calculations so that joint extraction could be achieved directly without extra additional parts. We applied our model to a standard dataset “SemEval2010 Task 8” and achieved the F1 score of 89.55 which demonstrates its rationality. We also established a dataset called “Equipment Manuals Corpus for KG” based on the concept KG and applied the joint model in the dataset to extract knowledge. The result was visualized in the form of a graph.

Original languageEnglish
Article number106723
JournalEngineering Applications of Artificial Intelligence
Volume125
DOIs
StatePublished - Oct 2023

Keywords

  • Concept Knowledge Graph
  • Entity and relation joint extraction
  • Equipment Knowledge Graph
  • Pre-training
  • Self-attention

Fingerprint

Dive into the research topics of 'Improving attention network to realize joint extraction for the construction of equipment knowledge graph'. Together they form a unique fingerprint.

Cite this