Industrial information extraction through multi-phase classification using ontology for unstructured documents

Rajbabu, K.; Srinivas, Harshavardhan; Selvaraj, S.

doi:10.1016/j.compind.2018.04.007

Cited by 16 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The other technical method for document analysis is text classification. In [31], text documents in the business domain such as e-mails, office documents, pdf files, etc., are classified using a knowledge base. An additional interesting example of the studies in the industry is resume automation [36] for human resource departments.…”

Section: Information Extractionmentioning

confidence: 99%

Deriving semantic validation rules from industrial standards: An OPC UA study

Bareedu,

Frühwirth,

Niedermeier

et al. 2024

View full text Add to dashboard Cite

Industrial standards provide guidelines for data modeling to ensure interoperability between stakeholders of an industry branch (e.g., robotics). Most frequently, such guidelines are provided in an unstructured format (e.g., pdf documents) which hampers the automated validations of information objects (e.g., data models) that rely on such standards in terms of their compliance with the modeling constraints prescribed by the guidelines. This raises the risk of costly interoperability errors induced by the incorrect use of the standards. There is, therefore, an increased interest in automatic semantic validation of information objects based on industrial standards. In this paper we focus on an approach to semantic validation by formally representing the modeling constraints from unstructured documents as explicit, machine-actionable rules (to be then used for semantic validation) and (semi-)automatically extracting such rules from pdf documents. While our approach aims to be generically applicable, we exemplify an adaptation of the approach in the concrete context of the OPC UA industrial standard, given its large-scale adoption among important industrial stakeholders and the OPC UA internal efforts towards semantic validation. We conclude that (i) it is feasible to represent modeling constraints from the standard specifications as rules, which can be organized in a taxonomy and represented using Semantic Web technologies such as OWL and SPARQL; (ii) we could automatically identify modeling constraints in the specification documents by inspecting the tables ( P = 87 %) and text of these documents (F1 up to 94%); (iii) the translation of the modeling constraints into formal rules could be fully automated when constraints were extracted from tables and required a Human-in-the-loop approach for constraints extracted from text.

show abstract

Section: Information Extractionmentioning

confidence: 99%

Deriving semantic validation rules from industrial standards: An OPC UA study

Bareedu,

Frühwirth,

Niedermeier

et al. 2024

View full text Add to dashboard Cite

show abstract

A task‐centric knowledge graph construction method based on multi‐modal representation learning for industrial maintenance automation

Liu,

2024

Engineering Reports

View full text Add to dashboard Cite

Maintenance manuals are crucial information sources for maintenance and repair. Prior studies explored factual knowledge extraction from textual documents. However, maintenance knowledge in manuals is more task‐centric rather than factual knowledge and often documented in an unstructured Portable Document Format (PDF), posing challenges for knowledge extraction. Addressing this, this research develops effective methods to extract task‐centric maintenance knowledge from unstructured PDF manuals. A new Task‐centric Knowledge Graph (TCKG) schema centralized on maintenance task components (MTCs) is proposed to address the need for structured knowledge representation. A method (Heterogeneous Graph‐based Method, HGM) for knowledge extraction is then proposed, which is enhanced by incorporating visual and spatial information. In the experiments, the proposed HGM exhibits robust performance in the knowledge extraction process, surpassing the baseline Graph‐based Interaction Model with a Tracker (GIT) method in MTCs extraction by 13.3%, and the baseline Translate Embedding (TransE) method in MTCs' relation extraction by 3.8%. A series of ablation studies also prove that including visual and spatial information through the proposed method can improve the relation extraction performance by over 10%. This research supplies valuable insights for future developments in information extraction from maintenance manuals.

show abstract