Systematic Literature Review on Neuro-Symbolic AI in Knowledge Graph Construction for Manufacturing

Tracking #: 3718-4932

This paper is currently under review
Authors: 
Wilma Schmidt
Diego Rincon-Yanez
Evgeny Kharlamov1
Adrian Paschke1

Responsible editor: 
Guest Editors KG Construction 2024

Submission type: 
Survey Article
Abstract: 
Numerous digitization initiatives and activities in manufacturing led to an enormous increase in available and accessible data. Knowledge graphs (KGs) become increasingly popular in this domain as they show strengths in integrating different data sources and serve as a basis for further downstream tasks.Yet, constructing aKGis still a challenging and time consuming process. Neuro-symbolic AI approaches have shown promising potentials in research and industry and can support KG construction. Nevertheless, KG construction with neural methods must be aware of, or ideally even handle, the inexplicability of results when applying the KG on further downstream tasks in manufacturing, e.g. on tasks of reliability- or safety-relevance. This makes it interesting to evaluate the utilization of neuro-symbolic AI approaches in KG construction in manufacturing. To the best of our knowledge, there is no systematic literature research on the review of neuro-symbolic AI in KGs in manufacturing, yet. Hence, this paper conducts a systematic literature review on neuro-symbolic AI approaches in KG construction in Smart Manufacturing. We show a continued increase in both overall publications on Manufacturing KG construction as well as especially on neural methods in these constructions.We further showthat BERT embeddings, RNN encodings, especially BiLSTM, and CRF decodings are common components of knowledge extraction from unstructured text documents to build KGs in manufacturing. With this systematic review we support both further research as well as industry application in this field. The main question to guide this review is “Which role play neuro-symbolic AI approaches in knowledge graph construction for Manufacturing?”.
Full PDF Version: 
Tags: 
Under Review