Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing Industry

Causal domain knowledge is commonly documented using natural language either in unstructured or semi-structured forms. This study aims to increase the usability of causal domain knowledge in industrial documents by transforming the information into a more structured format. The paper presents our wo...

Full description

Saved in:
Bibliographic Details
Main Authors: Houssam Razouk, Leonie Benischke, Daniel Gärber, Roman Kern
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/5/2573
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850226199925620736
author Houssam Razouk
Leonie Benischke
Daniel Gärber
Roman Kern
author_facet Houssam Razouk
Leonie Benischke
Daniel Gärber
Roman Kern
author_sort Houssam Razouk
collection DOAJ
description Causal domain knowledge is commonly documented using natural language either in unstructured or semi-structured forms. This study aims to increase the usability of causal domain knowledge in industrial documents by transforming the information into a more structured format. The paper presents our work on developing automated methods for causal information extraction from real-world industrial documents in the semiconductor manufacturing industry, including presentation slides and FMEA (Failure Mode and Effects Analysis) documents. Specifically, we evaluate two types of causal information extraction methods: single-stage sequence tagging (SST) and multi-stage sequence tagging (MST). The presented case study showcases that the proposed MST methods for extracting causal information from industrial documents are suitable for practical applications, especially for semi-structured documents such as FMEAs, with a 93% F1 score. Additionally, the study shows that extracting causal information from presentation slides is more challenging. The study highlights the importance of choosing a language model that is more aligned with the domain and in-domain pre-training.
format Article
id doaj-art-ff2e03c422cc4e4abc0f3af71bb1d0cd
institution OA Journals
issn 2076-3417
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-ff2e03c422cc4e4abc0f3af71bb1d0cd2025-08-20T02:05:08ZengMDPI AGApplied Sciences2076-34172025-02-01155257310.3390/app15052573Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing IndustryHoussam Razouk0Leonie Benischke1Daniel Gärber2Roman Kern3Infineon Technologies Austria AG, 9500 Villach, AustriaInfineon Technologies Austria AG, 9500 Villach, AustriaInstitute of Machine Learning and Neural Computation, Graz University of Technology, 8010 Graz, AustriaInstitute of Machine Learning and Neural Computation, Graz University of Technology, 8010 Graz, AustriaCausal domain knowledge is commonly documented using natural language either in unstructured or semi-structured forms. This study aims to increase the usability of causal domain knowledge in industrial documents by transforming the information into a more structured format. The paper presents our work on developing automated methods for causal information extraction from real-world industrial documents in the semiconductor manufacturing industry, including presentation slides and FMEA (Failure Mode and Effects Analysis) documents. Specifically, we evaluate two types of causal information extraction methods: single-stage sequence tagging (SST) and multi-stage sequence tagging (MST). The presented case study showcases that the proposed MST methods for extracting causal information from industrial documents are suitable for practical applications, especially for semi-structured documents such as FMEAs, with a 93% F1 score. Additionally, the study shows that extracting causal information from presentation slides is more challenging. The study highlights the importance of choosing a language model that is more aligned with the domain and in-domain pre-training.https://www.mdpi.com/2076-3417/15/5/2573causal information extractioncausal relation extractionnatural language processingpresentation slidesFMEAsemiconductor manufacturing
spellingShingle Houssam Razouk
Leonie Benischke
Daniel Gärber
Roman Kern
Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing Industry
Applied Sciences
causal information extraction
causal relation extraction
natural language processing
presentation slides
FMEA
semiconductor manufacturing
title Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing Industry
title_full Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing Industry
title_fullStr Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing Industry
title_full_unstemmed Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing Industry
title_short Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing Industry
title_sort increasing the accessibility of causal domain knowledge via causal information extraction methods a case study in the semiconductor manufacturing industry
topic causal information extraction
causal relation extraction
natural language processing
presentation slides
FMEA
semiconductor manufacturing
url https://www.mdpi.com/2076-3417/15/5/2573
work_keys_str_mv AT houssamrazouk increasingtheaccessibilityofcausaldomainknowledgeviacausalinformationextractionmethodsacasestudyinthesemiconductormanufacturingindustry
AT leoniebenischke increasingtheaccessibilityofcausaldomainknowledgeviacausalinformationextractionmethodsacasestudyinthesemiconductormanufacturingindustry
AT danielgarber increasingtheaccessibilityofcausaldomainknowledgeviacausalinformationextractionmethodsacasestudyinthesemiconductormanufacturingindustry
AT romankern increasingtheaccessibilityofcausaldomainknowledgeviacausalinformationextractionmethodsacasestudyinthesemiconductormanufacturingindustry