- Titel
- Automatic Information Extraction from Scientific Publications Based on the Use Case of Additive Manufacturing
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa2-1005228
- Quellenangabe
- Applied Sciences
Erscheinungsjahr: 2025
Jahrgang: 15
Heft: 17
E-ISSN: 2076-3417
Artikelnummer: 9331 - Erstveröffentlichung
- 2025
- Abstract (EN)
- A systematic literature review is fundamental to building a robust research foundation, informing experimental methodology, and ensuring the quality of future scientific output. However, manual extraction of targeted information from scientific publications is often laborious and prone to error, especially when researchers require rapid access to relevant findings without specialized hardware. This paper introduces an automated workflow for information extraction from scientific publications in the engineering domain. The proposed workflow consists of two primary stages: data preparation and information extraction. During data preparation, PDF files are converted to plain text and segmented into logical sections using a rule-based block detection and classification algorithm for keeping semantics. Information extraction is then performed by applying regular expressions both on keys and values in the same sentence to identify and extract relevant process and material data from the segmented text. The approach was evaluated on a dataset of 18 open-access scientific publications from various journals and conference proceedings in the AM domain. The results of the automated extraction were compared with manual extraction and with a modern large language model (LLM)-based approach. The findings demonstrate that the proposed workflow can accurately and efficiently extract relevant process and material data, achieving competitive performance relative to the LLM-based method. The workflow offers a significant reduction in time and potential errors associated with manual extraction, with automated processing averaging 15 seconds per document compared to one hour for manual extraction, and achieving a 76% match rate. This efficiency enables researchers to rapidly and effectively extract data. The methodology is readily transferable to other scientific fields where systematic literature reviews and structured data extraction are required.
- Andere Ausgabe
- Link zum Artikel, der zuerst in der Zeitschrift „Applied sciences” im Verlag MDPI erschienen ist.
DOI: 10.3390/app15179331 - Freie Schlagwörter (DE)
- Automatische Extraktion, Literaturrecherche, Wissenschaftliche Publikationen, Informationsextraktion, Text Mining, PDF-Format, Additive Fertigung
- Freie Schlagwörter (EN)
- Automatic Extraction, Literature Research, Scientific Publications, Information Extraction, Text Mining, PDF Format, Additive Manufacturing
- Klassifikation (DDC)
- 600
- Verlag
- MDPI, Basel
- Förder- / Projektangaben
- Sächsisches Staatsministerium für Wissenschaft, Kultur und Tourismus (SMWK)
Europäischen Fonds für regionale Entwicklung (EFRE)
Datengetriebene Prozess-, Werkstoff- und Strukturanalyse für die Additive Fertigung
(AMTwin)
ID: 100373343, 100373343 - Bundesministerium für Wirtschaft und Klimaschutz (BMWK)
Vom konventionellen Produktionswerk zum resilienten Kompetenz-Werk durch Industrie 4.0
(Werk 4.0)
ID: 13IK022K - Version / Begutachtungsstatus
- publizierte Version / Verlagsversion
- URN Qucosa
- urn:nbn:de:bsz:14-qucosa2-1005228
- Veröffentlichungsdatum Qucosa
- 26.11.2025
- Dokumenttyp
- Artikel
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis
CC BY 4.0