TY  - CONF
A1  - Zia, Ghezal Ahmad Jan
A1  - Valdestilhas, Andre
A1  - Moreno Torres, Benjami
A1  - Kruschwitz, Sabine
T1  - Leveraging large language models for automated knowledge graphs generation in non-destructive testing
T2  - SeMatS 2024 - Proceedings of the first international workshop on semantic materials science: Harnessing the power of semantic web technologies in materials science
N2  - This paper presents an innovative approach for the automatic generation of Knowledge Graphs (KGs) from heterogeneous scientific articles in the domain of Non-Destructive Testing (NDT) applied to building materials.

Our methodology leverages large language models (LLMs) to extract and semantically relate concepts from diverse sources. We developed material-specific agents for concrete, wood, steel, and bricks, each equipped with a curated glossary of terms to ensure domain accuracy. These agents process PDF documents, extracting relevant information on deterioration mechanisms, physical changes, and applicable NDT methods. The extracted data is then normalized, validated, and structured into a Neo4j graph database, forming a comprehensive KG. Our results demonstrate the system’s ability to automatically discover and represent intricate relationships between materials, deterioration mechanisms, physical changes, and NDT techniques. The generated KG successfully captures complex interactions, such as the applicability of specific NDT methods to various materials under different deterioration conditions. This work not only highlights the potential of KGs in enhancing knowledge discovery and representation in NDT research but also provides a scalable framework for extending this approach to other scientific domains.
T2  - SeMatS 2024 - The 1st International Workshop on Semantic Materials Science
CY  - Amsterdam, The Netherlands
DA  - 17.09.2024
KW  - Materials science and engineering
KW  - Large language model
KW  - Linked open data
KW  - Data interoperability
KW  - RDF
KW  - Semantic web
PY  - 2024
UR  - https://nbn-resolving.org/urn:nbn:de:kobv:b43-624597
DO  - https://doi.org/10.5281/zenodo.13834164
SN  - 1613-0073
N1  - Serientitel: CEUR workshop proceedings – Series title: CEUR workshop proceedings
VL  - 3760
SP  - 101
EP  - 110
PB  - RWTH Aachen
CY  - Aachen
AN  - OPUS4-62459
LA  - eng
AD  - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany
ER  -