Parsing Causal Models – An Instance Segmentation Approach
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Standard
Intelligent Information Systems - CAiSE Forum 2023, Proceedings. ed. / Cristina Cabanillas; Francisca Pérez. Springer Science and Business Media Deutschland GmbH, 2023. p. 43-51 (Lecture Notes in Business Information Processing; Vol. 477 LNBIP).
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - Parsing Causal Models – An Instance Segmentation Approach
AU - Scharfenberger, Jonas
AU - Funk, Burkhardt
N1 - Conference code: 35
PY - 2023/6/8
Y1 - 2023/6/8
N2 - The steadily growing number of publications in the field of information systems as well as the confusion arising from the naming of theoretical concepts, complicate the process of literature reviewing. While several knowledge repositories and databases are developed to combat this issue, a considerable amount of manual effort to populate the databases is required. The information these tools seek to present is often compactly summarized in causal models with a graph-like structure (e.g., structural equation models). Our work aims to develop a graph parsing method that reduces the amount of manual effort required and thus builds a foundation towards an augmentation of knowledge extraction from causal models. We contribute to the ongoing efforts in developing graph parsing tools by proposing a novel instance segmentation-based approach that leverages a new method to generate annotated synthetic graph images. Our solution is evaluated on a dataset of 166 images of structural equation models and outperforms existing graph parsing approaches in this use case.
AB - The steadily growing number of publications in the field of information systems as well as the confusion arising from the naming of theoretical concepts, complicate the process of literature reviewing. While several knowledge repositories and databases are developed to combat this issue, a considerable amount of manual effort to populate the databases is required. The information these tools seek to present is often compactly summarized in causal models with a graph-like structure (e.g., structural equation models). Our work aims to develop a graph parsing method that reduces the amount of manual effort required and thus builds a foundation towards an augmentation of knowledge extraction from causal models. We contribute to the ongoing efforts in developing graph parsing tools by proposing a novel instance segmentation-based approach that leverages a new method to generate annotated synthetic graph images. Our solution is evaluated on a dataset of 166 images of structural equation models and outperforms existing graph parsing approaches in this use case.
KW - Graph parsing
KW - Instance segmentation
KW - Structural equation models
KW - Synthetic data
KW - Informatics
KW - Business informatics
UR - http://www.scopus.com/inward/record.url?scp=85163957389&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/a618afd7-de24-3150-ba45-89440ce6ca2f/
U2 - 10.1007/978-3-031-34674-3_6
DO - 10.1007/978-3-031-34674-3_6
M3 - Article in conference proceedings
AN - SCOPUS:85163957389
SN - 978-3-031-34673-6
T3 - Lecture Notes in Business Information Processing
SP - 43
EP - 51
BT - Intelligent Information Systems - CAiSE Forum 2023, Proceedings
A2 - Cabanillas, Cristina
A2 - Pérez, Francisca
PB - Springer Science and Business Media Deutschland GmbH
T2 - 35th International Conference on Advanced Information Systems Engineering - CAiSE 2023
Y2 - 12 June 2023 through 16 June 2023
ER -