Figure Descriptive Text Extraction Using Ontological Representation
Conference
·
OSTI ID:1657153
Abstract Experimental research publications provide figure form resources including graphs, charts, and any type of images to effectively support and convey methods and results. To describe figures, authors add captions, which are often incomplete, and more descriptions reside in body text. This work presents a method to extract figure descriptive text from the body of scientific articles. We adopted ontological semantics to aid concept recognition of figure-related information, which generates human- and machine-readable knowledge representations from sentences. Our results show that conceptual models bring an improvement in figure descriptive sentence classification over word-based approaches.
- Research Organization:
- Brookhaven National Laboratory (BNL), Upton, NY (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Advanced Scientific Computing Research (SC-21); Laboratory-Directed Research and Development (LDRD)
- DOE Contract Number:
- SC0012704
- OSTI ID:
- 1657153
- Report Number(s):
- BNL-216329-2020-COPA
- Country of Publication:
- United States
- Language:
- English
Similar Records
Ontological Annotation with WordNet
Automating Ontological Annotation with WordNet
Structure Discovery in Large Semantic Graphs Using Extant Ontological Scaling and Descriptive Statistics
Conference
·
Tue Jun 06 00:00:00 EDT 2006
·
OSTI ID:908503
Automating Ontological Annotation with WordNet
Conference
·
Sat Jan 21 23:00:00 EST 2006
·
OSTI ID:908203
Structure Discovery in Large Semantic Graphs Using Extant Ontological Scaling and Descriptive Statistics
Conference
·
Mon Jul 18 00:00:00 EDT 2011
·
OSTI ID:1092681