Full text
|
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (285kB) | Preview |
Alobaid, Ahmad and Corcho, Oscar (2018). Fuzzy Semantic Labeling of Semi-structured Numerical Datasets. In: "European Knowledge Acquisition Workshop EKAW 2018", 12 - 16 Nov. 2018, Nancy - France. ISBN 978-3-030-03666-9. pp. 19-33. https://doi.org/10.1007/978-3-030-03667-6_2.
Title: | Fuzzy Semantic Labeling of Semi-structured Numerical Datasets |
---|---|
Author/s: |
|
Item Type: | Presentation at Congress or Conference (Article) |
Event Title: | European Knowledge Acquisition Workshop EKAW 2018 |
Event Dates: | 12 - 16 Nov. 2018 |
Event Location: | Nancy - France |
Title of Book: | European Knowledge Acquisition Workshop EKAW 2018 |
Date: | 2018 |
ISBN: | 978-3-030-03666-9 |
Volume: | 11313 |
Subjects: | |
Faculty: | E.T.S. de Ingenieros Informáticos (UPM) |
Department: | Inteligencia Artificial |
UPM's Research Group: | Ontology Engineering Group OEG |
Creative Commons Licenses: | None |
![]() | There is a more recent version of this electronic publication. Click here to see it. |
|
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (285kB) | Preview |
SPARQL endpoints provide access to rich sources of data (e.g. knowledge graphs), which can be used to classify other less structured datasets (e.g. CSV files or HTML tables on the Web). We propose an approach to suggest types for the numerical columns of a collection of input files available as CSVs. Our approach is based on the application of the fuzzy c-means clustering technique to numerical data in the input files, using existing SPARQL endpoints to generate training datasets. Our approach has three major advantages: it works directly with live knowledge graphs, it does not require knowledge-graph profiling beforehand, and it avoids tedious and costly manual training to match values with types. We evaluate our approach against manually annotated datasets. The results show that the proposed approach classifies most of the types correctly for our test sets.
Item ID: | 56252 |
---|---|
DC Identifier: | http://oa.upm.es/56252/ |
OAI Identifier: | oai:oa.upm.es:56252 |
DOI: | 10.1007/978-3-030-03667-6_2 |
Official URL: | https://link.springer.com/chapter/10.1007/978-3-030-03667-6_2 |
Deposited by: | Ahmad Alobaid |
Deposited on: | 02 Sep 2019 05:39 |
Last Modified: | 02 Sep 2019 05:39 |