Affiliations: [a] Department of Artificial Intelligence, Universidad Politécnica de Madrid, 28223, Madrid, Spain. E-mails: aalobaid@fi.upm.es, ocorcho@fi.upm.es | [b] Department of Electronics and Computer Science, University of Southampton, UK. E-mail: e.kacprzak@soton.ac.uk
Abstract: A lot of tabular data are being published on the Web. Semantic labeling of such data may help in their understanding and exploitation. However, many challenges need to be addressed to do this automatically. With numbers, it can be even harder due to the possible difference in measurement accuracy, rounding errors, and even the frequency of their appearance. Multiple approaches have been proposed in the literature to tackle the problem of semantic labeling of numeric values in existing tabular datasets. However, they also suffer from several shortcomings: closely coupled with entity-linking, rely on table context, need to profile the knowledge graph, and require manual training of the model. Above all, however, they all treat different types of numeric values evenly. In this paper, we tackle these problems and validate our hypothesis: whether taking into account the typology of numeric data in semantic labeling yields better results.
Keywords: Semantic labeling, semantic annotation, levels of measurements, typology of numbers, fuzzy clustering, Semantic Web
DOI: 10.3233/SW-200397
Journal: Semantic Web, vol. 12, no. 1, pp. 5-20, 2021
