DAGOBAH: An end-to-end context-free tabular data semantic annotation system

Chabot, Yoan; Labbé, Thomas; Liu, Jixiong; Troncy, Raphaël
SemTab 2019, Semantic Web Challenge on Tabular Data to Knowledge Graph Matching, collocated with the 18th International Semantic Web Conference, 30 October 2019, Auckland, New Zealand


In this paper, we present the DAGOBAH system which tackles the Tabular Data to Knowledge Graph Matching (TDKGM) challenge3 . DAGOBAH aims to semantically annotate tables with Wikidata and DBpedia entities, and more precisely performs cell and column annotation and relationship identification, via a pipeline starting from pre-processing to enriching an existing knowledge graph using the table information. This paper presents techniques for typing columns with fine-grained concepts while ensuring good coverage, and for valuing these types when disambiguating the cell content. This system obtains promising results in the CEA and CTA tasks on the challenge test datasets.


HAL
Type:
Conférence
City:
Auckland
Date:
2019-10-29
Department:
Data Science
Eurecom Ref:
6082
Copyright:
© Springer. Personal use of this material is permitted. The definitive version of this paper was published in SemTab 2019, Semantic Web Challenge on Tabular Data to Knowledge Graph Matching, collocated with the 18th International Semantic Web Conference, 30 October 2019, Auckland, New Zealand
 and is available at :

PERMALINK : https://www.eurecom.fr/publication/6082