The Artificial Intelligence for Data Analytics (AIDA) project aims at applying new advances in AI and machine learning to address data wrangling issues, and help to automate the data analytics process. Semantic Web technologies have the potential of contributing in the Data Science pipeline by providing a more complete (semantic) understanding of the data.
-
Embedding the Semantics of Tabular Data (sources in this project).
-
Tabular Data Semantics. Auxiliary classes to access DBpedia, Wikidata and Google's KG for Web table matching. (gihub-java) (github-python)
-
Data integration and Knowledge Graphs at the Norwegian Institute for Water Research: https://github.com/NIVA-Knowledge-Graph/
-
SemTab: Semantic Web Challenge on Tabular Data to Knowledge Graph Matching. This challenge is collocated with the International Semantic Web Conference (ISWC) and the International Workshop on Ontology Matching (OM).
- Ernesto Jimenez-Ruiz, Oktie Hassanzadeh, Vasilis Efthymiou, Jiaoyan Chen, Kavitha Srinivas. SemTab 2019: Resources to Benchmark Tabular Data to Knowledge Graph Matching Systems. In the 17th Extended Semantic Web Conference, ESWC 2020. (pre-print)
- Jiaoyan Chen, Ernesto Jimenez-Ruiz, Ian Horrocks, Charles Sutton. Learning Semantic Annotations for Tabular Data. In the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. (arXiv) (proceedings)
- Jiaoyan Chen, Ernesto Jimenez-Ruiz, Ian Horrocks, Charles Sutton. ColNet: Embedding the Semantics of Web Tables for Column Type Prediction. In the 33rd AAAI Conference on Artificial Intelligence. AAAI 2019. (arXiv) (proceedings) (Slides) (Slides extended).
- Erik Bryhn Myklebust, Ernesto Jimenez-Ruiz, Jiaoyan Chen, Raoul Wolf and Knut-Erik Tollefsen. Knowledge Graph Embedding for Ecotoxicological Effect Prediction. In The Semantic Web – ISWC 2019. (pdf) (Repository) (Slides).
This work is supported by the AIDA project (UK Government's Defence & Security Programme in support of the Alan Turing Institute), and the SIRIUS Centre for Scalable Data Access (Research Council of Norway, project 237889).