@misc{KochRiehleMueller2024, author = {Koch, Christian and Riehle, Dirk and M{\"u}ller, Katharina}, title = {Schema Inference for Tabular Data with Explainable Artificial Intelligence}, doi = {10.34646/thn/ohmdok-1560}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:92-opus4-15601}, pages = {2 -- 6}, year = {2024}, abstract = {Data engineering is an integral part of the data science process. It comprises tasks such as data ingestion, data transformation, and data quality assurance. In order to fulfill these tasks, schema inference is an important capability. Its goal is to detect the structure of a dataset and to derive metadata on hierarchies, data types, etc. Artificial intelligence (AI) has the potential to automate schema inference and thus increase the efficiency of the data science process. However, as government institutions are subject to special regulations, explainability of AI models can be a mandatory requirement. Goal of this research protocol is to plan a systematic review of literature on schema inference for tabular data with explainable AI (XAI). This third version was derived from two earlier review protocols.}, subject = {Explainable Artificial Intelligence}, language = {en} } @misc{KochRiehle2024, author = {Koch, Christian and Riehle, Dirk}, title = {Schema Inference with Explainable AI for Data Engineering in Government Institutions}, doi = {10.34646/thn/ohmdok-1505}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:92-opus4-15059}, pages = {2 -- 6}, year = {2024}, abstract = {Data engineering is an integral part of the data science process. It comprises tasks such as data ingestion, data transformation, and data quality assurance. In order to fulfill these tasks, schema inference is an important capability. Its goal is to detect the structure of a dataset and to derive metadata on hierarchies, data types, etc. Artificial intelligence (AI) has the potential to automate schema inference and thus increase the efficiency of the data science process. However, as government institutions are subject to special regulations, explainability of AI models can be a mandatory requirement. Goal of this research protocol is to plan a systematic review of literature on schema inference with explainable AI (XAI) for data engineering in government institutions. This second version includes adjustments resulting from the first iteration of the review.}, subject = {Explainable Artificial Intelligence}, language = {en} } @misc{KochRiehle2023, author = {Koch, Christian and Riehle, Dirk}, title = {Schema Inference with Explainable AI for Data Engineering in Government Institutions}, doi = {10.34646/thn/ohmdok-1160}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:92-opus4-11609}, pages = {2 -- 6}, year = {2023}, abstract = {Data engineering is an integral part of the data science process. It comprises tasks such as data ingestion, data transformation, and data quality assurance. In order to fulfill these tasks, schema inference is an important capability. Its goal is to detect the structure of a dataset and to derive metadata on hierarchies, data types, etc. Artificial intelligence (AI) has the potential to automate schema inference and thus increase the efficiency of the data science process. However, as government institutions are subject to special regulations, explainability of AI models can be a mandatory requirement. Goal of this research protocol is to plan a systematic review of literature on schema inference with explainable AI (XAI) for data engineering in government institutions.}, subject = {Explainable Artificial Intelligence}, language = {en} }