Semantic Schema Matching for String Attribute with Word Vectors
Kenji Nozaki, Teruhisa Hochin, Hiroki Nomiya · 2019
Instance based schema matching is to determine the correspondences between heterogeneous databases by comparing instances. This process is especially effective when schema information is worthless to detect correspondences. Many previous processes often use schema information and statistics for analyzing correspondences. Heterogeneous databases consist of an enormous number of tables containing various attributes and arise the data heterogeneity. This problem degenerates the schema matching process seriously. Furthermore, these researches describe the need to consider semantic information because of the limitations of matching quality in schema information. In this paper, we propose the instance based schema matching considering attributes' semantics. We used Word2Vec to match attributes of character strings. The result shows a possibility to detect matching between attributes with high semantic similarity.