EmbNum: Semantic labeling for numerical values with deep metric learning

Semantic labeling is a task of matching unknown data source to labeled data sources. The semantic labels could be properties, classes in knowledge bases or labeled data are manually annotated by domain experts. In this paper, we present EmbNum, a novel approach to match numerical columns from different table data sources. We use a representation network architecture consisting of triplet network and convolutional neural network to learn a mapping function from numerical columns to a transformed space. In this space, the Euclidean distance can be used to measure "semantic similarity" of two columns. Our experiments on City-Data and Open-Data demonstrate that EmbNum achieves considerable improvements in comparison with the state-of-the-art methods on effectiveness and efficiency.