DCoM: A Deep Column Mapper for Semantic Data Type Detection

Subhadip Maji, Swapna sourav Rout, Sudeep Choudhary

Keywords: Semantic Data Type Detection, Machine Learning, Natural Language Processing, Semantic Column Tagging, Sensitive Data Detection, Column Search

Abstract: Detection of semantic data types is a very crucial task in data science for automated data cleaning, schema matching, data discovery, semantic data type normalization and sensitive data identification. Existing methods include regular expression-based or dictionary lookup-based methods that are not robust to dirty as well unseen data and are limited to a very less number of semantic data types to predict. Existing Machine Learning methods extract a large number of engineered features from data and build logistic regression, random forest or feedforward neural network for this purpose. In this paper, we introduce DCoM, a collection of multi-input NLP-based deep neural networks to detect semantic data types where instead of extracting a large number of features from the data, we feed the raw values of columns (or instances) to the model as texts. We train DCoM on 686,765 data columns extracted from the VizNet corpus with 78 different semantic data types. DCoM outperforms other contemporary results with a quite significant margin on the same dataset achieving a support-weighted F1 score of 0.925.

One-sentence Summary: This paper introduces a novel NLP-based approach to automatically detect the semantic type data i.e. prediction of column headers given the column values.