DCoM: A Deep Column Mapper for Semantic Data Type Detection

TL;DR

This paper introduces DCoM, a deep learning model that detects semantic data types directly from raw column data, outperforming traditional methods and previous machine learning approaches.

Contribution

DCoM leverages NLP-based deep neural networks to classify semantic data types from raw data, reducing feature engineering and improving accuracy.

Findings

DCoM achieves higher accuracy than existing methods on VizNet dataset.

The model effectively handles 78 different semantic data types.

Deep neural networks trained on raw data outperform traditional feature-based approaches.

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 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 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 VizNet corpus with 78 different semantic data types. DCoM outperforms other contemporary results with a quite significant margin on the same dataset.