This is not the latest version of this item. The latest version can be found here.
Sherlock: A Deep Learning Approach to Semantic Data Type Detection
Name
1905.10688.pdf
Description
Submitted version
Size
2.21 MB
Format
Adobe PDF
Checksum (MD5)
54e98423eca623a27288a4a1c3af213e
Author(s)
Hulsebos, Madelon
Hu, Kevin
Bakker, Michiel
Zgraggen, Emanuel
Satyanarayan, Arvind
Kraska, Tim
Demiralp, Çagatay
Hidalgo, César
Journal
Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Publisher
Association for Computing Machinery (ACM)
Version
Original manuscript
Abstract
© 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM. Correctly detecting the semantic type of data columns is crucial for data science tasks such as automated data cleaning, schema matching, and data discovery. Existing data preparation and analysis systems rely on dictionary lookups and regular expression matching to detect semantic types. However, these matching-based approaches often are not robust to dirty data and only detect a limited number of types. We introduce Sherlock, a multi-input deep neural network for detecting semantic types. We train Sherlock on 686, 765 data columns retrieved from the VizNet corpus by matching 78 semantic types from DBpedia to column headers. We characterize each matched column with 1, 588 features describing the statistical properties, character distributions, word embeddings, and paragraph vectors of column values. Sherlock achieves a support-weighted F1 score of 0.89, exceeding that of machine learning baselines, dictionary and regular expression benchmarks, and the consensus of crowdsourced annotations.
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
10.1145/3292500.3330993
