mlsanityData to 14 Oct 2026

Sherlock: A Deep Learning Approach to Semantic Data Type Detection

arXiv 1905.10688 ↗First posted 25 May 2019cs.LG cs.DB cs.IRcited by 74

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 74 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 6; 2023: 22; 2024: 8; 2025: 10; 2026: 17.

74 papers.

Sort:

By area:

  1. 2022Fine-tuning language models to find agreement among humans with diverse preferencescited by 189
  2. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 137
  3. 2021TABBIE: Pretrained Representations of Tabular Datacited by 111
  4. 2024CARTE: Pretraining and Transfer for Tabular Learningcited by 76
  5. 2023Table-GPT: Table-tuned GPT for Diverse Table Taskscited by 69
  6. 2021GitTables: A Large-Scale Corpus of Relational Tablescited by 45
  7. 2021Annotating Columns with Pre-trained Language Modelscited by 37
  8. 2023HYTREL: Hypergraph-enhanced Tabular Data Representation Learningcited by 36
  9. 2021LightAutoML: AutoML Solution for a Large Financial Services Ecosystemcited by 32
  10. 2021TCN: Table Convolutional Network for Web Table Interpretationcited by 24
  11. 2023CHORUS: Foundation Models for Unified Data Discovery and Explorationcited by 24
  12. 2023TabLib: A Dataset of 627M Tables with Contextcited by 23
38 more
  1. 2023Towards Cross-Table Masked Pretraining for Web Data Miningcited by 21
  2. 2023Column Type Annotation using ChatGPTcited by 19
  3. 2024SpreadsheetLLM: Encoding Spreadsheets for Large Language Modelscited by 17
  4. 2025TARGET: Benchmarking Table Retrieval for Generative Taskscited by 17
  5. 2022DeepJoin: Joinable Table Discovery with Pre-trained Language Modelscited by 15
  6. 2023ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Modelscited by 15
  7. 2024Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AIcited by 15
  8. 2025MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmarkcited by 14
  9. 2023NameGuess: Column Name Expansion for Tabular Datacited by 13
  10. 2023Observatory: Characterizing Embeddings of Relational Tablescited by 12
  11. 2023LakeBench: Benchmarks for Data Discovery over Data Lakescited by 10
  12. 2023Knowledge Engineering using Large Language Modelscited by 9
  13. 2026Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMscited by 9
  14. 2022AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Taskscited by 8
  15. 2021Auto-Validate: Unsupervised Data Validation Using Data-Domain Patterns Inferred from Data Lakescited by 7
  16. 2025AutoG: Towards automatic graph construction from tabular datacited by 7
  17. 2023DataVinci: Learning Syntactic and Semantic String Repairscited by 6
  18. 2023KAER: A Knowledge Augmented Pre-Trained Language Model for Entity Resolutioncited by 5
  19. 2023Desbordante: from benchmarking suite to high-performance science-intensive data profiler (preprint)cited by 5
  20. 2023Cross Modal Data Discovery over Structured and Unstructured Data Lakescited by 5
  21. 2025Columbo: Expanding Abbreviated Column Names for Tabular Data Using Large Language Modelscited by 5
  22. 2021Auto-Tag: Tagging-Data-By-Example in Data Lakescited by 4
  23. 2023AdaTyper: Adaptive Semantic Column Type Detectioncited by 4
  24. 2021On Automatic Parsing of Log Recordscited by 3
  25. 2023Adversarial Attacks on Tables with Entity Swapcited by 3
  26. 2024Graph Neural Network Approach to Semantic Type Detection in Tablescited by 3
  27. 2024KGLink: A column type annotation method that combines knowledge graph and pre-trained language modelcited by 3
  28. 2021Flexible Table Recognition and Semantic Interpretation Systemcited by 2
  29. 2022Fine-Tuning BERT for Automatic ADME Semantic Labeling in FDA Drug Labeling to Enhance Product-Specific Guidance Assessmentcited by 2
  30. 2023Tab2KG: Semantic Table Interpretation with Lightweight Semantic Profilescited by 2
  31. 2023KGLiDS: A Platform for Semantic Abstraction, Linking, and Automation of Data Sciencecited by 2
  32. 2025Auto-Test: Learning Semantic-Domain Constraints for Unsupervised Error Detection in Tablescited by 2
  33. 2025Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligencecited by 2
  34. 2021Making Table Understanding Work in Practicecited by 1
  35. 2024TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakescited by 1
  36. 2024Gem: Gaussian Mixture Model Embeddings for Numerical Feature Distributionscited by 1
  37. 2025Detection of Personal Data in Structured Datasets Using a Large Language Modelcited by 1
  38. 2025Robust LLM-based Column Type Annotation via Prompt Augmentation with LoRA Tuningcited by 1

50 most cited of 74 All 74 (JSON)