Watchog: A Light-weight Contrastive Learning based Framework for Column Annotation

Summary: Watchog uses contrastive learning on an unlabeled table corpus to yield robust representations for column annotation with few labels. Semi-supervised optimizations mitigate imbalance, delivering Micro/Macro F1 gains on semantic-type detection. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 6835
Venue: SIGMOD
Year: 2023
Pagerank: 5.3564029e-05
Overall Rank: 8,860 | 39.22%
DOI: 10.1145/3626766

Incoming Non-self Citations Over Time

Authors

1. Zhengjie Miao (Megagon Labs)
2. Jin Wang (Megagon Labs)

BibTeX Citation

@inproceedings{miao_sigmod23,
        title = {{Watchog: A Light-weight Contrastive Learning based Framework for Column Annotation}},
        author = {Miao, Zhengjie and Wang, Jin},
        series = {{SIGMOD} '23},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3626766},
        url = {https://dl.acm.org/doi/10.1145/3626766},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 4 of 4 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
9,972	Cents: A Flexible and Cost-Effective Framework for LLM-Based Table Understanding	2025	VLDB	5.1845938e-05
10,399	Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations	2026	SIGMOD	5.093636e-05
10,785	Auto-Test: Learning Semantic-Domain Constraints for Unsupervised Error Detection in Tables	2025	SIGMOD	5.093636e-05
10,933	LakeVisage: Towards Scalable, Flexible and Interactive Visualization Recommendation for Data Discovery over Data Lakes	2025	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 12 of 12 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
91	WebTables: Exploring the Power of Tables on the Web	2008	VLDB	0.00034838835
317	Annotating and Searching Web Tables Using Entities, Types and Relationships	2010	VLDB	0.00021402049
397	TURL: Table Understanding through Representation Learning	2021	VLDB	0.00019278189
1,923	Annotating Columns with Pre-trained Language Models	2022	SIGMOD	9.4789109e-05
2,192	Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning	2023	VLDB	8.9767241e-05
2,223	Sato: Contextual Semantic Type Detection in Tables	2020	VLDB	8.9189986e-05
2,790	GitTables: A Large-Scale Corpus of Relational Tables	2023	SIGMOD	8.1200509e-05
4,735	Leva: Boosting Machine Learning Performance with Relational Embedding Data Augmentation	2022	SIGMOD	6.5315782e-05
4,836	Transformers for Tabular Data Representation: A Tutorial on Models and Applications	2022	VLDB	6.4848269e-05
4,966	Rotom: A Meta-Learned Data Augmentation Framework for Entity Matching, Data Cleaning, Text Classification, and Beyond	2021	SIGMOD	6.4225454e-05
6,192	Pre-trained Embeddings for Entity Resolution: An Experimental Analysis	2023	VLDB	5.947284e-05
9,930	Data Augmentation for ML-driven Data Preparation and Integration	2021	VLDB	5.1955087e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	5,816	Observatory: Characterizing Embeddings of Relational Tables	2024	VLDB
2	317	Annotating and Searching Web Tables Using Entities, Types and Relationships	2010	VLDB
3	4,515	ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models	2024	VLDB
4	2,223	Sato: Contextual Semantic Type Detection in Tables	2020	VLDB
5	3,181	InfoGather+: Semantic Matching and Annotation of Numeric and Time-Varying Attributes in Web Tables	2013	SIGMOD
6	1,055	Answering Table Queries on the Web using Column Keywords	2012	VLDB
7	753	Recovering Semantics of Tables on the Web	2011	VLDB
8	1,923	Annotating Columns with Pre-trained Language Models	2022	SIGMOD
9	10,399	Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations	2026	SIGMOD
10	8,458	RECA: Related Tables Enhanced Column Semantic Type Annotation Framework	2023	VLDB