Database Paper Browser

Back to papers

RECA: Related Tables Enhanced Column Semantic Type Annotation Framework

Summary: RECA: a related-tables-based column semantic type annotation framework that aligns schema-similar, topic-relevant tables via a novel named-entity schema to incorporate inter-table context and naturally handle wide tables. Outperforms prior art on two web-table datasets (support-weighted F1 0.853/0.937; macro F1 0.674/0.783). (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
12997
Venue
VLDB
Year
2023
Pagerank
4.4922446e-05
Overall Rank
8,579 | 40.32%
DOI
10.14778/3583140.3583149

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 5 of 5 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 6 of 6 cited papers.

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

Rank Cited Paper Year Venue Pagerank
112 Potter's Wheel: An Interactive Data Cleaning System 2001 VLDB 0.00047045036
513 TURL: Table Understanding through Representation Learning 2021 VLDB 0.00021288342
1,001 Recovering Semantics of Tables on the Web 2011 VLDB 0.00014706505
2,517 Annotating Columns with Pre-trained Language Models 2022 SIGMOD 8.6092139e-05
2,730 Open Data Integration 2018 VLDB 8.2126735e-05
2,888 Sato: Contextual Semantic Type Detection in Tables 2020 VLDB 7.9594996e-05
Previous Page 1 / 1 Next

Semantically Similar Papers