Database Paper Browser

Back to papers

TURL: Table Understanding through Representation Learning

Summary: TURL pre-trains on relational Web tables using a structure-aware Transformer and a Masked Entity Recovery objective for unsupervised representation learning. The universal model adapts to multiple tasks (relation extraction, cell filling) with minimal fine-tuning, outperforming prior methods on 6 benchmarks. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
12513
Venue
VLDB
Year
2021
Pagerank
0.00021288342
Overall Rank
513 | 96.44%
DOI
10.14778/3430915.3430921

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 5 of 55 citing papers.

Previous Page 2 / 2 Next

Outgoing Citations (Sorted by Pagerank)

Showing 5 of 5 cited papers.

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

Previous Page 1 / 1 Next

Semantically Similar Papers