Making Table Understanding Work in Practice
Summary: Identifies a gap between high-accuracy DL table-understanding models on benchmarks and real-world deployments that still rely on heuristics/regex for a few semantic types. Characterizes practical needs—robustness, coverage, explainability, efficiency, calibration, domain adaptation—and prescribes evaluation and design directions to make table understanding usable in production. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Madelon Hulsebos
- 2. Sneha Gathani
- 3. James Gale
- 4. Isil Dillig
- 5. Paul Groth
- 6. Çağatay Demiralp
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 11,205 | Steered Training Data Generation for Learned Semantic Type Detection | 2023 | SIGMOD | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 513 | TURL: Table Understanding through Representation Learning | 2021 | VLDB | 0.00021288342 |
| 3,520 | GitTables: A Large-Scale Corpus of Relational Tables | 2023 | SIGMOD | 7.0131061e-05 |
Previous
Page 1 / 1
Next