Annotating Columns with Pre-trained Language Models
Summary: Doduo, a multi-task framework using pre-trained language models, annotates table columns and their relations from the table. Achieves SOTA on two benchmarks for column types and relations, with up to 4.0% and 11.9% gains, using 8 tokens per column. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Yoshihiko Suhara (Megagon Labs)
- 2. Jinfeng Li (Megagon Labs)
- 3. Yuliang Li (Megagon Labs)
- 4. Dan Zhang (Megagon Labs)
- 5. Çağatay Demiralp (Megagon Labs; Sigma Computing)
- 6. Chen Chen (Megagon Labs)
- 7. Wang-Chiew Tan (Megagon Labs; Meta)
BibTeX Citation
@inproceedings{suhara_sigmod22,
title = {{Annotating Columns with Pre-trained Language Models}},
author = {Suhara, Yoshihiko and Li, Jinfeng and Li, Yuliang and Zhang, Dan and Demiralp, Çağatay and Chen, Chen and Tan, Wang-Chiew},
series = {{SIGMOD} '22},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3514221.3517906},
url = {https://dl.acm.org/doi/10.1145/3514221.3517906},
year = {2022}
}Incoming Citations (Sorted by Pagerank)
Showing 23 of 23 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 14 of 14 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
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,836 | Transformers for Tabular Data Representation: A Tutorial on Models and Applications | 2022 | VLDB |
| 2 | 8,945 | Generation of Training Examples for Tabular Natural Language Inference | 2023 | SIGMOD |
| 3 | 317 | Annotating and Searching Web Tables Using Entities, Types and Relationships | 2010 | VLDB |
| 4 | 9,067 | Making Table Understanding Work in Practice | 2022 | CIDR |
| 5 | 4,515 | ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models | 2024 | VLDB |
| 6 | 3,073 | DeepJoin: Joinable Table Discovery with Pre-trained Language Models | 2023 | VLDB |
| 7 | 8,860 | Watchog: A Light-weight Contrastive Learning based Framework for Column Annotation | 2023 | SIGMOD |
| 8 | 10,399 | Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations | 2026 | SIGMOD |
| 9 | 5,354 | Can Large Language Models Predict Data Correlations from Column Names? | 2023 | VLDB |
| 10 | 6,545 | DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models | 2024 | SIGMOD |