Unstructured Data Fusion for Schema and Data Extraction
Summary: Introduces SDE: enrich partial query tables from unstructured text by jointly inferring missing schema/data and constructing output tables. End-to-end retrieval + multi-document seq2seq augmentation with interpolation keeps context nearly constant, mitigating retrieval noise and outperforming baselines. (summarized by gpt-5.4-mini on May 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Kaiwen Chen (University of Toronto)
- 2. Nick Koudas (University of Toronto)
BibTeX Citation
@inproceedings{chen_sigmod24,
title = {{Unstructured Data Fusion for Schema and Data Extraction}},
author = {Chen, Kaiwen and Koudas, Nick},
series = {{SIGMOD} '24},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3654984},
url = {https://dl.acm.org/doi/10.1145/3654984},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 329 | Can Foundation Models Wrangle Your Data? | 2023 | VLDB | 0.00020867521 |
| 377 | TURL: Table Understanding through Representation Learning | 2021 | VLDB | 0.00019564011 |
| 1,038 | ARDA: Automatic Relational Data Augmentation for Machine Learning | 2020 | VLDB | 0.000123653 |
| 1,990 | SANTOS: Relationship-based Semantic Table Union Search | 2023 | SIGMOD | 9.2443028e-05 |
| 3,015 | Saga: A Platform for Continuous Construction and Serving of Knowledge At Scale | 2022 | SIGMOD | 7.7504975e-05 |
| 3,617 | Leva: Boosting Machine Learning Performance with Relational Embedding Data Augmentation | 2022 | SIGMOD | 7.1540505e-05 |
| 7,199 | Cross Modal Data Discovery over Structured and Unstructured Data Lakes | 2023 | VLDB | 5.5864204e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 658 | DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing | 2025 | VLDB |
| 2 | 11,047 | Semantic Data Systems: From Data Management to Data Understanding | 2026 | VLDB |
| 3 | 13,590 | SciTables: A Dataset and Evaluation Framework for Complex Table-to-Text Generation | 2026 | VLDB |
| 4 | 8,182 | DocDB: A Database for Unstructured Document Analysis | 2025 | VLDB |
| 5 | 12,284 | Building Structured Databases of Factual Knowledge from Massive Text Corpora | 2017 | SIGMOD |
| 6 | 5,686 | DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models | 2024 | SIGMOD |
| 7 | 1,696 | Answering Table Augmentation Queries from Unstructured Lists on the Web [Extended Abstract] | 2009 | VLDB |
| 8 | 10,814 | Document-to-Database: Extraction Meets Relational Semantics | 2026 | VLDB |
| 9 | 8,687 | Relational Deep Dive: Error-Aware Queries Over Unstructured Data | 2026 | VLDB |
| 10 | 8,688 | Unstructured Data Analysis Using LLMs: A Comprehensive Benchmark | 2026 | VLDB |