CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web
Summary: CERES uses distant supervision for relation extraction on semi-structured sites by aligning a knowledge base with site structure. Classifier trained on noisy labels achieves annotation parity, scales to 400k pages and 1.25M facts at ~90% precision. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Colin Lockard (University of Washington)
- 2. Xin Luna Dong (Amazon)
- 3. Arash Einolghozati (Meta)
- 4. Prashant Shiralkar (Amazon)
BibTeX Citation
@article{lockard_vldb18,
title = {{CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web}},
author = {Lockard, Colin and Dong, Xin Luna and Einolghozati, Arash and Shiralkar, Prashant},
journal = {PVLDB},
series = {{VLDB} '18},
volume = {11},
number = {10},
pages = {1084--1096},
doi = {10.14778/3231751.3231758},
url = {https://doi.org/10.14778/3231751.3231758},
year = {2018}
}
Incoming Citations (Sorted by Pagerank)
Showing 6 of 6 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,424 | Data Integration and Machine Learning: A Natural Synergy | 2018 | VLDB | 5.6214566e-05 |
| 7,811 | The Smallest Extraction Problem | 2021 | VLDB | 5.5393291e-05 |
| 8,921 | Generations of Knowledge Graphs: The Crazy Ideas and the Business Impact | 2023 | VLDB | 5.3483178e-05 |
| 9,398 | Improving Information Extraction from Visually Rich Documents using Visual Span Representations | 2021 | VLDB | 5.2755515e-05 |
| 11,455 | Self-Training for Label-Efficient Information Extraction from Semi-Structured Web-Pages | 2023 | VLDB | 5.093636e-05 |
| 11,740 | Migrating a Privacy-Safe Information Extraction System to a Software 2.0 Design | 2020 | CIDR | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 13 of 13 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 | 6,011 | From Information to Knowledge: Harvesting Entities and Relationships from Web Sources | 2010 | PODS |
| 2 | 4,494 | Structured Annotations of Web Queries | 2010 | SIGMOD |
| 3 | 11,980 | Building Structured Databases of Factual Knowledge from Massive Text Corpora | 2017 | SIGMOD |
| 4 | 2,322 | Extraction and Integration of Partially Overlapping Web Sources | 2013 | VLDB |
| 5 | 4,736 | REX: Explaining Relationships between Entity Pairs | 2012 | VLDB |
| 6 | 5,545 | A Hierarchical Approach to Model Web Query Interfaces for Web Source Integration | 2009 | VLDB |
| 7 | 1,316 | Harvesting Relational Tables from Lists on the Web | 2009 | VLDB |
| 8 | 317 | Annotating and Searching Web Tables Using Entities, Types and Relationships | 2010 | VLDB |
| 9 | 11,455 | Self-Training for Label-Efficient Information Extraction from Semi-Structured Web-Pages | 2023 | VLDB |
| 10 | 5,745 | DIADEM: Thousands of Websites to a Single Database | 2014 | VLDB |