English

CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web

Artificial Intelligence 2018-04-13 v1 Information Retrieval

Abstract

The web contains countless semi-structured websites, which can be a rich source of information for populating knowledge bases. Existing methods for extracting relations from the DOM trees of semi-structured webpages can achieve high precision and recall only when manual annotations for each website are available. Although there have been efforts to learn extractors from automatically-generated labels, these methods are not sufficiently robust to succeed in settings with complex schemas and information-rich websites. In this paper we present a new method for automatic extraction from semi-structured websites based on distant supervision. We automatically generate training labels by aligning an existing knowledge base with a web page and leveraging the unique structural characteristics of semi-structured websites. We then train a classifier based on the potentially noisy and incomplete labels to predict new relation instances. Our method can compete with annotation-based techniques in the literature in terms of extraction quality. A large-scale experiment on over 400,000 pages from dozens of multi-lingual long-tail websites harvested 1.25 million facts at a precision of 90%.

Keywords

Cite

@article{arxiv.1804.04635,
  title  = {CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web},
  author = {Colin Lockard and Xin Luna Dong and Arash Einolghozati and Prashant Shiralkar},
  journal= {arXiv preprint arXiv:1804.04635},
  year   = {2018}
}

Comments

Expanded version of paper under review for VLDB

R2 v1 2026-06-23T01:22:04.446Z