Harvesting Entities from the Web Using Unique Identifiers -- IBEX

TL;DR

This paper presents a systematic method for harvesting and associating unique entity identifiers from the Web, creating a large, accurate database that enables new insights into entity distribution online.

Contribution

It introduces a scalable approach to extract, filter, and link unique identifiers with human-readable names, significantly improving coverage and accuracy over existing knowledge bases.

Findings

Achieved 73-96% accuracy in entity identification.

Created a database of millions of uniquely identified entities.

Provided new statistics on entity presence on the Web.

Abstract

In this paper we study the prevalence of unique entity identifiers on the Web. These are, e.g., ISBNs (for books), GTINs (for commercial products), DOIs (for documents), email addresses, and others. We show how these identifiers can be harvested systematically from Web pages, and how they can be associated with human-readable names for the entities at large scale. Starting with a simple extraction of identifiers and names from Web pages, we show how we can use the properties of unique identifiers to filter out noise and clean up the extraction result on the entire corpus. The end result is a database of millions of uniquely identified entities of different types, with an accuracy of 73--96% and a very high coverage compared to existing knowledge bases. We use this database to compute novel statistics on the presence of products, people, and other entities on the Web.