Transformer-based Subject Entity Detection in Wikipedia Listings

TL;DR

This paper introduces a transformer-based method for detecting subject entities in Wikipedia listings, enhancing knowledge graph coverage by accurately identifying entities in semi-structured data without relying on entity boundary annotations.

Contribution

It presents a novel transformer-based approach that effectively identifies subject entities in listings, applicable to any listing format, and improves upon previous methods in performance and flexibility.

Findings

Extracted 40 million subject entity mentions from Wikipedia

Achieved an estimated precision of 71% and recall of 77%

Enhanced the CaLiGraph knowledge base with new entity data

Abstract

In tasks like question answering or text summarisation, it is essential to have background knowledge about the relevant entities. The information about entities - in particular, about long-tail or emerging entities - in publicly available knowledge graphs like DBpedia or CaLiGraph is far from complete. In this paper, we present an approach that exploits the semi-structured nature of listings (like enumerations and tables) to identify the main entities of the listing items (i.e., of entries and rows). These entities, which we call subject entities, can be used to increase the coverage of knowledge graphs. Our approach uses a transformer network to identify subject entities at the token-level and surpasses an existing approach in terms of performance while being bound by fewer limitations. Due to a flexible input format, it is applicable to any kind of listing and is, unlike prior work, not dependent on entity boundaries as input. We demonstrate our approach by applying it to the complete Wikipedia corpus and extracting 40 million mentions of subject entities with an estimated precision of 71% and recall of 77%. The results are incorporated in the most recent version of CaLiGraph.