header

Fine-Grained Evaluation for Entity Linking

10 Pages Posted: 20 Jan 2021 Publication Status: Accepted

See all articles by Henry Rosales-Mendez

Henry Rosales-Mendez

University of Chile - Department of Computer Science

Barbara Poblete

IMFD Chile & Department of Computer Science, University of Chile

Aidan Hogan

IMFD Chile & Department of Computer Science, University of Chile

Abstract

The Entity Linking (EL) task identifies entity mentions in a text corpus and associates them with an unambiguous identifier in a Knowledge Base. While much work has been done on the topic, we first present the results of a survey that reveal a lack of consensus in the community regarding what forms of mentions in a text and what forms of links the EL task should consider. We argue that no one definition of the Entity Linking task fits all, and rather propose a fine-grained cate-gorization of different types of entity mentions and links. We then re-annotate three EL benchmark datasets-ACE2004, KORE50, and VoxEL-with respect to these categories. We propose a fuzzy recall metric to address the lack of consensus and conclude with fine-grained evaluation results comparing a selection of online EL systems.

Suggested Citation

Rosales-Mendez, Henry and Poblete, Barbara and Hogan, Aidan, Fine-Grained Evaluation for Entity Linking. Journal of Web Semantics First Look , Available at SSRN: https://ssrn.com/abstract=3769924 or http://dx.doi.org/10.2139/ssrn.3769924

Henry Rosales-Mendez (Contact Author)

University of Chile - Department of Computer Science ( email )

Avenida Blanco Encalada
Santiago
Chile

Barbara Poblete

IMFD Chile & Department of Computer Science, University of Chile ( email )

Aidan Hogan

IMFD Chile & Department of Computer Science, University of Chile ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
64
Downloads
2
PlumX Metrics