On the Surprising Effectiveness of Name Matching Alone in Autoregressive Entity Linking

Elliot Schumacher, James Mayfield, Mark Dredze

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Fifteen years of work on entity linking has established the importance of different information sources in making linking decisions: mention and entity name similarity, contextual relevance, and features of the knowledge base. Modern state-of-the-art systems build on these features, including through neural representations (Wu et al., 2020). In contrast to this trend, the autoregressive language model GENRE (De Cao et al., 2021) generates normalized entity names for mentions and beats many other entity linking systems, despite making no use of knowledge base (KB) information. How is this possible? We analyze the behavior of GENRE on several entity linking datasets and demonstrate that its performance stems from memorization of name patterns. In contrast, it fails in cases that might benefit from using the KB. We experiment with a modification to the model to enable it to utilize KB information, highlighting challenges to incorporating traditional entity linking information sources into autoregressive models.

Original languageEnglish (US)
Title of host publication1st Workshop on Matching from Unstructured and Structured Data, MATCHING 2023 - Proceedings of the Workshop
EditorsEstevam Hruschka, Tom Mitchell, Sajjadur Rahman, Dunja Mladenic, Marko Grobelnik
PublisherAssociation for Computational Linguistics (ACL)
Pages58-69
Number of pages12
ISBN (Electronic)9781959429821
StatePublished - 2023
Event1st Workshop on Matching from Unstructured and Structured Data, MATCHING 2023 - Toronto, Canada
Duration: Jul 13 2023 → …

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

Conference1st Workshop on Matching from Unstructured and Structured Data, MATCHING 2023
Country/TerritoryCanada
CityToronto
Period7/13/23 → …

ASJC Scopus subject areas

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'On the Surprising Effectiveness of Name Matching Alone in Autoregressive Entity Linking'. Together they form a unique fingerprint.

Cite this