Musical Heritage Historical Entity Linking

TL;DR

This paper introduces MHERCL, a challenging benchmark for entity linking in historical music texts, and proposes unsupervised models leveraging knowledge graphs to improve linking accuracy for underrepresented entities.

Contribution

The work presents a new benchmark dataset for historical music entity linking and develops unsupervised models that utilize knowledge graphs to enhance linking performance.

Findings

MHERCL is a challenging dataset for current models.

Unsupervised techniques outperform supervised ones on historical texts.

Knowledge graphs and heuristics improve NIL entity prediction.

Abstract

Linking named entities occurring in text to their corresponding entity in a Knowledge Base (KB) is challenging, especially when dealing with historical texts. In this work, we introduce Musical Heritage named Entities Recognition, Classification and Linking (MHERCL), a novel benchmark consisting of manually annotated sentences extrapolated from historical periodicals of the music domain. MHERCL contains named entities under-represented or absent in the most famous KBs. We experiment with several State-of-the-Art models on the Entity Linking (EL) task and show that MHERCL is a challenging dataset for all of them. We propose a novel unsupervised EL model and a method to extend supervised entity linkers by using Knowledge Graphs (KGs) to tackle the main difficulties posed by historical documents. Our experiments reveal that relying on unsupervised techniques and improving models with logical constraints based on KGs and heuristics to predict NIL entities (entities not represented in the KB of reference) results in better EL performance on historical documents.