Focusing on Context is NICE: Improving Overshadowed Entity Disambiguation

TL;DR

This paper introduces NICE, an iterative entity disambiguation method that leverages entity type information to improve disambiguation of overshadowed entities by reducing over-reliance on frequency priors.

Contribution

NICE is a novel iterative approach that effectively incorporates entity type information to address overshadowing in entity disambiguation tasks.

Findings

NICE outperforms existing models on overshadowed entities.

NICE maintains competitive performance on frequent entities.

The approach reduces frequency bias in entity disambiguation.

Abstract

Entity disambiguation (ED) is the task of mapping an ambiguous entity mention to the corresponding entry in a structured knowledge base. Previous research showed that entity overshadowing is a significant challenge for existing ED models: when presented with an ambiguous entity mention, the models are much more likely to rank a more frequent yet less contextually relevant entity at the top. Here, we present NICE, an iterative approach that uses entity type information to leverage context and avoid over-relying on the frequency-based prior. Our experiments show that NICE achieves the best performance results on the overshadowed entities while still performing competitively on the frequent entities.