English

Focusing on Context is NICE: Improving Overshadowed Entity Disambiguation

Computation and Language 2022-10-13 v1 Information Retrieval

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.

Keywords

Cite

@article{arxiv.2210.06164,
  title  = {Focusing on Context is NICE: Improving Overshadowed Entity Disambiguation},
  author = {Vera Provatorova and Simone Tedeschi and Svitlana Vakulenko and Roberto Navigli and Evangelos Kanoulas},
  journal= {arXiv preprint arXiv:2210.06164},
  year   = {2022}
}
R2 v1 2026-06-28T03:26:12.156Z