NAACL 2024short3 citations

GenDecider: Integrating “None of the Candidates” Judgments in Zero-Shot Entity Linking Re-ranking

Kang Zhou, Yuepei Li, Qing Wang, Qiao Qiao, Qi Li

Abstract

We introduce GenDecider, a novel re-ranking approach for Zero-Shot Entity Linking (ZSEL), built on the Llama model. It innovatively detects scenarios where the correct entity is not among the retrieved candidates, a common oversight in existing re-ranking methods. By autoregressively generating outputs based on the context of the entity mention and the candidate entities, GenDecider significantly enhances disambiguation, improving the accuracy and reliability of ZSEL systems, as demonstrated on the benchmark ZESHEL dataset. Our code is available at https://github.com/kangISU/GenDecider.

BibTeX
@inproceedings{zhou-etal-2024-gendecider,
    title = "{G}en{D}ecider: Integrating {\textquotedblleft}None of the Candidates{\textquotedblright} Judgments in Zero-Shot Entity Linking Re-ranking",
    author = "Zhou, Kang  and
      Li, Yuepei  and
      Wang, Qing  and
      Qiao, Qiao  and
      Li, Qi",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-short.22/",
    doi = "10.18653/v1/2024.naacl-short.22",
    pages = "239--245"
}
GenDecider: Integrating “None of the Candidates” Judgments in Zero-Shot Entity Linking Re-ranking · NAACL 2024