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

Anonymous

TL;DR: In this paper, we integrate the commonly overlooked “None of the Candidates” predictions into zero-shot entity linking re-ranking stage.

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.

Paper Type: short

Research Area: Information Extraction

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English