Adversarial Learning for Multi-Lingual Entity Linking
Bingbing Wang, Bin Liang, Zhixin Bai, Yongzhuo Ma · 2024
Entity linking aims to identify mentions from the text and link them to a knowledge base.Further, Multi-lingual Entity Linking (MEL) is a more challenging task, where the languagespecific mentions need to be linked to a multilingual knowledge base.To tackle the MEL task, we propose a novel model that employs the merit of adversarial learning and fewshot learning to generalize the learning ability across languages.Specifically, we first randomly select a fraction of language-agnostic unlabeled data as the language signal to construct the language discriminator.Based on it, we devise a simple and effective adversarial learning framework with two characteristic branches, including an entity classifier and a language discriminator with adversarial training.Experimental results on two benchmark datasets indicate the excellent performance in few-shot learning and the effectiveness of the proposed adversarial learning framework.