RetrieveAll: A Multilingual Named Entity Recognition Framework with Large Language Models

Le résumé fourni par la source

The rise of large language models has led to breakthroughs in named entity recognition for high-resource languages, yet substantial room for improvement remains in low- and medium-resource languages. Existing multilingual named entity recognition methods face severe language interference during the multi-language adaptation process, manifested in feature conflicts between different languages and the competitive suppression of low-resource language features by high-resource languages. Although training a dedicated model for each language can mitigate such interference, it lacks scalability and incurs excessive computational costs in real-world applications. To address this issue, we propose RetrieveAll, a universal multilingual named entity recognition framework based on dynamic LoRA. The framework decouples task-specific features across languages and demonstrates efficient dynamic adaptability. Furthermore, we introduce a cross-granularity knowledge augmented method that fully exploits the intrinsic potential of the data without relying on external resources. Experimental results show that RetrieveAll achieves an average F1 improvement of 12.1% on the PAN-X dataset.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.