SLIMER-IT: Zero-Shot NER on Italian Language
This work addresses the problem of limited annotated data and generalization in NER for Italian, though it is incremental as it adapts an existing method to a new language.
The paper tackles zero-shot named entity recognition (NER) for Italian by introducing SLIMER-IT, an instruction-tuning approach with enriched prompts, and demonstrates its superiority over state-of-the-art models on unseen entity tags.
Traditional approaches to Named Entity Recognition (NER) frame the task into a BIO sequence labeling problem. Although these systems often excel in the downstream task at hand, they require extensive annotated data and struggle to generalize to out-of-distribution input domains and unseen entity types. On the contrary, Large Language Models (LLMs) have demonstrated strong zero-shot capabilities. While several works address Zero-Shot NER in English, little has been done in other languages. In this paper, we define an evaluation framework for Zero-Shot NER, applying it to the Italian language. Furthermore, we introduce SLIMER-IT, the Italian version of SLIMER, an instruction-tuning approach for zero-shot NER leveraging prompts enriched with definition and guidelines. Comparisons with other state-of-the-art models, demonstrate the superiority of SLIMER-IT on never-seen-before entity tags.