SLIMER-IT: Zero-Shot NER on Italian Language
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929590585262080 |
|---|---|
| author | Zamai, Andrew Rigutini, Leonardo Maggini, Marco Zugarini, Andrea |
| author_facet | Zamai, Andrew Rigutini, Leonardo Maggini, Marco Zugarini, Andrea |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15933 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SLIMER-IT: Zero-Shot NER on Italian Language Zamai, Andrew Rigutini, Leonardo Maggini, Marco Zugarini, Andrea Computation and Language Information Retrieval 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. |
| title | SLIMER-IT: Zero-Shot NER on Italian Language |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2409.15933 |