Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SLIMER-IT: Zero-Shot NER on Italian Language

Andrew Zamai, Leonardo Rigutini, Marco Maggini, Andrea Zugarini

TL;DR

This paper defines an evaluation framework for Zero-Shot NER, applying it to the Italian language and introduces SLIMER-IT, the Italian version of SLIMER, an instruction-tuning approach for zero-shot NER leveraging prompts enriched with definition and guidelines.

Abstract

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.

SLIMER-IT: Zero-Shot NER on Italian Language

TL;DR

This paper defines an evaluation framework for Zero-Shot NER, applying it to the Italian language and introduces SLIMER-IT, the Italian version of SLIMER, an instruction-tuning approach for zero-shot NER leveraging prompts enriched with definition and guidelines.

Abstract

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.
Paper Structure (26 sections, 2 figures, 4 tables)

This paper contains 26 sections, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. NER for Italian.
  4. Zero-Shot NER Framework
  5. In-domain.
  6. Out-Of-Domain (OOD).
  7. Unseen Named Entities.
  8. SLIMER-IT
  9. Experiments
  10. Datasets
  11. NERMuD.
  12. Multinerd-IT.
  13. Backbones
  14. Compared Models
  15. Token classification.
  16. ...and 11 more sections

Figures (2)

  • Figure 1: SLIMER-IT instruction tuning prompt. Dedicated entity definition and guidelines steer the model labelling.
  • Figure 2: SLIMER-IT performance for different backbones.