SLIMER-IT：義大利語零樣本命名實體識別

SLIMER-IT: Zero-Shot NER on Italian Language

September 24, 2024

作者: Andrew Zamai, Leonardo Rigutini, Marco Maggini, Andrea Zugarini

cs.AI

摘要

傳統的命名實體識別（NER）方法將該任務定義為一個BIO序列標記問題。儘管這些系統在手頭的下游任務中表現出色，但它們需要大量標註數據，並且難以推廣到超出分布輸入領域和看不見的實體類型。相反，大型語言模型（LLMs）展現出強大的零-shot能力。雖然有幾篇論文探討了英語中的零-shot NER，但在其他語言中所做的工作很少。在本文中，我們為零-shot NER 定義了一個評估框架，並將其應用於義大利語。此外，我們介紹了SLIMER-IT，這是SLIMER的義大利語版本，一種利用富含定義和指南的提示的說明調整方法，用於零-shot NER。與其他最先進的模型進行比較，證明了SLIMER-IT在從未見過的實體標籤上的優越性。

English

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.