展示更少，指導更多：豐富提示與定義和指南，用於零樣本NER

Show Less, Instruct More: Enriching Prompts with Definitions and Guidelines for Zero-Shot NER

July 1, 2024

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

cs.AI

摘要

最近，出現了幾種針對命名實體識別（NER）的專門調整的大型語言模型（LLM）。與傳統的NER方法相比，這些模型具有強大的泛化能力。現有的LLM主要專注於在域外分佈的零-shot NER，通常在大量的實體類別上進行微調，這些類別與測試集高度或完全重疊。相反，在這項工作中，我們提出了SLIMER，一種旨在通過指導模型進行更少範例和利用富含定義和指南的提示來應對從未見過的命名實體標籤的方法。實驗表明，定義和指南能夠提供更好的性能、更快速和更穩健的學習，特別是在標記未見過的命名實體時。此外，SLIMER在域外零-shot NER中表現與最先進的方法相當，同時在經過簡化的標籤集上進行訓練。

English

Recently, several specialized instruction-tuned Large Language Models (LLMs) for Named Entity Recognition (NER) have emerged. Compared to traditional NER approaches, these models have strong generalization capabilities. Existing LLMs mainly focus on zero-shot NER in out-of-domain distributions, being fine-tuned on an extensive number of entity classes that often highly or completely overlap with test sets. In this work instead, we propose SLIMER, an approach designed to tackle never-seen-before named entity tags by instructing the model on fewer examples, and by leveraging a prompt enriched with definition and guidelines. Experiments demonstrate that definition and guidelines yield better performance, faster and more robust learning, particularly when labelling unseen Named Entities. Furthermore, SLIMER performs comparably to state-of-the-art approaches in out-of-domain zero-shot NER, while being trained on a reduced tag set.