展示更少，指导更多：用定义和指南丰富提示，实现零样本命名实体识别

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，出现了几种专门针对命名实体识别（NER）进行调优的大型语言模型（LLMs）。与传统的NER方法相比，这些模型具有强大的泛化能力。现有的LLMs主要专注于零样本NER在域外分布上，通过在大量实体类别上进行微调，这些类别通常与测试集高度或完全重叠。相反，在这项工作中，我们提出了SLIMER，一种旨在通过指导模型少量示例并利用富含定义和指南的提示来解决以前从未见过的命名实体标签的方法。实验证明，定义和指南可以提高性能，加快和增强学习，特别是在标记未知命名实体时。此外，SLIMER在域外零样本NER中表现出与最先进方法相当的性能，同时在经过减少的标签集上进行训练。

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.