Large Language Models for Few-Shot Named Entity Recognition

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhao, Yufei, Zhong, Xiaoshi, Cambria, Erik, Rajapakse, Jagath C.
Format: Preprint
Publié: 2018
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915583609536512
author Zhao, Yufei
Zhong, Xiaoshi
Cambria, Erik
Rajapakse, Jagath C.
author_facet Zhao, Yufei
Zhong, Xiaoshi
Cambria, Erik
Rajapakse, Jagath C.
contents Named entity recognition (NER) is a fundamental task in numerous downstream applications. Recently, researchers have employed pre-trained language models (PLMs) and large language models (LLMs) to address this task. However, fully leveraging the capabilities of PLMs and LLMs with minimal human effort remains challenging. In this paper, we propose GPT4NER, a method that prompts LLMs to resolve the few-shot NER task. GPT4NER constructs effective prompts using three key components: entity definition, few-shot examples, and chain-of-thought. By prompting LLMs with these effective prompts, GPT4NER transforms few-shot NER, which is traditionally considered as a sequence-labeling problem, into a sequence-generation problem. We conduct experiments on two benchmark datasets, CoNLL2003 and OntoNotes5.0, and compare the performance of GPT4NER to representative state-of-the-art models in both few-shot and fully supervised settings. Experimental results demonstrate that GPT4NER achieves the $F_1$ of 83.15\% on CoNLL2003 and 70.37\% on OntoNotes5.0, significantly outperforming few-shot baselines by an average margin of 7 points. Compared to fully-supervised baselines, GPT4NER achieves 87.9\% of their best performance on CoNLL2003 and 76.4\% of their best performance on OntoNotes5.0. We also utilize a relaxed-match metric for evaluation and report performance in the sub-task of named entity extraction (NEE), and experiments demonstrate their usefulness to help better understand model behaviors in the NER task.
format Preprint
id arxiv_https___arxiv_org_abs_1810_06818
institution arXiv
publishDate 2018
record_format arxiv
spellingShingle Large Language Models for Few-Shot Named Entity Recognition
Zhao, Yufei
Zhong, Xiaoshi
Cambria, Erik
Rajapakse, Jagath C.
Computation and Language
Information Retrieval
Named entity recognition (NER) is a fundamental task in numerous downstream applications. Recently, researchers have employed pre-trained language models (PLMs) and large language models (LLMs) to address this task. However, fully leveraging the capabilities of PLMs and LLMs with minimal human effort remains challenging. In this paper, we propose GPT4NER, a method that prompts LLMs to resolve the few-shot NER task. GPT4NER constructs effective prompts using three key components: entity definition, few-shot examples, and chain-of-thought. By prompting LLMs with these effective prompts, GPT4NER transforms few-shot NER, which is traditionally considered as a sequence-labeling problem, into a sequence-generation problem. We conduct experiments on two benchmark datasets, CoNLL2003 and OntoNotes5.0, and compare the performance of GPT4NER to representative state-of-the-art models in both few-shot and fully supervised settings. Experimental results demonstrate that GPT4NER achieves the $F_1$ of 83.15\% on CoNLL2003 and 70.37\% on OntoNotes5.0, significantly outperforming few-shot baselines by an average margin of 7 points. Compared to fully-supervised baselines, GPT4NER achieves 87.9\% of their best performance on CoNLL2003 and 76.4\% of their best performance on OntoNotes5.0. We also utilize a relaxed-match metric for evaluation and report performance in the sub-task of named entity extraction (NEE), and experiments demonstrate their usefulness to help better understand model behaviors in the NER task.
title Large Language Models for Few-Shot Named Entity Recognition
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/1810.06818