TPL-NER: Three-Stage Prompt-Based Low-Resource Named Entity Recognition

Longyi Ye, Huaping Zhang*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Recent studies have shown that large language models perform excellently on downstream tasks. However, applying large models to named entity recognition (NER) through fine-tuning faces significant cost barriers. Therefore, we introduced a Three-Stage Prompt-based Low-Resource Named Entity Recognition (TPL-NER) model, aimed at improving the performance of zero-shot and few-shot NER tasks through contextual learning. TPL-NER addresses zero-shot and few-shot NER problems through a three-tiered step-by-step reasoning strategy. First, it identifies the possible entity types in a sentence, then recognizes which entities belong to each category within the sentence, and finally confirms the entity type for predicted entities that are easily confused across multiple categories. Experimental results on datasets from multiple domains and different languages show that TPL-NER’s superior performance in zero-shot and few-shot NER tasks.

Original languageEnglish
Title of host publicationIntelligent Multilingual Information Processing - 1st International Conference, IMLIP 2024, Proceedings
EditorsHuaping Zhang, Jianyun Shang, Jinsong Su
PublisherSpringer Science and Business Media Deutschland GmbH
Pages425-438
Number of pages14
ISBN (Print)9789819651221
DOIs
Publication statusPublished - 2025
Event1st International Conference on Intelligent Multilingual Information Processing, IMLIP 2024 - Beijing, China
Duration: 16 Nov 202417 Nov 2024

Publication series

NameCommunications in Computer and Information Science
Volume2395 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference1st International Conference on Intelligent Multilingual Information Processing, IMLIP 2024
Country/TerritoryChina
CityBeijing
Period16/11/2417/11/24

Keywords

  • few-shot
  • large language models
  • NER

Fingerprint

Dive into the research topics of 'TPL-NER: Three-Stage Prompt-Based Low-Resource Named Entity Recognition'. Together they form a unique fingerprint.

Cite this