@inproceedings{190757a46d6f41e48cec9d6db2d72d80,
title = "TPL-NER: Three-Stage Prompt-Based Low-Resource Named Entity Recognition",
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{\textquoteright}s superior performance in zero-shot and few-shot NER tasks.",
keywords = "few-shot, large language models, NER",
author = "Longyi Ye and Huaping Zhang",
note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.; 1st International Conference on Intelligent Multilingual Information Processing, IMLIP 2024 ; Conference date: 16-11-2024 Through 17-11-2024",
year = "2025",
doi = "10.1007/978-981-96-5123-8\_29",
language = "English",
isbn = "9789819651221",
series = "Communications in Computer and Information Science",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "425--438",
editor = "Huaping Zhang and Jianyun Shang and Jinsong Su",
booktitle = "Intelligent Multilingual Information Processing - 1st International Conference, IMLIP 2024, Proceedings",
address = "Germany",
}