Research on knowledge concept extraction method based on few-shot learning and chain-of-thought prompting

Knowledge concept extraction has important application value in the fields of education, medical care, and finance. Knowledge concept extraction is a sub-task of named entity recognition. However, due to the lack of data sets and the particularity of knowledge concept entity types, directly applying...

Full description

Saved in:
Bibliographic Details
Main Authors: SHE Linlin, XIONG Longyang, LU Xuesong
Format: Article
Language:zho
Published: China InfoCom Media Group 2025-01-01
Series:大数据
Subjects:
Online Access:http://www.j-bigdataresearch.com.cn/thesisDetails?columnId=109257829&Fpath=home&index=0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849470648429051904
author SHE Linlin
XIONG Longyang
LU Xuesong
author_facet SHE Linlin
XIONG Longyang
LU Xuesong
author_sort SHE Linlin
collection DOAJ
description Knowledge concept extraction has important application value in the fields of education, medical care, and finance. Knowledge concept extraction is a sub-task of named entity recognition. However, due to the lack of data sets and the particularity of knowledge concept entity types, directly applying general named entity recognition methods to knowledge concept extraction tasks often has poor results. In view of the above challenges, a method based on few-shot learning and chain-of-thought prompting for knowledge concept extraction was proposed, utilizing open-source large language models. Firstly, text representations focusing on entity semantics were trained through contrastive learning, and the relevance of the retrieved few-shot examples was enhanced using the <italic>K</italic>-nearest neighbors algorithm. Secondly, a method utilizing chain-of-thought prompting was adopted to present the samples, with the aim of improving the reasoning ability of large language models in knowledge concept extraction. Experimental results on multiple datasets demonstrate that the few-shot learning and chain-of-thought prompting for knowledge concept extraction method, onthe whole, has shown results superior over existing methods.
format Article
id doaj-art-72e00fbe4094466187c11d3a30fed516
institution Kabale University
issn 2096-0271
language zho
publishDate 2025-01-01
publisher China InfoCom Media Group
record_format Article
series 大数据
spelling doaj-art-72e00fbe4094466187c11d3a30fed5162025-08-20T03:25:07ZzhoChina InfoCom Media Group大数据2096-02712025-01-01114109257829Research on knowledge concept extraction method based on few-shot learning and chain-of-thought promptingSHE LinlinXIONG LongyangLU XuesongKnowledge concept extraction has important application value in the fields of education, medical care, and finance. Knowledge concept extraction is a sub-task of named entity recognition. However, due to the lack of data sets and the particularity of knowledge concept entity types, directly applying general named entity recognition methods to knowledge concept extraction tasks often has poor results. In view of the above challenges, a method based on few-shot learning and chain-of-thought prompting for knowledge concept extraction was proposed, utilizing open-source large language models. Firstly, text representations focusing on entity semantics were trained through contrastive learning, and the relevance of the retrieved few-shot examples was enhanced using the <italic>K</italic>-nearest neighbors algorithm. Secondly, a method utilizing chain-of-thought prompting was adopted to present the samples, with the aim of improving the reasoning ability of large language models in knowledge concept extraction. Experimental results on multiple datasets demonstrate that the few-shot learning and chain-of-thought prompting for knowledge concept extraction method, onthe whole, has shown results superior over existing methods.http://www.j-bigdataresearch.com.cn/thesisDetails?columnId=109257829&Fpath=home&index=0named entity recognitionlarge language model
spellingShingle SHE Linlin
XIONG Longyang
LU Xuesong
Research on knowledge concept extraction method based on few-shot learning and chain-of-thought prompting
大数据
named entity recognition
large language model
title Research on knowledge concept extraction method based on few-shot learning and chain-of-thought prompting
title_full Research on knowledge concept extraction method based on few-shot learning and chain-of-thought prompting
title_fullStr Research on knowledge concept extraction method based on few-shot learning and chain-of-thought prompting
title_full_unstemmed Research on knowledge concept extraction method based on few-shot learning and chain-of-thought prompting
title_short Research on knowledge concept extraction method based on few-shot learning and chain-of-thought prompting
title_sort research on knowledge concept extraction method based on few shot learning and chain of thought prompting
topic named entity recognition
large language model
url http://www.j-bigdataresearch.com.cn/thesisDetails?columnId=109257829&Fpath=home&index=0
work_keys_str_mv AT shelinlin researchonknowledgeconceptextractionmethodbasedonfewshotlearningandchainofthoughtprompting
AT xionglongyang researchonknowledgeconceptextractionmethodbasedonfewshotlearningandchainofthoughtprompting
AT luxuesong researchonknowledgeconceptextractionmethodbasedonfewshotlearningandchainofthoughtprompting