Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Brain Abscess l: Introduction01:26

Brain Abscess l: Introduction

A brain abscess is a focal, intracerebral infection characterized by a localized collection of pus within the brain parenchyma, resulting from microbial invasion and the body’s inflammatory response. It progresses through stages: early and late cerebritis, followed by early and late capsule formation, reflecting tissue destruction, immune response, and eventual encapsulation.Etiology and PathogenesisCausative organisms vary with source and host factors, often involving polymicrobial infections,...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

GhSCAMP13 Negatively Modulates Salt Tolerance Through GhNHX7b-Dependent Na<sup>+</sup> Homeostasis in Cotton.

Plant biotechnology journal·2026
Same author

Multi-Omics Reveals the Impact of Domestic Wastewater Input on the Dissolved Organic Carbon Pool and Microbial Community in the Qiantang River Estuary.

Microorganisms·2026
Same author

Unraveling coronavirus cell invasion: The role of glycan receptors in human coronavirus-HKU1 cell entry.

Infectious diseases & immunity·2026
Same author

MRI-guided risk stratification for neoadjuvant immunotherapy in rectal cancer.

Frontiers in immunology·2026
Same author

Author Correction: A broadly protective antibody targeting gammaherpesvirus gB.

Nature·2026
Same author

Advances in BODIPY Derivatives for Antibacterial Phototherapy.

Angewandte Chemie (International ed. in English)·2026

相关实验视频

Updated: Jun 2, 2026

Eye-tracking to Distinguish Comprehension-based and Oculomotor-based Regressive Eye Movements During Reading
05:54

Eye-tracking to Distinguish Comprehension-based and Oculomotor-based Regressive Eye Movements During Reading

Published on: October 18, 2018

6.1K

以示范为基础的学习为机器阅读理解下的少数镜头生物医学命名实体识别.

Leilei Su1, Jian Chen2, Yifan Peng3

  • 1Department of Mathematics, Hainan University, Haikou 570228, China.

Journal of biomedical informatics
|November 3, 2024
PubMed
概括

这项研究引入了一种新的机器阅读理解 (MRC) 方法,以改进几次射击的生物医学命名实体识别 (BioNER). 该方法在低数据场景中提高实体识别准确性,优于传统的序列标记技术.

关键词:
生物医学命名实体的识别.基于示范的学习是基于示范的学习.有几次射击学习学习.机器阅读理解 机器阅读理解基于提示的即时学习.

更多相关视频

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment
06:48

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment

Published on: June 25, 2019

9.1K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.6K

相关实验视频

Last Updated: Jun 2, 2026

Eye-tracking to Distinguish Comprehension-based and Oculomotor-based Regressive Eye Movements During Reading
05:54

Eye-tracking to Distinguish Comprehension-based and Oculomotor-based Regressive Eye Movements During Reading

Published on: October 18, 2018

6.1K
Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment
06:48

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment

Published on: June 25, 2019

9.1K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.6K

科学领域:

  • 生物医学信息学 生物医学信息学
  • 自然语言处理自然语言处理.
  • 机器学习 机器学习

背景情况:

  • 深度学习模型通常需要广泛的标记数据来实现有效的生物医学命名实体识别 (BioNER).
  • 标记数据稀缺的少数射击学习场景,对BioNER当前的深度学习模型构成重大挑战.
  • 当训练数据有限时,现有的方法难以达到高精度.

研究的目的:

  • 开发一种有效的策略,以改善生物医学实体识别在少数射击学习场景.
  • 为了提高模型在识别有限的注释数据的生物医学实体的性能.
  • 解决像BioNER这样的专业领域中数据饥饿的深度学习模型的局限性.

主要方法:

  • 重新定义生物医学命名实体识别 (BioNER) 作为机器阅读理解 (MRC) 问题.
  • 提出了一种基于演示的学习方法,利用任务演示来解决 BioNER.
  • 在六个基准数据集 (BC4CHEMD,BC5CDR-Chemical,BC5CDR-Disease,NCBI-Disease,BC2GM,JNLPBA) 上对先进技术进行了评估.

主要成果:

  • 与基线方法相比,在25射击学习中实现了1.1%的F1平均得分改善,在50射击学习中达到1.0%.
  • 在六个不同的生物医学数据集中表现出强的表现,每个数据集都报告了特定的F1分数.
  • 展示了基于MRC的方法在少数 BioNER 任务中的有效性.

结论:

  • 基于MRC的语言模型显著超过了为数不多的BioNER的序列标记方法.
  • 拟议的MRC模型显示了与完全监督的方法相比具有竞争力的性能,即使有有限的注释数据.
  • 这项研究为推进少量 BioNER 方法提供了有希望的途径,减少了对大型标记数据集的依赖.