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

RNA Editing02:23

RNA Editing

9.0K
RNA editing is a post-transcriptional modification where a precursor mRNA (pre-mRNA) nucleotide sequence is changed by base insertion, deletion, or modification. The extent of RNA editing varies from a few hundred bases, in mitochondrial DNA of trypanosomes, to a just single base, in nuclear genes of mammals. Even a single base change in the pre-mRNA can convert a codon for one amino acid into the codon for another amino acid or a stop codon. This type of re-coding can significantly affect the...
9.0K
lncRNA - Long Non-coding RNAs02:39

lncRNA - Long Non-coding RNAs

2.8K
2.8K

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

Development of a Machine Learning-Based Predictive Model and Clinically Oriented Web Application for 30-Day Mortality Following Cardiac Surgery.

Sensors (Basel, Switzerland)·2026
Same author

TOP-BIOCom: A Feature Fusion-based Prediction of Protein Complexes from PPI Networks.

Current computer-aided drug design·2025
Same author

Edge-Based Autonomous Fire and Smoke Detection Using MobileNetV2.

Sensors (Basel, Switzerland)·2025
Same author

Predictive Modeling of Weight Loss and Metabolic Health Outcomes: A Retrospective Predictive Modeling Study.

Health science reports·2025
Same author

BI-SENT: bilingual aspect-based sentiment analysis of COVID-19 Tweets in Urdu language.

PloS one·2025
Same author

Integrated brain tumor segmentation and MGMT promoter methylation status classification from multimodal MRI data using deep learning.

Digital health·2025

相关实验视频

Updated: Jun 29, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.5K

在乌尔都语中进行命名实体识别的深度学习方法.

Rimsha Anam1, Muhammad Waqas Anwar1,2, Muhammad Hasan Jamal1

  • 1Department of Computer Science, COMSATS University Islamabad, Lahore, Pakistan.

PloS one
|March 28, 2024
PubMed
概括

这项研究引入了乌尔都语命名实体识别 (NER) 的新型深度学习方法,显著提高了准确性. 该方法使用FastText和Floret字嵌入,达到0.98.98的最高F分数.

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

530
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

3.7K

相关实验视频

Last Updated: Jun 29, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.5K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

530
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

3.7K

科学领域:

  • 自然语言处理 (Natural Language Processing) 是一种自然语言处理.
  • 机器学习 机器学习
  • 计算语言学 计算语言学

背景情况:

  • 命名实体识别 (NER) 对于信息提取至关重要,但由于语言复杂性,乌尔都语仍未得到充分研究.
  • 现有的乌尔都语NER模型通常依赖于词嵌入来提取特征,但成功程度各不相同.

研究的目的:

  • 为乌尔都语命名实体识别 (NER) 提出一个强大的深度学习方法.
  • 通过利用FastText和Floret词嵌入来增强功能提取,以获得上下文信息.
  • 评估拟议的模型与基准乌尔都语数据集的最先进方法对比.

主要方法:

  • 利用预训练的FastText和Floret字嵌入来生成四个乌尔都语数据集的特征向量.
  • 训练了各种深度学习模型,包括长短期记忆 (LSTM),双向LSTM (BiLSTM) 和带有条件随机场 (CRF) 的门式循环单元 (GRU).
  • 实现了BiLSTM+GRU与Floret嵌入的组合作为主要模型架构.

主要成果:

  • 提出的深度学习方法显著优于现有的最先进的乌尔都语NER方法.
  • 使用BiLSTM+GRU架构与Floret嵌入实现了0.98的最大F分数.
  • 具有较低的分类错误率,在数据集中从1.24%到3.63%不等的稳定性.

结论:

  • 将FastText和Floret嵌入式与先进的深度学习架构 (BiLSTM+GRU) 集成为乌尔都语NER提供了一个非常有效的解决方案.
  • 拟议的方法代表了乌尔都语自然语言处理的重大进步,解决了语言形态学带来的挑战.
  • 取得的成绩表明,这种方法在乌尔都文本分析和信息检索方面具有更广泛的应用潜力.