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

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

Data augmentation for Arabic text classification: a review of current methods, challenges and prospective directions.

PeerJ. Computer science·2025
Same author

Enhanced transformer for length-controlled abstractive summarization based on summary output area.

PeerJ. Computer science·2025
Same author

TF-BERT: Tensor-based fusion BERT for multimodal sentiment analysis.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

A multi-view representation technique based on principal component analysis for enhanced short text clustering.

PloS one·2024
Same author

A normalization model for repeated letters in social media hate speech text based on rules and spelling correction.

PloS one·2024
Same author

Breast cancer diagnosis using the fast learning network algorithm.

Frontiers in oncology·2023

相关实验视频

Updated: Jun 5, 2025

Radio Frequency Identification and Motion-sensitive Video Efficiently Automate Recording of Unrewarded Choice Behavior by Bumblebees
09:09

Radio Frequency Identification and Motion-sensitive Video Efficiently Automate Recording of Unrewarded Choice Behavior by Bumblebees

Published on: November 15, 2014

10.9K

一个优化的BERT微调模型使用人工蜂群算法进行自动作文得分预测.

Ridha Hussein Chassab1, Lailatul Qadri Zakaria1, Sabrina Tiun1

  • 1Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia.

PeerJ. Computer science
|December 9, 2024
PubMed
概括
此摘要是机器生成的。

本研究介绍了一种优化的双向编码器转换 (BERT) 模型,使用人工蜂群 (ABC) 算法来提高自动作文评分 (AES) 预测的准确性. ABC-BERT-FTM方法有效地解决了分类器的灾难性遗忘问题,达到高达98.5%的准确性.

关键词:
人工蜂群算法的人工蜂群算法自动作文评分 自动作文评分来自转换的双向编码器表示.灾难性的遗忘.结机制的冷机制预测错误是因为预测错误.

更多相关视频

Tactile Conditioning And Movement Analysis Of Antennal Sampling Strategies In Honey Bees Apis mellifera L.
10:14

Tactile Conditioning And Movement Analysis Of Antennal Sampling Strategies In Honey Bees Apis mellifera L.

Published on: December 12, 2012

10.6K
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 5, 2025

Radio Frequency Identification and Motion-sensitive Video Efficiently Automate Recording of Unrewarded Choice Behavior by Bumblebees
09:09

Radio Frequency Identification and Motion-sensitive Video Efficiently Automate Recording of Unrewarded Choice Behavior by Bumblebees

Published on: November 15, 2014

10.9K
Tactile Conditioning And Movement Analysis Of Antennal Sampling Strategies In Honey Bees Apis mellifera L.
10:14

Tactile Conditioning And Movement Analysis Of Antennal Sampling Strategies In Honey Bees Apis mellifera L.

Published on: December 12, 2012

10.6K
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:

  • 自然语言处理自然语言处理.
  • 机器学习在教育中的应用

背景情况:

  • 自动作文得分 (AES) 预测系统对于教育应用至关重要.
  • AES系统分析文本和语法特征,用于得分预测.
  • 线性回归和分类器需要学习模式来提高得分准确度.

研究的目的:

  • 为了解决灾难性遗忘问题,并减少AES分类器中的计算复杂性.
  • 通过解决遗忘问题来提高预测准确度.
  • 提出一个优化的双向编码器从转换表示 (BERT) 模型.

主要方法:

  • 一个优化的BERT模型,称为ABC-BERT-FTM,是通过整合人工蜂群 (ABC) 算法来开发的.
  • 该ABC算法优化网络参数,以减轻遗忘问题.
  • 该模型进行了微调,以提高性能.

主要成果:

  • 优化的BERT模型在ASAP和ETS数据集上实现了高预测准确率,高达98.5%.
  • 在AES预测中,ABC算法有效地减少了灾难性遗忘问题.
  • 与现有方法相比,拟议的方法显示出更高的性能.

结论:

  • 使用像ABC这样的元启发式算法优化BERT可以解决AES系统中的忘记问题.
  • 采用ABC-BERT-FTM方法可以显著提高AES预测的准确性.
  • 这项研究为自动化作文评分提供了一个强大的解决方案.