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

Machine Learning for IoT Applications and Digital Twins.

Sensors (Basel, Switzerland)·2024
Same author

Security in Transformer Visual Trackers: A Case Study on the Adversarial Robustness of Two Models.

Sensors (Basel, Switzerland)·2024
Same author

Offensive language detection in low resource languages: A use case of Persian language.

PloS one·2024
Same author

Unveiling Human Values: Analyzing Emotions behind Arguments.

Entropy (Basel, Switzerland)·2024
Same author

A survey on multi-lingual offensive language detection.

PeerJ. Computer science·2024
Same author

Widening Blockchain Technology toward Access Control for Service Provisioning in Cellular Networks.

Sensors (Basel, Switzerland)·2023
Same journal

Research on a Regional Availability Evaluation Model for Road-Area High-Entropy Energy Based on Synergy Factors.

Entropy (Basel, Switzerland)·2026
Same journal

Atmospheric Turbulence Channel Modeling and Performance Analysis of a CO-ZP-OFDM Coherent Optical Communication System for UAV Air-to-Ground Scenarios.

Entropy (Basel, Switzerland)·2026
Same journal

Information Geometry and Asymptotic Theory for SMML Estimators.

Entropy (Basel, Switzerland)·2026
Same journal

Correlation Entropy and Power-Law Kinetics.

Entropy (Basel, Switzerland)·2026
Same journal

Research on the Contagion of Systemic Financial Risk Under the Impact of Climate Risks-From the Perspective of Complex Networks and Machine Learning.

Entropy (Basel, Switzerland)·2026
Same journal

The Statistical-Mechanical Meaning of the Wave Function of Quantum Mechanics.

Entropy (Basel, Switzerland)·2026
查看所有相关文章

相关实验视频

Updated: Jun 27, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

548

多语言仇恨言论检测:一个半监督的生成对抗方法.

Khouloud Mnassri1, Reza Farahbakhsh1, Noel Crespi1

  • 1Samovar, Télécom SudParis, Institut Polytechnique de Paris, 91120 Palaiseau, France.

Entropy (Basel, Switzerland)
|April 26, 2024
PubMed
概括
此摘要是机器生成的。

本研究介绍了一种使用生成对抗网络 (GAN) 和预训练语言模型 (PLM) 进行有效检测仇恨言论的多语言半监督模型. 该模型在英语,德语和印度语的有限标记数据中实现了高性能.

关键词:
没有了,没有了,没有了.在 PLM 和 PLM 之间.仇恨言论 仇恨言论 仇恨言论 是一个多语言的多语种.半监督 半监督 半监督社交媒体 社交媒体

更多相关视频

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

443
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

相关实验视频

Last Updated: Jun 27, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

548
Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

443
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

科学领域:

  • 自然语言处理 (NLP) 是一种自然语言处理.
  • 人工智能 (AI) 是一种人工智能.

背景情况:

  • 社交媒体的全球影响力在不同语言中检测仇恨言论方面带来了挑战.
  • 标记数据的稀缺性阻碍了有效的仇恨言论检测模型的开发.
  • 半监督和生成人工智能方法对于克服数据限制至关重要.

研究的目的:

  • 开发一种创新的多语言半监督模型,用于检测仇恨言论和冒犯性语言.
  • 将生成对抗网络 (GAN) 与预训练语言模型 (PLM) 结合起来,以提高性能.
  • 为了应对跨语言仇恨言论检测中有限的标记数据的挑战.

主要方法:

  • 实施一个多语言半监督模型,将GAN与mBERT和XLM-RoBERTa集成在一起.
  • 仅使用HASOC2019数据集中的20%注释数据进行培训.
  • 跨多语言,零射击跨语言和单语言培训场景的评估.

主要成果:

  • 拟议的SS-GAN-mBERT模型在检测印欧语言中的仇恨言论和冒犯性语言方面表现出显著的有效性.
  • 该模型即使在有限的注释数据 (20%) 中也实现了高性能.
  • 基于mBERT的模型 (SS-GAN-mBERT) 的表现优于基于XLM-RoBERTa的模型 (SS-GAN-XLM),平均F1得分比基线增加9.23%,准确度增加5.75%.

结论:

  • 开发的半监督GAN模型为多语言仇恨言论检测提供了强大的解决方案.
  • 这种方法有效地减轻了NLP任务中有限的标记数据的挑战.
  • 这些发现突出了将GAN和PLM结合起来,促进跨语言内容调节的潜力.