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

Encoding01:19

Encoding

1.1K
Information enters the brain through encoding, which is the input of information into the memory system. Once sensory information is received from the environment, the brain labels or codes it. The information is then organized with similar information and connected to existing concepts. Encoding occurs through automatic processing and effortful processing.
Automatic processing involves the encoding of details like time, space, frequency, and the meaning of words, usually done without conscious...
1.1K

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

Targeting stemness of cancer stem cells to fight colorectal cancers.

Seminars in cancer biology·2021
Same author

Discovery of a novel AR/HDAC6 dual inhibitor for prostate cancer treatment.

Aging·2021
Same author

Superconductivity of Topological Surface States and Strong Proximity Effect in Sn<sub>1-x</sub>Pb<sub>x</sub>Te-Pb Heterostructures.

Advanced materials (Deerfield Beach, Fla.)·2021
Same author

A comparison of efficacy and safety of complementary and alternative therapies for severe mycoplasma pneumonia in children: A protocol for systematic review and meta-analysis.

Medicine·2021
Same author

Lower-than-standard particulate matter air pollution reduced life expectancy in Hong Kong: A time-series analysis of 8.5 million years of life lost.

Chemosphere·2021
Same author

Pemetrexed-based first-line chemotherapy had particularly prominent objective response rate for advanced NSCLC: A network meta-analysis.

Open medicine (Warsaw, Poland)·2021

相关实验视频

Updated: May 1, 2026

Comparing the Frequency Effect Between the Lexical Decision and Naming Tasks in Chinese
08:08

Comparing the Frequency Effect Between the Lexical Decision and Naming Tasks in Chinese

Published on: April 1, 2016

9.3K

来自变压器的顺序词典增强双向编码器表示:使用顺序词典增强BERT的中文命名实体识别.

Xin Liu1, Jiashan Zhao2, Junping Yao1

  • 1Department of Basic, Xi'an Research Institute of High-Tech, Xi'an, Shaanxi, China.

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

序列词典增强的BERT (SLEBERT) 通过减少噪音和冲突来改善中文命名实体识别 (NER). 这种新的方法增强了词汇特征,在性能和效率方面超过了以前的方法.

关键词:
适应性注意力是一种适应性注意力.贝尔特 (BERT) 公司中国的NER是中国的NER.词汇增强的词汇增强

更多相关视频

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology
05:38

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Published on: June 29, 2021

2.3K
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

1.4K

相关实验视频

Last Updated: May 1, 2026

Comparing the Frequency Effect Between the Lexical Decision and Naming Tasks in Chinese
08:08

Comparing the Frequency Effect Between the Lexical Decision and Naming Tasks in Chinese

Published on: April 1, 2016

9.3K
Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology
05:38

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Published on: June 29, 2021

2.3K
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

1.4K

科学领域:

  • 自然语言处理自然语言处理.
  • 人工智能的人工智能
  • 计算语言学 计算语言学

背景情况:

  • 词典从变压器 (LEBERT) 的增强双向编码器表示已经在中国命名实体识别 (NER) 中取得了成功.
  • 勒伯特的词典适配器层融合了词典知识,但可能会引入噪音,无法解决单词冲突.
  • 现有的方法缺乏强大的机制来处理词汇噪声和单词间冲突.

研究的目的:

  • 引入一种新的词汇增强方法,即序列词典增强BERT (SLEBERT),用于中文NER.
  • 解决LEBERT的局限性,特别是噪音词引入和词汇冲突.
  • 通过加强词汇集成,提高中文NER的性能和效率.

主要方法:

  • 开发了SLEBERT,该模型构建了一个序列词典,以减轻噪音和解决冲突.
  • 嵌入了序列词典的位置编码,以增强特征表示.
  • 在序列词典中利用了适应性注意力机制,以改善特征融合.

主要成果:

  • 与现有的词汇增强模型相比,SLEBERT 在四个中国NER数据集上表现出优异的性能.
  • 提出的顺序词典方法有效地减少了词语噪音,并解决了词汇冲突.
  • 斯莱伯特在加工和特征提取方面实现了更高的效率.

结论:

  • 斯莱伯特为中文NER提供了一种更有效和高效的词汇增强方法.
  • 顺序词汇策略成功克服了与以前方法中的噪音和冲突相关的局限性.
  • 在将词汇知识应用于NER的深度学习模型方面,SLEBERT代表了重大进展.