您当前的位置：
首页 >
文章列表页 >
Research on Data Augmentation for Extractive Reading Comprehension
更新时间：2024-06-27
|

    • Research on Data Augmentation for Extractive Reading Comprehension

    • “在抽取式阅读理解领域，针对语言模型在训练数据不足时表现不佳的问题，研究者提出了一种基于语义相似度的数据增强方法（DASS），通过单词级和句子级数据增强，在保留问题正确答案的同时，提升训练数据质量，增强模型鲁棒性。实验结果表明，DASS能有效解决模型在样本数量较少时获取语义信息不足的问题，显著提升了模型预测的F1值。”
      ”
    • Software Guide   Vol. 23, Issue 6, Pages: 32-37(2024)

    • DOI：10.11907/rjdk.231137    

      CLC： TP391

    • Published：15 June 2024，

      Received：31 May 2023，

    扫 描 看 全 文

  • HU Xinrong,XU Wei,LUO Ruiqi,et al.Research on Data Augmentation for Extractive Reading Comprehension[J].Software Guide,2024,23(06):32-37. DOI： 10.11907/rjdk.231137.

  •  
  •  

0

Views

0

下载量

0

CSCD

Alert me when the article has been cited
提交
Tools
Download
Export Citation
Share
Add to favorites
Add to my album

Related Articles

A Faster R-CNN Small Object Detection Algorithm Based on Circular Anchor
Construction and Application of the Policy Event Logic Graph
Research on Runtime Hotspot Data and Its Collection System for Industrial Control Cloud Service Optimization
Attention-based Ship Classification in Remote Sensing Images

Related Author

YAN Chunxiang
XU Zunyi
LIU Kangning
LI Chen
XU Qinya
YU Lu
LIU Kan
LIU Sichun

Related Institution

College of Computer Science and Technology， Shandong Jianzhu University， Ji'nan
School of Information and Safety Engineering， Zhongnan University of Economics and Law
Institute of Electronic and Information Engineering， Tongji University
Institute of Software， Chinese Academy of Sciences
School of Computer Science， Jiangsu University of Science and Technology
0