Text data augmentations: Permutation, antonyms and negation

Giannis Haralabopoulos,Mercedes Torres Torres,Ioannis Anagnostopoulos,Derek McAuley

Expert Systems with Applications（2021）

引用 20|浏览39

暂无评分

摘要

•Three novel text data augmentation techniques.•Accuracy improvement across eight datasets, 4.1%.•TF-IDF filtering•Max accuracy reduction 2.08%.•Minimum training time reduction 212%.

查看译文

关键词

Text,Augmentation,Multilabel,Multiclass,LSTM

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要