.png){kind=icon}
返回
Learning policy scheduling for text augmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2021.09.028.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
When training deep learning models, data augmentation is an important technique to improve the performance and alleviate overfitting. In natural language processing (NLP), existing augmentation methods often use fixed strategies. However, it might be preferred to use different augmentation policies in different stage of training, and different datasets may require different augmentation policies. In this paper, we take dynamic policy scheduling into consideration. We design a search space over augmentation policies by integrating several common augmentation operations. Then, we adopt a population based training method to search the best augmentation schedule. We conduct extensive experiments on five text classification and two machine translation tasks. The results show that the optimized dynamic augmentation schedules achieve significant improvements against previous methods. (C) 2021 Elsevier Ltd. All rights reserved.
Keyword:
Data augmentation
Text classification
期刊
IF:
6.3
论文数:
8.3K
被引数:
3.0W
机构
引用论文
.png){kind=icon}
Cobalt and Copper Composite Oxides as Efficient Catalysts for Preferential Oxidation of CO in H2-Rich Stream钴和铜复合氧化物作为H2-Rich流中CO优先氧化的有效催化剂
PREAI
分享收藏Developing Wind and/or Solar Powered Crop Irrigation Systems for the Great Plains为大平原开发风能和/或太阳能作物灌溉系统
PREAI
分享收藏分享收藏 没有更多内容
没有更多内容