.png){kind=icon}
返回
Data augmentation using virtual word insertion techniques in text classification tasks
.png){kind=icon}
PRE
AI
DOI：10.1111/exsy.13519.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Labelling multiple training examples for text classification models is usually time-consuming and complex. Data augmentation can be used to automatically expand the dataset by transforming the original data. However, it may cause semantic changes without modifying the labels, which reduces the effectiveness of the classifiers. In this paper, we propose a data-augmentation method called the virtual word insertion technique, which generates new sentences by randomly inserting virtual words into existing sentences. Two methods are used to achieve virtual word embedding: unweighted average and weighted average. Furthermore, a new concept of weight is proposed: the class deviation factor, which demonstrates the correlation between words and classes. Based on this new concept, different weights are assigned to words of different classes. Experiments are conducted on five different classification tasks. Ablation experiments are also performed to explore the effects of random operation and number of augmented sentences for classification results. The results of these experiments show that our method improves the classification performance and outperforms two other contrasting data-augmentation methods in automatically augmenting the dataset. Compared to raw datasets, the average accuracy improvement of our method is 3.5% for a small-scale dataset and 1% for a large-scale dataset.
Keyword:
class deviation factor
data augmentation
text classification
virtual word insertion techniques
期刊
IF:
2.3
论文数:
2.6K
被引数:
3.8K
机构
引用论文
分享收藏
Wearable ECG for Real Time Complex P-QRS-T Detection and Classification of Various Arrhythmias可穿戴ECG用于实时复杂P-QRS-T检测和各种心律失常的分类
PREAI
分享收藏THE PENETRATION EFFECTS ON TANDEM-X ELEVATION USING THE GNSS AND LASER ALTIMETRY MEASUREMENTS IN ANTARCTICA.png)
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
OAAI
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesIF0
OAAI分享收藏
查看更多内容