TABAS: Text augmentation based on attention score for text classification model
To improve the performance of text classification, we propose text augmentation based on attention score (TABAS). We recognized that a criterion for selecting a replacement word rather than a random selection was necessary. Therefore, TABAS utilizes attention scores for text modification, processing...
Main Authors: | Yeong Jae Yu, Seung Joo Yoon, So Young Jun, Jong Woo Kim |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-12-01
|
Series: | ICT Express |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405959521001454 |
Similar Items
-
LiDA: Language-Independent Data Augmentation for Text Classification
by: Yudianto Sujana, et al.
Published: (2023-01-01) -
STTA: enhanced text classification via selective test-time augmentation
by: Haoyu Xiong, et al.
Published: (2023-12-01) -
An enhanced text classification model by the inverted attention orthogonal projection module
by: Hong Zhao, et al.
Published: (2023-12-01) -
A Submodular Optimization Framework for Imbalanced Text Classification With Data Augmentation
by: Eyor Alemayehu, et al.
Published: (2023-01-01) -
Data Augmentation Methods for Enhancing Robustness in Text Classification Tasks
by: Huidong Tang, et al.
Published: (2023-01-01)