STTA: enhanced text classification via selective test-time augmentation

STTA: enhanced text classification via selective test-time augmentation

Test-time augmentation (TTA) is a well-established technique that involves aggregating transformed examples of test inputs during the inference stage. The goal is to enhance model performance and reduce the uncertainty of predictions. Despite its advantages of not requiring additional training or hy...

Full description

Bibliographic Details
Main Authors: Haoyu Xiong, Xinchun Zhang, Leixin Yang, Yu Xiang, Yaping Zhang
Format: Article
Language:English
Published: PeerJ Inc. 2023-12-01
Series:PeerJ Computer Science
Subjects:
Text classification
Sentiment analysis
Data augmentation
Language model
Sentiment classification
Test-time augmentation
Online Access:https://peerj.com/articles/cs-1757.pdf

Internet

https://peerj.com/articles/cs-1757.pdf

Similar Items