Revisiting the Role of Label Smoothing in Enhanced Text Sentiment Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Yijie, Si, Shijing, Luo, Hua, Sun, Haixia, Zhang, Yugui
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913241006866432
author Gao, Yijie
Si, Shijing
Luo, Hua
Sun, Haixia
Zhang, Yugui
author_facet Gao, Yijie
Si, Shijing
Luo, Hua
Sun, Haixia
Zhang, Yugui
contents Label smoothing is a widely used technique in various domains, such as text classification, image classification and speech recognition, known for effectively combating model overfitting. However, there is little fine-grained analysis on how label smoothing enhances text sentiment classification. To fill in the gap, this article performs a set of in-depth analyses on eight datasets for text sentiment classification and three deep learning architectures: TextCNN, BERT, and RoBERTa, under two learning schemes: training from scratch and fine-tuning. By tuning the smoothing parameters, we can achieve improved performance on almost all datasets for each model architecture. We further investigate the benefits of label smoothing, finding that label smoothing can accelerate the convergence of deep models and make samples of different labels easily distinguishable.
format Preprint
id arxiv_https___arxiv_org_abs_2312_06522
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Revisiting the Role of Label Smoothing in Enhanced Text Sentiment Classification
Gao, Yijie
Si, Shijing
Luo, Hua
Sun, Haixia
Zhang, Yugui
Computation and Language
Artificial Intelligence
Machine Learning
Label smoothing is a widely used technique in various domains, such as text classification, image classification and speech recognition, known for effectively combating model overfitting. However, there is little fine-grained analysis on how label smoothing enhances text sentiment classification. To fill in the gap, this article performs a set of in-depth analyses on eight datasets for text sentiment classification and three deep learning architectures: TextCNN, BERT, and RoBERTa, under two learning schemes: training from scratch and fine-tuning. By tuning the smoothing parameters, we can achieve improved performance on almost all datasets for each model architecture. We further investigate the benefits of label smoothing, finding that label smoothing can accelerate the convergence of deep models and make samples of different labels easily distinguishable.
title Revisiting the Role of Label Smoothing in Enhanced Text Sentiment Classification
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2312.06522