paper-with-me

홈 › Papers

Improving short text classification through global augmentation methods

2019-07-07 · Vukosi Marivate, Tshephisho Sefara

We study the effect of different approaches to text augmentation. To do this we use 3 datasets that include social media and formal text in the form of news articles. Our goal is to provide insights for practitioners and researchers on making choices for augmentation for classification use cases. We observe that Word2vec-based augmentation is a viable option when one does not have access to a formal synonym model (like WordNet-based augmentation). The use of \emph{mixup} further improves performance of all text based augmentations and reduces the effects of overfitting on a tested deep learning model. Round-trip translation with a translation service proves to be harder to use due to cost and as such is less accessible for both normal and low resource use-cases.

📄 PDF Abstract BibTeX arXiv:1907.03752

Code (1)

dsfsi/textaugment 공식 구현 tf

Tasks

ArticlesClassificationGeneral ClassificationText Augmentationtext-classificationText ClassificationTranslation

Similar Papers 제목 키워드 기반

Optimizing Small Transformer-Based Language Models for Multi-Label Sentiment Analysis in Short Texts

2025-09-05 · Julius Neumann, Robert Lange, Yuni Susanti, Michael Färber arxiv

Sentiment classification in short text datasets faces significant challenges such as class imbalance, limited training samples, and the inherent subjectivity of sentiment labels -- issues that are further intensified by …

Sentiment AnalysisData Augmentation

A Simple Graph Contrastive Learning Framework for Short Text Classification

2025-01-16 · Yonghao Liu, Fausto Giunchiglia, Lan Huang, Ximing Li 외

Short text classification has gained significant attention in the information age due to its prevalence and real-world applications. Recent advancements in graph learning combined with contrastive learning have shown pro…

Contrastive LearningData AugmentationGraph Learningtext-classification+1

Low resource language dataset creation, curation and classification: Setswana and Sepedi -- Extended Abstract

2020-03-30 · Vukosi Marivate, Tshephisho Sefara, Vongani Chabalala, Keamogetswe Makhaya 외

The recent advances in Natural Language Processing have only been a boon for well represented languages, negating research in lesser known global languages. This is in part due to the availability of curated data and res…

Data AugmentationGeneral ClassificationTopic Classification

The Effectiveness of Data Augmentation in Image Classification using Deep Learning

2017-12-13 · Luis Perez, Jason Wang

In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such …

Data AugmentationGeneral Classificationimage-classificationImage Classification

From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection

2025-05-19 · Lincan Cai, Jingxuan Kang, Shuang Li, Wenxuan Ma 외

Pretrained vision-language models (VLMs), e.g., CLIP, demonstrate impressive zero-shot capabilities on downstream tasks. Prior research highlights the crucial role of visual augmentation techniques, like random cropping,…

feature selectionOut-of-Distribution GeneralizationTest-time Adaptationzero-shot-classification+1