ZeroBERTo: Leveraging Zero-Shot Text Classification by Topic Modeling
Abstract
Traditional text classification approaches often require a good amount of labeled data, which is difficult to obtain, especially in restricted domains or less widespread languages. This lack of labeled data has led to the rise of low-resource methods, that assume low data availability in natural language processing. Among them, zero-shot learning stands out, which consists of learning a classifier without any previously labeled data. The best results reported with this approach use language models such as Transformers, but fall into two problems: high execution time and inability to handle long texts as input. This paper proposes a new model, ZeroBERTo, which leverages an unsupervised clustering step to obtain a compressed data representation before the classification task. We show that ZeroBERTo has better performance for long inputs and shorter execution time, outperforming XLM-R by about 12% in the F1 score in the FolhaUOL dataset. Keywords: Low-Resource NLP, Unlabeled data, Zero-Shot Learning, Topic Modeling, Transformers.
Cite
@article{arxiv.2201.01337,
title = {ZeroBERTo: Leveraging Zero-Shot Text Classification by Topic Modeling},
author = {Alexandre Alcoforado and Thomas Palmeira Ferraz and Rodrigo Gerber and Enzo Bustos and André Seidel Oliveira and Bruno Miguel Veloso and Fabio Levy Siqueira and Anna Helena Reali Costa},
journal= {arXiv preprint arXiv:2201.01337},
year = {2022}
}
Comments
Accepted at PROPOR 2022: 15th International Conference on Computational Processing of Portuguese