English

FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification

Computation and Language 2022-12-16 v2

Abstract

Weakly-supervised text classification aims to train a classifier using only class descriptions and unlabeled data. Recent research shows that keyword-driven methods can achieve state-of-the-art performance on various tasks. However, these methods not only rely on carefully-crafted class descriptions to obtain class-specific keywords but also require substantial amount of unlabeled data and takes a long time to train. This paper proposes FastClass, an efficient weakly-supervised classification approach. It uses dense text representation to retrieve class-relevant documents from external unlabeled corpus and selects an optimal subset to train a classifier. Compared to keyword-driven methods, our approach is less reliant on initial class descriptions as it no longer needs to expand each class description into a set of class-specific keywords. Experiments on a wide range of classification tasks show that the proposed approach frequently outperforms keyword-driven models in terms of classification accuracy and often enjoys orders-of-magnitude faster training speed.

Keywords

Cite

@article{arxiv.2212.05506,
  title  = {FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification},
  author = {Tingyu Xia and Yue Wang and Yuan Tian and Yi Chang},
  journal= {arXiv preprint arXiv:2212.05506},
  year   = {2022}
}

Comments

EMNLP 2022

R2 v1 2026-06-28T07:29:44.437Z