READ: Reinforcement-based Adversarial Learning for Text Classification with Limited Labeled Data
Year: 2025
Type: preprint
Abstract: Pre-trained transformer models such as BERT have shown massive gains across many text classification tasks. However, these models usually need enormous labeled data to achieve impressive performances. Obtaining labeled data is often expensive and time-consuming, whereas collecting unlabeled data using some heuristics is relatively much cheaper for any task. Therefore, this paper proposes a method that encapsulates reinforcement learning-based text generation and semi-supervised adversarial learning approaches in a novel way to improve the model's performance. Our method READ, Reinforcement-based Adversarial learning, utilizes an unlabeled dataset to generate diverse synthetic text through reinforcement learning, improving the model's generalization capability using adversarial learning. Our experimental results show that READ outperforms the existing state-of-art methods on multiple datasets.
Source: arXiv (Cornell University)
Authors: Sharma, Rohit, Kumar, Shanu, Kumar, Avinash
Institution: Microsoft (India)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4406449677