Rank-Aware Negative Training for Semi-Supervised Text Classification

TL;DR

This paper introduces a Rank-aware Negative Training framework for semi-supervised text classification that effectively handles noisy pseudo-labels by ranking unlabeled data and using negative training, leading to improved performance over existing methods.

Contribution

The paper proposes a novel Rank-aware Negative Training approach that incorporates uncertainty-based ranking and negative training to enhance semi-supervised text classification.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effectively reduces noise impact in pseudo-labeling

Achieves competitive results in various scenarios

Abstract

Semi-supervised text classification-based paradigms (SSTC) typically employ the spirit of self-training. The key idea is to train a deep classifier on limited labeled texts and then iteratively predict the unlabeled texts as their pseudo-labels for further training. However, the performance is largely affected by the accuracy of pseudo-labels, which may not be significant in real-world scenarios. This paper presents a Rank-aware Negative Training (RNT) framework to address SSTC in learning with noisy label manner. To alleviate the noisy information, we adapt a reasoning with uncertainty-based approach to rank the unlabeled texts based on the evidential support received from the labeled texts. Moreover, we propose the use of negative training to train RNT based on the concept that ``the input instance does not belong to the complementary label''. A complementary label is randomly selected from all labels except the label on-target. Intuitively, the probability of a true label serving as a complementary label is low and thus provides less noisy information during the training, resulting in better performance on the test data. Finally, we evaluate the proposed solution on various text classification benchmark datasets. Our extensive experiments show that it consistently overcomes the state-of-the-art alternatives in most scenarios and achieves competitive performance in the others. The code of RNT is publicly available at:https://github.com/amurtadha/RNT.