Shuffle & Divide: Contrastive Learning for Long Text
This method reduces the need for expensive human labeling in AI by enabling effective unsupervised classification of long text documents, though it appears incremental as it builds on existing contrastive learning and BERT-based approaches.
The paper tackles the problem of unsupervised text classification for long documents by proposing a self-supervised contrastive learning method with a Shuffle and Divide augmentation algorithm, achieving state-of-the-art results including a 20.94% accuracy improvement on the 20 Newsgroups dataset and over 95% accuracy on BBC datasets.
We propose a self-supervised learning method for long text documents based on contrastive learning. A key to our method is Shuffle and Divide (SaD), a simple text augmentation algorithm that sets up a pretext task required for contrastive updates to BERT-based document embedding. SaD splits a document into two sub-documents containing randomly shuffled words in the entire documents. The sub-documents are considered positive examples, leaving all other documents in the corpus as negatives. After SaD, we repeat the contrastive update and clustering phases until convergence. It is naturally a time-consuming, cumbersome task to label text documents, and our method can help alleviate human efforts, which are most expensive resources in AI. We have empirically evaluated our method by performing unsupervised text classification on the 20 Newsgroups, Reuters-21578, BBC, and BBCSport datasets. In particular, our method pushes the current state-of-the-art, SS-SB-MT, on 20 Newsgroups by 20.94% in accuracy. We also achieve the state-of-the-art performance on Reuters-21578 and exceptionally-high accuracy performances (over 95%) for unsupervised classification on the BBC and BBCSport datasets.