Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification
This work addresses data scarcity for document classification tasks in multiple languages, but it is incremental as it combines existing techniques rather than introducing a fundamentally new approach.
The paper tackled the problem of labeled data shortage in document classification by combining semi-supervised deep generative models with multi-lingual pretraining, resulting in a framework that outperforms state-of-the-art methods in low-resource settings across multiple languages.
Semi-supervised learning through deep generative models and multi-lingual pretraining techniques have orchestrated tremendous success across different areas of NLP. Nonetheless, their development has happened in isolation, while the combination of both could potentially be effective for tackling task-specific labelled data shortage. To bridge this gap, we combine semi-supervised deep generative models and multi-lingual pretraining to form a pipeline for document classification task. Compared to strong supervised learning baselines, our semi-supervised classification framework is highly competitive and outperforms the state-of-the-art counterparts in low-resource settings across several languages.