Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding
This addresses text categorization for NLP applications, but it is incremental as it builds on existing CNN and semi-supervised learning approaches.
The paper tackles text categorization by introducing a semi-supervised CNN framework that learns embeddings of small text regions from unlabeled data, achieving better results than previous methods on sentiment and topic classification tasks.
This paper presents a new semi-supervised framework with convolutional neural networks (CNNs) for text categorization. Unlike the previous approaches that rely on word embeddings, our method learns embeddings of small text regions from unlabeled data for integration into a supervised CNN. The proposed scheme for embedding learning is based on the idea of two-view semi-supervised learning, which is intended to be useful for the task of interest even though the training is done on unlabeled data. Our models achieve better results than previous approaches on sentiment classification and topic classification tasks.