Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding. Article Swipe

View

Related Concepts

Categorization Computer science Convolutional neural network Artificial intelligence Embedding Word embedding Task (project management) Machine learning Labeled data Supervised learning Word (group theory) Text categorization Scheme (mathematics) Semi-supervised learning Natural language processing Pattern recognition (psychology) Artificial neural network Mathematics Geometry Economics Mathematical analysis Management

Rie Johnson , Tong Zhang ·

YOU? · · 2015 · Open Access · · OA: W1810499140

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.