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

TL;DR

This paper introduces a semi-supervised CNN framework that learns region embeddings from unlabeled data to improve text categorization, outperforming previous methods in sentiment and topic classification.

Contribution

It proposes a novel semi-supervised approach that learns region embeddings from unlabeled data for CNN-based text categorization, differing from prior word embedding methods.

Findings

Achieved better results than previous approaches on sentiment classification.

Improved performance on topic classification tasks.

Demonstrated effectiveness of region embeddings learned from unlabeled data.

Abstract

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.