Effective Use of Word Order for Text Categorization with Convolutional Neural Networks

TL;DR

This paper explores the application of convolutional neural networks to text categorization, leveraging word order and local text structures for improved accuracy, introducing a novel bag-of-words convolution variation and multi-layer extensions.

Contribution

It introduces a new CNN-based approach for text classification that directly models high-dimensional text data and incorporates a bag-of-words convolution variation and multi-layer configurations.

Findings

CNN effectively captures word order in text classification

Proposed bag-of-words convolution improves accuracy

Multi-layer CNN further enhances performance

Abstract

Convolutional neural network (CNN) is a neural network that can make use of the internal structure of data such as the 2D structure of image data. This paper studies CNN on text categorization to exploit the 1D structure (namely, word order) of text data for accurate prediction. Instead of using low-dimensional word vectors as input as is often done, we directly apply CNN to high-dimensional text data, which leads to directly learning embedding of small text regions for use in classification. In addition to a straightforward adaptation of CNN from image to text, a simple but new variation which employs bag-of-word conversion in the convolution layer is proposed. An extension to combine multiple convolution layers is also explored for higher accuracy. The experiments demonstrate the effectiveness of our approach in comparison with state-of-the-art methods.