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

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.

References in corpus (3)

• Improving neural networks by preventing co-adaptation of feature detectors
• Going Deeper with Convolutions
• Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews

Cited by in corpus (27)

• Quasi-Recurrent Neural Networks
• Representation Learning for Natural Language Processing
• Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function
• Deep Learning Sentiment Analysis of Amazon.com Reviews and Ratings
• Multi-Label Classification of Patient Notes a Case Study on ICD Code Assignment
• Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications
• Structural block driven - enhanced convolutional neural representation for relation extraction
• Fishing for Clickbaits in Social Images and Texts with Linguistically-Infused Neural Network Models
• Joint Text Embedding for Personalized Content-based Recommendation
• SeMemNN: A Semantic Matrix-Based Memory Neural Network for Text Classification
• Syntactic Recurrent Neural Network for Authorship Attribution
• A Data-driven Neural Network Architecture for Sentiment Analysis
• GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training
• Literature review on vulnerability detection using NLP technology
• Convolutional Neural Networks for Sentiment Classification on Business Reviews
• Empirical Comparisons of CNN with Other Learning Algorithms for Text Classification in Legal Document Review
• Visual and Textual Sentiment Analysis Using Deep Fusion Convolutional Neural Networks
• Light-Weighted CNN for Text Classification
• Learning Semantically Coherent and Reusable Kernels in Convolution Neural Nets for Sentence Classification
• Article citation study: Context enhanced citation sentiment detection
• Contextual and Position-Aware Factorization Machines for Sentiment Classification
• Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis
• RISC-NN: Use RISC, NOT CISC as Neural Network Hardware Infrastructure
• Ranking-Based Autoencoder for Extreme Multi-label Classification
• CNN Application in Detection of Privileged Documents in Legal Document Review
• Text Classification with Lexicon from PreAttention Mechanism
• Search Intelligence: Deep Learning For Dominant Category Prediction