Text Classification based on Multiple Block Convolutional Highways

Abstract

In the Text Classification areas of Sentiment Analysis, Subjectivity/Objectivity Analysis, and Opinion Polarity, Convolutional Neural Networks have gained special attention because of their performance and accuracy. In this work, we applied recent advances in CNNs and propose a novel architecture, Multiple Block Convolutional Highways (MBCH), which achieves improved accuracy on multiple popular benchmark datasets, compared to previous architectures. The MBCH is based on new techniques and architectures including highway networks, DenseNet, batch normalization and bottleneck layers. In addition, to cope with the limitations of existing pre-trained word vectors which are used as inputs for the CNN, we propose a novel method, Improved Word Vectors (IWV). The IWV improves the accuracy of CNNs which are used for text classification tasks.

arXiv commentarXiv admin note: text overlap with arXiv:1711.08609

References in corpus (13)

• Efficient Estimation of Word Representations in Vector Space
• Natural Language Processing (almost) from Scratch
• Deep Residual Learning for Image Recognition
• Character-level Convolutional Networks for Text Classification
• Semantics derived automatically from language corpora contain human-like biases
• Training Very Deep Networks
• Convolutional Neural Networks for Sentence Classification
• A Convolutional Neural Network for Modelling Sentences
• ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
• A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification
• Encoding Source Language with Convolutional Neural Network for Machine Translation
• Highway Long Short-Term Memory RNNs for Distant Speech Recognition
• Very Deep Convolutional Networks for End-to-End Speech Recognition