Text Classification based on Multiple Block Convolutional Highways
This work addresses text classification problems for NLP researchers, but it appears incremental as it builds on existing CNN techniques.
The authors tackled text classification tasks like sentiment analysis by proposing a new architecture, Multiple Block Convolutional Highways (MBCH), and an improved word vector method (IWV), achieving improved accuracy on multiple benchmark datasets.
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.