Hybrid Tiled Convolutional Neural Networks for Text Sentiment Classification

TL;DR

This paper introduces a hybrid tiled CNN architecture tailored for NLP sentiment analysis, enhancing feature extraction and outperforming traditional CNNs and tiled CNNs on benchmark datasets.

Contribution

The paper proposes a novel hybrid tiled CNN architecture that applies filters selectively to improve feature extraction in NLP sentiment classification.

Findings

Hybrid tiled CNN outperforms CNN and tiled CNN on IMDB and SemEval datasets.

The architecture effectively captures salient features for sentiment analysis.

Improved accuracy demonstrates the model's effectiveness.

Abstract

The tiled convolutional neural network (tiled CNN) has been applied only to computer vision for learning invariances. We adjust its architecture to NLP to improve the extraction of the most salient features for sentiment analysis. Knowing that the major drawback of the tiled CNN in the NLP field is its inflexible filter structure, we propose a novel architecture called hybrid tiled CNN that applies a filter only on the words that appear in the similar contexts and on their neighbor words (a necessary step for preventing the loss of some n-grams). The experiments on the datasets of IMDB movie reviews and SemEval 2017 demonstrate the efficiency of the hybrid tiled CNN that performs better than both CNN and tiled CNN.