Hybrid Tiled Convolutional Neural Networks for Text Sentiment Classification

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.

8 pages, 2 figures, accepted for publication in the 12th International Conference on Agents and Artificial Intelligence (ICAART 2020), Malta, 22-24 February 2020

References in corpus (11)

• Natural Language Processing (almost) from Scratch
• Convolutional Neural Networks for Sentence Classification
• Comparative Study of CNN and RNN for Natural Language Processing
• An Experimental Comparison of Several Clustering and Initialization Methods
• Applying Deep Learning to Answer Selection: A Study and An Open Task
• Learning text representation using recurrent convolutional neural network with highway layers
• MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification
• Lexicon Integrated CNN Models with Attention for Sentiment Analysis
• Exploring Different Dimensions of Attention for Uncertainty Detection
• Parameterized Convolutional Neural Networks for Aspect Level Sentiment Classification
• Constructing a Word Similarity Graph from Vector based Word Representation for Named Entity Recognition