Convolutional Neural Networks for Text Categorization: Shallow Word-level vs. Deep Character-level

Abstract

This paper reports the performances of shallow word-level convolutional neural networks (CNN), our earlier work (2015), on the eight datasets with relatively large training data that were used for testing the very deep character-level CNN in Conneau et al. (2016). Our findings are as follows. The shallow word-level CNNs achieve better error rates than the error rates reported in Conneau et al., though the results should be interpreted with some consideration due to the unique pre-processing of Conneau et al. The shallow word-level CNN uses more parameters and therefore requires more storage than the deep character-level CNN; however, the shallow word-level CNN computes much faster.

Cited by in corpus (6)

• Deep Learning-based Sentiment Classification: A Comparative Survey
• Hash Embeddings for Efficient Word Representations
• A Data-driven Neural Network Architecture for Sentiment Analysis
• Empirical Comparisons of CNN with Other Learning Algorithms for Text Classification in Legal Document Review
• Evolving Character-level Convolutional Neural Networks for Text Classification
• FineText: Text Classification via Attention-based Language Model Fine-tuning