Squeezed Very Deep Convolutional Neural Networks for Text Classification

28 Jan 2019Andréa B. DuqueLuã Lázaro J. SantosDavid MacêdoCleber Zanchettin

Most of the research in convolutional neural networks has focused on increasing network depth to improve accuracy, resulting in a massive number of parameters which restricts the trained network to platforms with memory and processing constraints. We propose to modify the structure of the Very Deep Convolutional Neural Networks (VDCNN) model to fit mobile platforms constraints and keep performance... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Text Classification AG News SVDCNN Error 9.45 # 18
Sentiment Analysis Yelp Binary classification SVDCNN Error 4.74 # 15
Sentiment Analysis Yelp Fine-grained classification SVDCNN Error 46.80 # 14

Methods used in the Paper