Effects of padding on LSTMs and CNNs

TL;DR

This paper investigates how different padding strategies affect the performance of LSTM and CNN models in sentiment analysis, providing guidelines for optimal padding techniques.

Contribution

It systematically compares padding methods for LSTMs and CNNs using a sentiment analysis task, offering practical recommendations for preprocessing.

Findings

Padding significantly impacts model accuracy and performance.

Optimal padding strategies vary between LSTMs and CNNs.

Preprocessing techniques can enhance model effectiveness.

Abstract

Long Short-Term Memory (LSTM) Networks and Convolutional Neural Networks (CNN) have become very common and are used in many fields as they were effective in solving many problems where the general neural networks were inefficient. They were applied to various problems mostly related to images and sequences. Since LSTMs and CNNs take inputs of the same length and dimension, input images and sequences are padded to maximum length while testing and training. This padding can affect the way the networks function and can make a great deal when it comes to performance and accuracies. This paper studies this and suggests the best way to pad an input sequence. This paper uses a simple sentiment analysis task for this purpose. We use the same dataset on both the networks with various padding to show the difference. This paper also discusses some preprocessing techniques done on the data to ensure effective analysis of the data.