A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification

TL;DR

This paper investigates how sensitive one-layer CNNs are to architectural choices in sentence classification, providing practical guidance for practitioners to optimize model performance.

Contribution

It conducts a comprehensive sensitivity analysis of one-layer CNNs, identifying key design decisions affecting performance in sentence classification tasks.

Findings

Certain hyperparameters significantly impact accuracy

Some architectural choices are less influential

Practical recommendations for model tuning are provided

Abstract

Convolutional Neural Networks (CNNs) have recently achieved remarkably strong performance on the practically important task of sentence classification (kim 2014, kalchbrenner 2014, johnson 2014). However, these models require practitioners to specify an exact model architecture and set accompanying hyperparameters, including the filter region size, regularization parameters, and so on. It is currently unknown how sensitive model performance is to changes in these configurations for the task of sentence classification. We thus conduct a sensitivity analysis of one-layer CNNs to explore the effect of architecture components on model performance; our aim is to distinguish between important and comparatively inconsequential design decisions for sentence classification. We focus on one-layer CNNs (to the exclusion of more complex models) due to their comparative simplicity and strong empirical performance, which makes it a modern standard baseline method akin to Support Vector Machine (SVMs) and logistic regression. We derive practical advice from our extensive empirical results for those interested in getting the most out of CNNs for sentence classification in real world settings.