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

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.

Cited by in corpus (15)

• TextBugger: Generating Adversarial Text Against Real-world Applications
• Improving the Accuracy of Pre-trained Word Embeddings for Sentiment Analysis
• Convolutional Neural Network: Text Classification Model for Open Domain Question Answering System
• What Makes a Good TODO Comment?
• Argument Identification in Public Comments from eRulemaking
• CB2CF: A Neural Multiview Content-to-Collaborative Filtering Model for Completely Cold Item Recommendations
• Multi Task Deep Morphological Analyzer: Context Aware Joint Morphological Tagging and Lemma Prediction
• Open Loop Hyperparameter Optimization and Determinantal Point Processes
• Solar cell patent classification method based on keyword extraction and deep neural network
• Convolutional Neural Networks for Sentiment Analysis in Persian Social Media
• User Preference-aware Fake News Detection
• CNN Application in Detection of Privileged Documents in Legal Document Review
• Exploring Neural Net Augmentation to BERT for Question Answering on SQUAD 2.0
• Fairness-aware Summarization for Justified Decision-Making
• Text Classification based on Multiple Block Convolutional Highways