Convolutional Neural Networks for Sentence Classification

Abstract

We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vectors for sentence-level classification tasks. We show that a simple CNN with little hyperparameter tuning and static vectors achieves excellent results on multiple benchmarks. Learning task-specific vectors through fine-tuning offers further gains in performance. We additionally propose a simple modification to the architecture to allow for the use of both task-specific and static vectors. The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification.

To appear in EMNLP 2014

References in corpus (4)

• Improving neural networks by preventing co-adaptation of feature detectors
• ADADELTA: An Adaptive Learning Rate Method
• Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales
• A Convolutional Neural Network for Modelling Sentences

Cited by in corpus (21)

• Hierarchical Multiscale Recurrent Neural Networks
• Deep Learning and Its Applications to Machine Health Monitoring: A Survey
• dna2vec: Consistent vector representations of variable-length k-mers
• Joint Deep Modeling of Users and Items Using Reviews for Recommendation
• Discriminative Neural Sentence Modeling by Tree-Based Convolution
• Automatic Rule Extraction from Long Short Term Memory Networks
• Interpretation of Prediction Models Using the Input Gradient
• Learning to Decode for Future Success
• Neural Information Retrieval: A Literature Review
• Neural Models for Sequence Chunking
• Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
• Deep Multi-Task Learning with Shared Memory
• Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networks
• Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
• Word Embeddings and Their Use In Sentence Classification Tasks
• Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks
• Comparing Rule-Based and Deep Learning Models for Patient Phenotyping
• Character-level Convolutional Network for Text Classification Applied to Chinese Corpus
• Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding
• A Multichannel Convolutional Neural Network For Cross-language Dialog State Tracking
• Search Intelligence: Deep Learning For Dominant Category Prediction