Convolutional Neural Networks for Sentence Classification

TL;DR

This paper demonstrates that convolutional neural networks with pre-trained word vectors can effectively perform sentence classification, achieving state-of-the-art results on multiple benchmarks with minimal tuning.

Contribution

It introduces a simple CNN architecture that leverages static and fine-tuned word vectors for improved sentence classification performance.

Findings

Achieved state-of-the-art results on 4 out of 7 tasks

Simple CNN with minimal hyperparameter tuning is highly effective

Fine-tuning word vectors further improves performance

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.