Convolutional Neural Networks for Sentence Classification

Code

• github.com/facebookresearch/pytext
  pytorch★ 6,305
• github.com/dennybritz/cnn-text-classification-tf
  tf★ 5,684
• github.com/prakashpandey9/Text-Classification-Pytorch
  pytorch★ 818
• github.com/inspirehep/magpie
  none★ 688
• github.com/alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras
  tf★ 595
• github.com/threelittlemonkeys/cnn-text-classification-pytorch
  pytorch★ 21
• github.com/plkumjorn/FIND
  tf★ 18
• github.com/wy-ei/Text-CNN
  pytorch★ 11
• github.com/ahmedssabir/textual-visual-semantic-dataset
  tf★ 9
• github.com/pipidog/CNLP
  tf★ 5

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.

Tasks

Benchmark Results

Reproductions