Character-level Convolutional Networks for Text Classification
2015-09-04NeurIPS 2015Code Available1· sign in to hype
Xiang Zhang, Junbo Zhao, Yann Lecun
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/makcedward/nlpaugtf★ 4,652
- github.com/threelittlemonkeys/cnn-text-classification-pytorchpytorch★ 21
- github.com/tuvuumass/SCoPEtf★ 18
- github.com/alrope123/prompt-waywardnesspytorch★ 14
- github.com/uds-lsv/bert-lnlpytorch★ 10
- github.com/ZeweiChu/NatCatpytorch★ 10
- github.com/anutkk/RambaNettf★ 2
- github.com/hc495/staiccpytorch★ 2
- github.com/gmichalo/question_identification_on_medical_logspytorch★ 2
- github.com/HeyLynne/char_cnntf★ 0
Abstract
This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| Yelp Binary classification | Char-level CNN | Error | 4.88 | — | Unverified |
| Yelp Fine-grained classification | Char-level CNN | Error | 37.95 | — | Unverified |