Papers › Character-level Convolutional Networks for Text Classification

Character-level Convolutional Networks for Text Classification

4 Sep 2015NeurIPS 2015 12arXiv:1509.01626archive 2025-07-28

Xiang Zhang, Junbo Zhao, Yann Lecun

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1509.01626")

Code

Syntology Ran 4 of 20 code samples harvested from 6 repositories linked to this paper; 16 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: community (archive-listed): 18 samples from 6 repositories, 3 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

30 repositories listed; official and paper-mentioned ones first.

ArdalanM/nlp-benchmarks mentioned on GitHubpytorch report
Fadeich/HotFlip-CNN-pytorch mentioned on GitHubpytorch report
HeyLynne/char_cnn mentioned on GitHubtf report
ZeweiChu/NatCat mentioned on GitHubpytorchCC0-1.0 report
ahmedbesbes/character-based-cnn mentioned on GitHubpytorchMIT report
alrope123/prompt-waywardness mentioned on GitHubpytorch report
anutkk/RambaNet mentioned on GitHubtfGPL-3.0 report
cmasch/cnn-text-classification mentioned on GitHubtf report
hc495/staicc mentioned on GitHubpytorch report
mhjabreel/CharCNN mentioned on GitHubtfMIT report
mhjabreel/CharCnn_Keras mentioned on GitHubtf report
paddorch/CharCNN.paddle mentioned on GitHubpaddleApache-2.0 report
paper-cat/Sentence-Classifications mentioned on GitHubtfMIT report
protonx-tf-03-projects/CharCNN mentioned on GitHubtf report
srviest/char-cnn-text-classification-pytorch mentioned on GitHubpytorchApache-2.0 report
sunginmkone/AWS_Training_NLP mentioned on GitHubtorchBSD-3-Clause report
threelittlemonkeys/text-cnn-pytorch mentioned on GitHubpytorch report
tuvuumass/SCoPE mentioned on GitHubtf report
uds-lsv/bert-lnl mentioned on GitHubpytorchMIT report
zhangxiangxiao/Crepe mentioned on GitHubtorchBSD-3-Clause report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

20 samples harvested; 4 ran; 0 honoured the contract we drafted; 16 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
2ran · fixture could not drive it
16unverified

Licence: 5 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

dpp Fadeich/HotFlip-CNN-pytorch/data_loader_hotflip_greedy.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · cb41f722c36c3b59 · report
dpp_candidates Fadeich/HotFlip-CNN-pytorch/data_loader_hotflip_beam.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · fce2825df6934a6e · report
dpp_next_element Fadeich/HotFlip-CNN-pytorch/data_loader_hotflip_beam.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · 5aecd25926c298ca · report
F_score paddorch/CharCNN.paddle/model/metric.py community (archive-listed) unverified Apache-2.0 (permissive) · da3b18d772dc8f1f · report
char_base_vectorize paper-cat/Sentence-Classifications/preprocessing/text_preprocessing.py community (archive-listed) unverified MIT (permissive) · 47cacd8e59547060 · report
compute_metrics ZeweiChu/NatCat/code/utils.py community (archive-listed) unverified CC0-1.0 (permissive) · 8eaa3c45016e8715 · report
get_convolutional_model sjmiller8182/character-convolutions-classification/src/model.py community (archive-listed) unverified MIT (permissive) · eaa4cba327eb7e51 · report
get_recurrent_model sjmiller8182/character-convolutions-classification/src/model.py community (archive-listed) unverified MIT (permissive) · 584c7d5b746edcaf · report
get_sample_weights ahmedbesbes/character-based-cnn/src/data_loader.py community (archive-listed) unverified MIT (permissive) · 286cdf64bccfcc8e · report
label_converter paper-cat/Sentence-Classifications/preprocessing/text_preprocessing.py community (archive-listed) unverified MIT (permissive) · e4018986564263d5 · report
load_data ahmedbesbes/character-based-cnn/src/data_loader.py community (archive-listed) unverified MIT (permissive) · 74b2ee2bcf9a5318 · report
load_dicts paper-cat/Sentence-Classifications/pipeline.py community (archive-listed) unverified MIT (permissive) · e144f38dd5693140 · report
lower ahmedbesbes/character-based-cnn/src/utils.py community (archive-listed) unverified MIT (permissive) · d8919140d7bb81f7 · report
precision_recall paddorch/CharCNN.paddle/model/metric.py community (archive-listed) unverified Apache-2.0 (permissive) · c01024271e313d54 · report
remove_hashtags ahmedbesbes/character-based-cnn/src/utils.py community (archive-listed) unverified MIT (permissive) · 7031f3d110ff2bb6 · report
remove_user_mentions ahmedbesbes/character-based-cnn/src/utils.py community (archive-listed) unverified MIT (permissive) · fac1f52a515f3408 · report
similarity sjmiller8182/character-convolutions-classification/src/util.py community (archive-listed) unverified MIT (permissive) · fc127f1284f11efc · report
simple_accuracy ZeweiChu/NatCat/code/utils.py community (archive-listed) unverified CC0-1.0 (permissive) · 3c241ecfe3749a6d · report
get_time_dif identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · d9e00c99bc3b43d2 · report
feed_data identical code first harvested elsewhere unverified licence of this copy not recorded · 4515828165469544 · report

Tasks

General ClassificationSentiment AnalysisText Classification

Datasets

Introduced by this paper, per the archive.

AG NewsYahoo! AnswersYelp Review Polarity

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sentiment Analysis Yelp Binary classification Char-level CNN Error 4.88 #20 of 20 Archive leaderboard report
Sentiment Analysis Yelp Fine-grained classification Char-level CNN Error 37.95 #16 of 17 Archive leaderboard report
Text Classification AG News Char-level CNN Error 9.51 #19 of 24 Archive leaderboard report
Text Classification DBpedia Char-level CNN Error 1.55 #20 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections