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 View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples harvested from 7 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 20 samples from 7 repositories, 17 ran (13 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 5 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

ArdalanM/nlp-benchmarks mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
Fadeich/HotFlip-CNN-pytorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
HeyLynne/char_cnn mentioned on GitHubtfSyntology: not harvested report
ZeweiChu/NatCat mentioned on GitHubpytorchCC0-1.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
ahmedbesbes/character-based-cnn mentioned on GitHubpytorchMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
alrope123/prompt-waywardness mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Making Pre-trained Language Models Better Few-shot Learners (arXiv:2012.15723; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified) and Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts (arXiv:2112.08348; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
anutkk/RambaNet mentioned on GitHubtfGPL-3.0Syntology: not harvested report
cmasch/cnn-text-classification mentioned on GitHubtfSyntology: not harvested report
dongjun-Lee/text-classification-models-tf mentioned on GitHubtfSyntology: not harvested report
frederick0329/text-classification-benchmark mentioned on GitHubpytorchSyntology: not harvested report
gaussic/text-classification-cnn-rnn mentioned on GitHubtfSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
gmichalo/question_identification_on_medical_logs mentioned on GitHubpytorchSyntology: not harvested report
hc495/staicc mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to StaICC: Standardized Evaluation for Classification Task in In-context Learning (arXiv:2501.15708; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
lonePatient/char-cnn-text-classification mentioned on GitHubpytorchSyntology: not harvested report
mhjabreel/CharCNN mentioned on GitHubtfMITSyntology: not harvested report
mhjabreel/CharCnn_Keras mentioned on GitHubtfSyntology: not harvested report
paddorch/CharCNN.paddle mentioned on GitHubpaddleApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
paper-cat/Sentence-Classifications mentioned on GitHubtfMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
protonx-tf-03-projects/CharCNN mentioned on GitHubtfSyntology: not harvested report
sjmiller8182/character-convolutions-classification mentioned on GitHubtfMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
srviest/char-cnn-text-classification-pytorch mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
sucheta19/Text-Classification-Using-CNN mentioned on GitHubtfSyntology: not harvested report
sunginmkone/AWS_Training_NLP mentioned on GitHubtorchBSD-3-ClauseSyntology: not harvested report
threelittlemonkeys/cnn-text-classification-pytorch mentioned on GitHubpytorchSyntology: not harvested report
threelittlemonkeys/text-cnn-pytorch mentioned on GitHubpytorchSyntology: not harvested report
tuvuumass/SCoPE mentioned on GitHubtfSyntology: not harvested report
uds-lsv/bert-lnl mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification (arXiv:2204.09371; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
zhangxiangxiao/Crepe mentioned on GitHubtorchBSD-3-ClauseSyntology: not harvested report
Mrzhang3389/text_class tfSyntology: not harvested report
makcedward/nlpaug tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost (arXiv:2203.07860; that paper's own run record: 6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

20 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
2ran; the contract check could not run
13ran
3unverified

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 7 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

Fadeich/HotFlip-CNN-pytorch community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
dpp data_loader_hotflip_greedy.py ran · our draft was wrong fingerprinted no licence file found · pointer only · cb41f722c36c3b59 · report fixture: signature kernel_matrix:ndarray/2/float, max_length:int/0/int, epsilon:float/0/float · returned list · level recorded 2026-09-22
dpp_candidates data_loader_hotflip_beam.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · fce2825df6934a6e · report fixture: signature candidates:list/1/tuple, y_inds:list/1/int, theta:float/0/float · returned list · level recorded 2026-09-22
dpp_next_element data_loader_hotflip_beam.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 5aecd25926c298ca · report fixture: signature kernel_matrix:ndarray/2/float, R:list/1/int · returned ndarray · level recorded 2026-09-22
ZeweiChu/NatCat community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
compute_metrics in 208 papers code/utils.py ran CC0-1.0 (permissive) · 8eaa3c45016e8715 · report fixture: signature task_name:str/0/str, preds:ndarray/1/int, labels:ndarray/1/int · returned dict · level recorded 2026-09-26
simple_accuracy in 66 papers code/utils.py unverified CC0-1.0 (permissive) · 3c241ecfe3749a6d · report
ahmedbesbes/character-based-cnn community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
get_sample_weights src/data_loader.py ran MIT (permissive) · 286cdf64bccfcc8e · report fixture: signature labels:list/1/int · returned ndarray · level recorded 2026-09-26
lower src/utils.py ran fingerprinted MIT (permissive) · d8919140d7bb81f7 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
remove_hashtags src/utils.py ran fingerprinted MIT (permissive) · 7031f3d110ff2bb6 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
remove_user_mentions src/utils.py ran fingerprinted MIT (permissive) · fac1f52a515f3408 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
load_data in 700 papers src/data_loader.py unverified MIT (permissive) · 74b2ee2bcf9a5318 · report
gaussic/text-classification-cnn-rnn community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
get_time_dif run_cnn.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · d9e00c99bc3b43d2 · report fixture: signature start_time:float/0/float · returned timedelta · level recorded 2026-09-22
feed_data run_cnn.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 4515828165469544 · report
paddorch/CharCNN.paddle community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
F_score model/metric.py ran Apache-2.0 (permissive) · da3b18d772dc8f1f · report fixture: signature p:dict/0/?, r:dict/0/? · returned dict · level recorded 2026-09-26
precision_recall in 7 papers model/metric.py ran Apache-2.0 (permissive) · c01024271e313d54 · report fixture: signature output:list/1/int, target:list/1/int · returned tuple · level recorded 2026-09-26
paper-cat/Sentence-Classifications community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
char_base_vectorize preprocessing/text_preprocessing.py ran MIT (permissive) · 47cacd8e59547060 · report fixture: signature data:list/1/str, labels:list/1/str, char_dict:dict/0/?, label_dict:dict/0/?, train:bool/0/bool · returned tuple · level recorded 2026-09-26
label_converter preprocessing/text_preprocessing.py ran MIT (permissive) · e4018986564263d5 · report fixture: signature labels:list/1/str, label_dict:dict/0/? · returned tuple · level recorded 2026-09-26
load_dicts pipeline.py ran MIT (permissive) · e144f38dd5693140 · report fixture: signature route:str/0/str · returned tuple · level recorded 2026-09-26
sjmiller8182/character-convolutions-classification community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
get_convolutional_model src/model.py ran MIT (permissive) · eaa4cba327eb7e51 · report fixture: signature vocab_size:int/0/int, input_length:int/0/int, num_classes:int/0/int, embedding_size:int/0/int, model_size:str/0/str · returned Sequential · level recorded 2026-09-26
get_recurrent_model src/model.py ran MIT (permissive) · 584c7d5b746edcaf · report fixture: signature vocab_size:int/0/int, input_length:int/0/int, num_classes:int/0/int, embedding_size:int/0/int · returned Sequential · level recorded 2026-09-26
similarity in 17 papers src/util.py ran fingerprinted MIT (permissive) · fc127f1284f11efc · report fixture: signature vector1:ndarray/1/float, vector2:ndarray/1/float · returned float32 · level recorded 2026-09-26

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