Papers › Convolutional Neural Networks for Sentence Classification
Convolutional Neural Networks for Sentence Classification
Yoon Kim
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.
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):
get_harvested_code_for_paper(arxiv_id="1408.5882")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1408.5882", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1408.5882")
Code
Syntology 77 code samples harvested from 20 repositories linked to this paper: 53 ran (of which 0 constructed an object rather than computing a result; 40 with no instrument failure: 6 honoured, 1 violated, 33 with no contract checked; 13 where Syntology's instrument failed) · 24 unverified. Where Syntology's instrument failed: 12 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 77 samples from 20 repositories, 53 ran (40 with no instrument failure; 13 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 14 of its repositories that Syntology harvested for other papers:
- TsingZ0/PFL-Non-IID, community (archive-listed): harvested for 11 other papers, listed under the repository
- adi2103/AML-CoVe, community (archive-listed): harvested for 2 other papers, listed under the repository
- afrozloya/charrec, community (archive-listed): harvested for another paper, listed under the repository
- fangrouli/Document-embedding-generation-models, community (archive-listed): harvested for another paper, listed under the repository
- paper-cat/Sentence-Classifications, community (archive-listed): harvested for another paper, listed under the repository
- pranjalg96/Stylized-Image-captioning, community (archive-listed): harvested for another paper, listed under the repository
- reneang17/authorencoder, community (archive-listed): harvested for another paper, listed under the repository
- richinkabra/CoVe-BCN, community (archive-listed): harvested for another paper, listed under the repository
- wiseodd/controlled-text-generation, community (archive-listed): harvested for another paper, listed under the repository
- PaddlePaddle/PaddleNLP, community (archive-listed): harvested for another paper, listed under the repository
- PaddlePaddle/PaddleRec, community (archive-listed): harvested for another paper, listed under the repository
- dmlc/gluon-nlp, community (archive-listed): harvested for another paper, listed under the repository
- lvyufeng/mindspore-nlp-tutorial, community (archive-listed): harvested for another paper, listed under the repository
- mindspore-ai/models, community (archive-listed): harvested for another paper, listed under the repository
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. 1 of the 53 samples that ran has no recorded date.
118 repositories listed; official and paper-mentioned ones first.
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
77 samples harvested: 53 ran (of which 0 constructed an object rather than computing a result; 40 with no instrument failure: 6 honoured, 1 violated, 33 with no contract checked; 13 where Syntology's instrument failed) · 24 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 21 of the 77 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 20 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. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
74bca835aa136142 · report
fixture: signature dict_file:str/0/str · returned tuple · level recorded 2026-09-22 census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket prepare_data.py ran · violated contract fingerprinted no licence file found · pointer only ·
e55c5e84d71ce43a · report
fixture: signature vec:list/1/float · returned list · level recorded 2026-09-22 81912d07d41ad566 · report
fixture: signature opened_file:BytesIO/0/?, vec_len:int/0/int · returned tuple · level recorded 2026-09-22 1826f73b65b1976e · report
fixture: signature target:ndarray/1/int · returned ndarray · level recorded 2026-09-22 8ebb1beb61837fb1 · report
fixture: signature string:str/0/str · returned str · level recorded 2026-09-26 dfd16b852a1f08c1 · report
fixture: signature batch:list/1/tuple, min_len:int/0/int · returned tuple · level recorded 2026-09-26 795300f6734869ed · report
fixture: signature path:str/0/str · returned int · level recorded 2026-09-26 3327aa7527520a84 · report
fixture: signature classified:Tensor/2/float, answer:list/1/int · returned float · level recorded 2026-09-26 b32b5833493d607a · report
fixture: signature sentences:list/1/list · returned list · level recorded 2026-09-26 8f5471ca03ed0239 · report
fixture: signature sentences:list/1/list, padding_word:str/0/str · returned list · level recorded 2026-09-26 efe1a86fd9a2468e · report
fixture: signature string:str/0/str · returned str · level recorded 2026-09-22 24886408b62be99a · report
fixture: signature positive_data_file:str/0/str, negative_data_file:str/0/str · returned list · level recorded 2026-09-22 99c0dc46fd15bb10 · report
fixture: signature directory_path:str/0/str · returned dict · level recorded 2026-09-26 4677d82ba2d19519 · report
fixture: signature review_dataframe:DataFrame/0/?, rating_2_sentiment:dict/0/? · returned DataFrame · level recorded 2026-09-26 4f43bc8ef9323fc3 · report
efc3a77905da7a9d · report
fixture: signature string:str/0/str, TREC:bool/0/bool · returned str · level recorded 2026-09-26 a59a82e26e9459f2 · report
fixture: signature neg_file:str/0/str, pos_file:str/0/str · returned tuple · level recorded 2026-09-26 9e8508cb98e5104b · report
fixture: signature x:str/0/str · returned list · level recorded 2026-09-26 55365320fd689119 · report
fixture: signature x:str/0/str · returned list · level recorded 2026-09-26 d9e00c99bc3b43d2 · report
fixture: signature start_time:float/0/float · returned timedelta · level recorded 2026-09-22 8dc8d3a14cde192f · report
fixture: signature data_dir:str/0/str, filtered_by:NoneType/0/? · returned dict · level recorded 2026-09-26 7b9076aa00b98231 · report
aa2e11b6e900e44a · report
fixture: signature max_length:int/0/int · returned list · level recorded 2026-09-22 e46bdc997c311e22 · report
fixture: signature args:Args/0/? · returned tuple · level recorded 2026-09-26 c62648a11b00a100 · report
fixture: signature X_train:ndarray/2/float, Y_train:ndarray/1/int, batch_size:int/0/int, shuffle:bool/0/bool · returned generator · level recorded 2026-09-26 4df1c013c4cd5872 · report
fixture: signature tensor_list:list/1/EagerTensor, axis:int/0/int · returned EagerTensor · level recorded 2026-09-26 09cb65a28eb46830 · report
fixture: signature tensor:EagerTensor/2/float, keep_prob:float/0/float, name:NoneType/0/? · returned EagerTensor · level recorded 2026-09-26 506f16da45fa7bd5 · report
fixture: signature path:str/0/str, text_file_name:str/0/str, label_file_name:str/0/str · returned tuple · level recorded 2026-09-26 bdb736f7b92a0ad3 · report
fixture: signature labels:EagerTensor/2/float, preds:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26 9239e6af1bbb6e07 · report
fixture: signature X:ndarray/2/float, Y:ndarray/2/float, shuffle:bool/0/bool, val_size:float/0/float · returned tuple · level recorded 2026-09-26 c108960f22fe26aa · report
census: 5 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket nn/losses.py unverified MIT (permissive) ·
8197ee6236e68110 · report
census: 18 implementations from 29 papers, 4 distinct outputs across 2 buckets, one shared input per bucket nn/losses.py unverified MIT (permissive) ·
bd97236dd26fd34d · report
6e49b503ffe317d7 · report
fixture: signature review:str/0/str · returned str · level recorded 2026-09-26 3c77d69fa7310478 · report
fixture: signature input:Tensor/2/int, pad_id:int/0/int · returned Tensor · level recorded 2026-09-26 5cb79ca7ceefc156 · report
fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-26 8dc6cef357628e1b · report
fixture: signature glove_vector_path:str/0/str · returned dict · level recorded 2026-09-26 0402070ef0b2c2b3 · report
fixture: signature input_data_path:str/0/str · returned tuple · level recorded 2026-09-26 1f0857ef07d36305 · report
fixture: signature poscounts:dict/0/?, negcounts:dict/0/?, alpha:float/0/float · returned tuple · level recorded 2026-09-22 79c1b7c0f8e87a6b · report
fixture: signature sentence:str/0/str, grams:list/1/int · returned list · level recorded 2026-09-22 8e159fcba115372b · report
fixture: signature word_vecs:dict/0/?, k:int/0/int · returned tuple · level recorded 2026-09-22 2777a9ed50134acd · report
fixture: signature sent:str/0/str, word_idx_map:dict/0/?, max_l:int/0/int, k:int/0/int, filter_h:int/0/int, pad_left:bool/0/bool · returned list · level recorded 2026-09-22 c3873605307a3c77 · report
fixture: signature revs:list/1/dict, word_idx_map:dict/0/?, cv:int/0/int, max_l:int/0/int, k:int/0/int, filter_h:int/0/int, pad_left:bool/0/bool · returned list · level recorded 2026-09-22 781a7c253f13fdb1 · report
fixture: signature revs:list/1/dict, word_idx_map:dict/0/?, cv:int/0/int, max_l:int/0/int, k:int/0/int, filter_h:int/0/int, pad_left:bool/0/bool · returned list · level recorded 2026-09-22 dc39e2e56c9504b1 · report
85763dbc456f9a11 · report
31bacc027a1637a7 · report
fixture: signature files:list/1/str, num_words:int/0/int · returned dict · level recorded 2026-09-26 c5beea5bfbce4121 · report
fixture: signature model:callable/0/?, dl:list/1/tuple, device:device/0/? · returned ndarray · level recorded 2026-09-26 census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 pytorch_pretrained_bert/modeling.py ran · our draft was wrong fingerprinted MIT (permissive) ·
0f786c407fb1ee4c · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded 349d780dd4a89a37 · report
fixture: signature url_or_filename:str/0/str, cache_dir:str/0/str · returned str · level recorded 2026-09-26 728fbd506ea36d0d · report
fixture: signature tokens_list:list/1/dict, max_seq_length:int/0/int, tokenizer:MockTokenizer/0/? · returned list · level recorded 2026-09-26 9cf15995db9f9f06 · report
fixture: signature tokens_list:list/1/dict, max_seq_length:int/0/int, tokenizer:SimpleTokenizer/0/?, overlap_size_token:int/0/int · returned tuple · level recorded 2026-09-26 db0ac56aaf6e35e6 · report
fixture: signature filename:str/0/str, cache_dir:str/0/str · returned tuple · level recorded 2026-09-26 census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 pytorch_pretrained_bert/modeling.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only ·
40e9fee2e0b7e278 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 fb95c4b13cdf89a2 · report
fixture: signature vocab_file:str/0/str · returned OrderedDict · level recorded 2026-09-26 90d3ee4851872058 · report
fixture: signature vocab_file:str/0/str · returned OrderedDict · level recorded 2026-09-26 af64ec220e8bcdbc · report
fixture: signature url:str/0/str, etag:str/0/str · returned str · level recorded 2026-09-22 e7d542062316094a · report
fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-22 c58d57224530d17e · report
fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-22 da7295883cd7da14 · report
fixture: signature text:str/0/str · returned list · level recorded 2026-09-26 35f7cddf90dd05d4 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Emotion Recognition in Conversation | CPED | TextCNN | Accuracy of Sentiment | 48.90 | #6 of 11 | Archive leaderboard | report |
| Emotion Recognition in Conversation | CPED | TextCNN | Macro-F1 of Sentiment | 34.37 | #6 of 11 | Archive leaderboard | report |
| Sentiment Analysis | SST-2 Binary classification | CNN-multichannel [kim2013] | Accuracy | 88.1 | #67 of 87 | 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