Papers › QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension

QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension

23 Apr 2018ICLR 2018 1arXiv:1804.09541archive 2025-07-28

Adams Wei Yu, David Dohan, Minh-Thang Luong, Rui Zhao, Kai Chen, Mohammad Norouzi, Quoc V. Le

Current end-to-end machine reading and question answering (Q&A) models are primarily based on recurrent neural networks (RNNs) with attention. Despite their success, these models are often slow for both training and inference due to the sequential nature of RNNs. We propose a new Q&A architecture called QANet, which does not require recurrent networks: Its encoder consists exclusively of convolution and self-attention, where convolution models local interactions and self-attention models global interactions. On the SQuAD dataset, our model is 3x to 13x faster in training and 4x to 9x faster in inference, while achieving equivalent accuracy to recurrent models. The speed-up gain allows us to train the model with much more data. We hence combine our model with data generated by backtranslation from a neural machine translation model. On the SQuAD dataset, our single model, trained with augmented data, achieves 84.6 F1 score on the test set, which is significantly better than the best published F1 score of 81.8.

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 19 code samples harvested from 6 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 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): 19 samples from 6 repositories, 14 ran (10 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 1 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.

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

BangLiu/QANet-PyTorch mentioned on GitHubpytorchMITSyntology: 5 samples, 5 ran (1 instrument-failed) · 0 unverified report
Francois-Aubet/EQuANt mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
TSLNIHAOGIT/QANet_keras_debug mentioned on GitHubtfSyntology: not harvested report
Tao-Mind/QDD_Net mentioned on GitHubtfMITSyntology: 6 samples, 3 ran (0 instrument-failed) · 3 unverified report
ajoshi80/QANet mentioned on GitHubpytorchSyntology: not harvested report
andy840314/QANet-pytorch- mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
annaorosz/my_qanet_implementation mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
benywon/ComQA mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arXiv:1810.04805; that paper's own run record: 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified); nothing checks that they implement this paper's method. report
ewrfcas/QANet_keras mentioned on GitHubtfSyntology: not harvested report
lottens/QA-SQuAD mentioned on GitHubpytorchSyntology: not harvested report
mirbostani/QA-KD-AL mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
ni9elf/QANet mentioned on GitHubtfSyntology: not harvested report
shikhar1sharma/NLP-Resources mentioned on GitHubSyntology: not harvested report
yuriak/PPDAI mentioned on GitHubtfSyntology: not harvested 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

19 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 5 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.

3ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
7ran
5unverified

Licence: 3 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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 6 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.

BangLiu/QANet-PyTorch community (archive-listed) 5 samples, 5 ran (1 instrument-failed) · 0 unverified
OpenAITransformer_loss trainer/loss.py ran MIT (permissive) · 73f7bc81c21d46f4 · report fixture: signature lm_criterion:callable/0/?, clf_criterion:callable/0/?, lm_coef:float/0/float, X:Tensor/4/int, Y:Tensor/1/int, M:Tensor/3/float, clf_logits:Tensor/2/float, lm_logits:Tensor/2/float · returned Tensor · level recorded 2026-09-26
clones in 92 papers model/modules/attention.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · cf78c734df121970 · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-22
convert_idx data_loader/SQuAD.py ran MIT (permissive) · 23587f1e97b0e35d · report fixture: signature text:str/0/str, tokens:list/1/str · returned list · level recorded 2026-09-26
filter_func in 5 papers data_loader/SQuAD.py ran MIT (permissive) · c4d748327c33e6cc · report fixture: signature config:Config/0/?, example:dict/0/? · returned bool · level recorded 2026-09-26
my_loss in 5 papers trainer/loss.py ran MIT (permissive) · cb4ce684e3929e65 · report fixture: signature y_input:Tensor/2/float, y_target:Tensor/1/int · returned Tensor · level recorded 2026-09-26
Francois-Aubet/EQuANt community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
convert_idx prepro.py ran · honoured contract no licence file found · pointer only · 2a6a9ea511d97648 · report fixture: signature text:str/0/str, tokens:list/1/str · returned list · level recorded 2026-09-22
Tao-Mind/QDD_Net community (archive-listed) 6 samples, 3 ran (0 instrument-failed) · 3 unverified
crop_pad pre_process.py ran fingerprinted MIT (permissive) · 32abbed1f309ad9f · report fixture: signature max_length:int/0/int, word_index:list/1/int · returned list · level recorded 2026-09-26
get_ids in 12 papers pre_process.py ran MIT (permissive) · fc42ce0856c29480 · report fixture: signature qids:list/1/str · returned ndarray · level recorded 2026-09-26
get_texts in 12 papers pre_process.py ran MIT (permissive) · fdbd06a820d2930d · report fixture: signature file_path:str/0/str, question_path:str/0/str · returned list · level recorded 2026-09-26
add_dense_layer models/layers.py unverified MIT (permissive) · edf10b1abda15159 · report
biGRUs models/layers.py unverified MIT (permissive) · d6c2afca4b825f12 · report
dot_attention in 7 papers models/layers.py unverified MIT (permissive) · 96be8bbb7b022500 · report
andy840314/QANet-pytorch- community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
PosEncoder models.py ran; the contract check could not run (RAISES) MIT (permissive) · 5c8c86edd3d3e783 · report fixture: returned Tensor · level recorded 2026-09-22
get_timing_signal models.py ran · honoured contract fingerprinted MIT (permissive) · d2e8e18023f286ab · report fixture: signature length:int/0/int, channels:int/0/int, min_timescale:float/0/float, max_timescale:float/0/float · returned Tensor · level recorded 2026-09-22
mask_logits in 27 papers
census: 7 implementations from 10 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind int, dtype int32
models.py ran · our draft was wrong fingerprinted MIT (permissive) · dea46bb8718e5def · report fixture: signature inputs:Tensor/2/float, mask:Tensor/2/int · returned Tensor · level recorded 2026-09-22
annaorosz/my_qanet_implementation community (archive-listed) 1 sample, 0 ran · 1 unverified
highway QANet_keras.py unverified no licence file found · pointer only · 9549014140b95768 · report
mirbostani/QA-KD-AL community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
get_timing_signal qa/model/qanet.py ran · honoured contract fingerprinted MIT (permissive) · f82361ad7330d575 · report fixture: signature length:int/0/int, channels:int/0/int, min_timescale:float/0/float, max_timescale:float/0/float · returned Tensor · level recorded 2026-09-22
mask_logits in 27 papers
census: 7 implementations from 10 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 3 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind int, dtype int64
qa/model/qanet.py ran · our draft was wrong fingerprinted MIT (permissive) · 9dc49f46edd7a69d · report fixture: signature target:Tensor/2/float, mask:Tensor/2/int · returned Tensor · level recorded 2026-09-22
PosEncoder qa/model/qanet.py unverified MIT (permissive) · ee4ade0d8bcf356a · report

Tasks

Machine TranslationQuestion AnsweringReading ComprehensionTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering SQuAD1.1 QANet + data augmentation ×3 EM 76.2 #111 of 213 Archive leaderboard report
Question Answering SQuAD1.1 QANet + data augmentation ×3 F1 84.6 #111 of 213 Archive leaderboard report
Question Answering SQuAD1.1 dev QANet (data aug x3) EM 75.1 #27 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev QANet (data aug x3) F1 83.8 #27 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev QANet (data aug x2) EM 74.5 #28 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev QANet (data aug x2) F1 83.2 #28 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev QANet EM 73.6 #30 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev QANet F1 82.7 #30 of 55 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.

Methods

Convolution

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