Papers › Bidirectional Attention Flow for Machine Comprehension

Bidirectional Attention Flow for Machine Comprehension

5 Nov 2016arXiv:1611.01603archive 2025-07-28

Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, Hannaneh Hajishirzi

Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been successfully extended to MC. Typically these methods use attention to focus on a small portion of the context and summarize it with a fixed-size vector, couple attentions temporally, and/or often form a uni-directional attention. In this paper we introduce the Bi-Directional Attention Flow (BIDAF) network, a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization. Our experimental evaluations show that our model achieves the state-of-the-art results in Stanford Question Answering Dataset (SQuAD) and CNN/DailyMail cloze test.

PaperPDFCodeCode 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 11 code samples harvested from 5 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 10 samples from 4 repositories, 8 ran (3 with no instrument failure; 5 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.

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.

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

allenai/bi-att-flow officialmentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Deepak-Work/Passage_Retrieval mentioned on GitHubtfSyntology: not harvested report
ElizaLo/Question-Answering-based-on-SQuAD mentioned on GitHubpytorchSyntology: not harvested report
GauthierDmn/question_answering mentioned on GitHubpytorchSyntology: not harvested report
Shravsridhar/NLP-Question-Answer-Model mentioned on GitHubSyntology: not harvested report
Shravsridhar/QA-Model-INFO-7374 mentioned on GitHubSyntology: not harvested report
WarruzuEndo/BiDAF_mindspore mentioned on GitHubmindsporeSyntology: not harvested report
baidu/DuReader mentioned on GitHubtfSyntology: not harvested report
davidgolub/QuestionGeneration mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
distractor-generation/dg_survey mentioned on GitHubSyntology: not harvested report
dsouzadaniel/BiDAF mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
galsang/BiDAF-pytorch mentioned on GitHubpytorchSyntology: not harvested report
ghus75/Question_Answering mentioned on GitHubtfApache-2.0Syntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
kokikwbt/deepsect mentioned on GitHubSyntology: not harvested report
lmn-extracts/dcn_plus mentioned on GitHubtfSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
minstar/BIDAF mentioned on GitHubtfSyntology: not harvested report
rajatgermany/qa-nlp mentioned on GitHubpytorchSyntology: not harvested report
shmsw25/qa-transfer mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
surekhamedapati/NLPA_NEO mentioned on GitHubpytorchSyntology: not harvested report
suryaiyer/squad-bidaf mentioned on GitHubpytorchSyntology: not harvested report
techit-limtiyakul/bidirectional-attention-flow mentioned on GitHubpytorchSyntology: not harvested report
tikyau/bidaf-quick-test mentioned on GitHubtfSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
white127/squad-2.0-bidaf mentioned on GitHubtfSyntology: not harvested report
xiaobaicxy/Bidaf_SQuAD_MC_Pytorch mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
yugrocks/Question-Answering-with-BIDAF mentioned on GitHubtfSyntology: not harvested report
Wadaboa/squad-question-answering pytorchSyntology: 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.

Code Syntology ran Syntology

11 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 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.

1ran · honoured contract
2ran · violated contract
5ran · our draft was wrong
1ran
2unverified

Licence: 7 of the 11 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 5 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.

allenai/bi-att-flow official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
f1_score in 121 papers squad/evaluate-v1.1.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 2112c433b9c6d343 · report fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned float · level recorded 2026-09-22
ghus75/Question_Answering community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
exact_match_score in 82 papers code/evaluate.py ran · violated contract fingerprinted Apache-2.0 (permissive) · f6c275d6a18330a9 · report fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned bool · level recorded 2026-09-22
masked_softmax in 51 papers
census: 10 implementations from 10 papers, 10 distinct outputs across 6 buckets, one shared input per bucket
code/modules.py ran Apache-2.0 (permissive) · 591485e987c9ea09 · report fixture: signature logits:ndarray/2/float, mask:ndarray/2/float, dim:int/0/int · returned tuple · level recorded 2026-09-26
normalize_answer in 304 papers code/evaluate.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · c6a80c065d2e4851 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22
lmn-extracts/dcn_plus community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
data_from_json question_answering/preprocessing/squad_preprocess.py ran · our draft was wrong no licence file found · pointer only · 40b9eb36720710bb · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-22
maybe_download in 10 papers question_answering/preprocessing/squad_preprocess.py unverified no licence file found · pointer only · 4839200676aaf471 · report
reporthook in 5 papers question_answering/preprocessing/squad_preprocess.py unverified no licence file found · pointer only · 9724d0da37841e48 · report
shmsw25/qa-transfer community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_word2vec squad/prepro.py ran · our draft was wrong no licence file found · pointer only · a7dd8bca3454ecd5 · report fixture: signature args:Args/0/?, word_counter:dict/0/? · returned dict · level recorded 2026-09-22
tikyau/bidaf-quick-test community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
gb analyze.py ran · our draft was wrong no licence file found · pointer only · 27e4ebf8000ce768 · report fixture: signature collection:list/1/Item, keyfunc:callable/0/? · returned list · level recorded 2026-09-22
mask_answer zeroshot/zeroshot2squad.py ran · our draft was wrong no licence file found · pointer only · 5b15515dc2386cc7 · report fixture: signature answer:str/0/str, rnd:Random/0/? · returned str · level recorded 2026-09-22
parse_no_answers analyze.py ran · violated contract no licence file found · pointer only · d8ae123b2848fad9 · report fixture: signature results:list/1/dict · returned list · level recorded 2026-09-22

Tasks

Cloze TestNavigateOpen-Domain Question AnsweringQuestion AnsweringReading Comprehension

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open-Domain Question Answering Quasar BiDAF EM (Quasar-T) 25.9 #6 of 6 Archive leaderboard report
Open-Domain Question Answering Quasar BiDAF F1 (Quasar-T) 28.5 #6 of 6 Archive leaderboard report
Question Answering CNN / Daily Mail BiDAF CNN 76.9 #4 of 16 Archive leaderboard report
Question Answering CNN / Daily Mail BiDAF Daily Mail 79.6 #4 of 16 Archive leaderboard report
Question Answering MS MARCO BiDaF Baseline BLEU-1 10.64 #4 of 4 Archive leaderboard report
Question Answering MS MARCO BiDaF Baseline Rouge-L 23.96 #4 of 4 Archive leaderboard report
Question Answering NarrativeQA BiDAF BLEU-1 33.45 #8 of 10 Archive leaderboard report
Question Answering NarrativeQA BiDAF BLEU-4 15.69 #8 of 10 Archive leaderboard report
Question Answering NarrativeQA BiDAF METEOR 15.68 #8 of 10 Archive leaderboard report
Question Answering NarrativeQA BiDAF Rouge-L 36.74 #8 of 10 Archive leaderboard report
Question Answering SQuAD1.1 BiDAF (ensemble) EM 73.744 #134 of 213 Archive leaderboard report
Question Answering SQuAD1.1 BiDAF (ensemble) F1 81.525 #134 of 213 Archive leaderboard report
Question Answering SQuAD1.1 BiDAF (single model) EM 67.974 #170 of 213 Archive leaderboard report
Question Answering SQuAD1.1 BiDAF (single model) F1 77.323 #170 of 213 Archive leaderboard report
Question Answering SQuAD1.1 dev BIDAF (single) EM 67.7 #41 of 55 Archive leaderboard report
Question Answering SQuAD1.1 dev BIDAF (single) F1 77.3 #41 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.

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