Papers › End-To-End Memory Networks

End-To-End Memory Networks

31 Mar 2015NeurIPS 2015 12arXiv:1503.08895archive 2025-07-28

Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus

We introduce a neural network with a recurrent attention model over a possibly large external memory. The architecture is a form of Memory Network (Weston et al., 2015) but unlike the model in that work, it is trained end-to-end, and hence requires significantly less supervision during training, making it more generally applicable in realistic settings. It can also be seen as an extension of RNNsearch to the case where multiple computational steps (hops) are performed per output symbol. The flexibility of the model allows us to apply it to tasks as diverse as (synthetic) question answering and to language modeling. For the former our approach is competitive with Memory Networks, but with less supervision. For the latter, on the Penn TreeBank and Text8 datasets our approach demonstrates comparable performance to RNNs and LSTMs. In both cases we show that the key concept of multiple computational hops yields improved results.

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

The archive's official repository (facebook/MemNN) was not harvested; the 15 samples below come from 6 community repositories.

Syntology 15 code samples harvested from 6 repositories linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 15 samples from 6 repositories, 4 ran (3 with no instrument failure; 1 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.

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

facebook/MemNN officialmentioned in papermentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
HSabbar/Question-Answering mentioned on GitHubtfSyntology: not harvested report
Monireh2/kg-deductive-reasoner mentioned on GitHubNOASSERTIONSyntology: not harvested report
RAGHAVJHA01/chatboat mentioned on GitHubSyntology: not harvested report
Saurabh2798/Q-A-bot mentioned on GitHubSyntology: not harvested report
SeonbeomKim/TensorFlow-MemN2N mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
TDeepanshPandey/Chat_Bot mentioned on GitHubSyntology: not harvested report
TommyWongww/MemoryNetworks mentioned on GitHubpytorchSyntology: not harvested report
VikrantChauhan001/NLP-Deep-Learning-Chatbot mentioned on GitHubSyntology: not harvested report
aadil-srivastava01/End-To-End-Memory-Networks mentioned on GitHubSyntology: not harvested report
benprano/Question-Answering-Deep-Learning mentioned on GitHubtfSyntology: not harvested report
candoz/memn2n-dialog-babi-keras mentioned on GitHubtfSyntology: not harvested report
cstghitpku/GateMemN2N mentioned on GitHubtfMITSyntology: 1 sample, 0 ran · 1 unverified report
dare0021/MemN2N_Bench mentioned on GitHubMITSyntology: 9 samples, 2 ran (0 instrument-failed) · 7 unverified report
domluna/memn2n mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks (arXiv:1502.05698; 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
facebook/MazeBase mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
facebook/bAbI-tasks mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
facebookarchive/MazeBase mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
facebookarchive/babi-tasks mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
gaurav9713/simpleQA_chatbot mentioned on GitHubSyntology: not harvested report
google/neural-logic-machines mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neural Logic Machines (arXiv:1904.11694; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
gryan12/chat-bot mentioned on GitHubtfSyntology: not harvested report
huiyinglu/NLP-Deep-Learning-Chatbot mentioned on GitHubSyntology: not harvested report
ishalyminov/memn2n mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jojonki/MemoryNetworks mentioned on GitHubpytorchSyntology: not harvested report
mustafa-yavuz/chatbot-qa mentioned on GitHubSyntology: not harvested report
nbansal90/bAbi_QA mentioned on GitHubSyntology: 2 samples, 0 ran · 2 unverified report
prashil2792/Question-Answering-System-Deep-Learning mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
qapitan/babi-marcus mentioned on GitHubtorchNOASSERTIONSyntology: not harvested report
rakeshbm/QA-using-Torch mentioned on GitHubtorchSyntology: not harvested report
sayakbanerjee1999/Chat-Bot mentioned on GitHubSyntology: not harvested report
sheryl-ai/MemGCN mentioned on GitHubtfSyntology: not harvested report
shivanidogra0301/NLP-Deep_Learning_Chatbot mentioned on GitHubSyntology: not harvested report
simonjisu/E2EMN mentioned on GitHubpytorchSyntology: not harvested report
stikbuf/Language_Modeling mentioned on GitHubtfSyntology: not harvested report
sy-sunmoon/Clever-Commenter-Let-s-Try-More-Apps mentioned on GitHubpytorchSyntology: not harvested report
thomlake/pytorch-attention mentioned on GitHubpytorchBSD-2-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Pointer Networks (arXiv:1506.03134; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 1 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
umutguneri/Question-Answering-Assistant mentioned on GitHubtfSyntology: not harvested report
uwnlp/qrn mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Query-Reduction Networks for Question Answering (arXiv:1606.04582; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
vinhkhuc/MemN2N-babi-python mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
wujsAct/DeepLearningModels mentioned on GitHubtfSyntology: not harvested report
yulangz/End-to-End-Memory-Networks-in-Paddle mentioned on GitHubpaddleSyntology: not harvested report
PaddlePaddle/PaddleNLP paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation... (arXiv:2301.03416; 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) · 1 unverified); nothing checks that they implement this paper's method. report
hizvi/memN2N Syntology: 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

15 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 11 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
1ran · our draft was wrong
2ran
11unverified

Licence: 5 of the 15 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; 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”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.

SeonbeomKim/TensorFlow-MemN2N community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
toNumpy training.py ran · our draft was wrong no licence file found · pointer only · f0dbdbccfb2bbdd5 · report fixture: returned ndarray · level recorded 2026-09-22
cstghitpku/GateMemN2N community (archive-listed) 1 sample, 0 ran · 1 unverified
tokenize in 176 papers data_utils.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 · 6d27ce4e6c139f45 · report
dare0021/MemN2N_Bench community (archive-listed) 9 samples, 2 ran (0 instrument-failed) · 7 unverified
parse_stories in 5 papers data_process.py ran MIT (permissive) · e94421d72e63a32e · report fixture: signature lines:list/1/bytes, only_supporting:bool/0/bool · returned list · level recorded 2026-09-26
tokenize in 176 papers data_process.py ran fingerprinted MIT (permissive) · a8a4fc29963cfdd9 · report fixture: signature sentence:str/0/str · returned list · level recorded 2026-09-26
get_stories data_process.py unverified MIT (permissive) · 02143fa734f99d53 · report
get_stories src/babi_baseline.py unverified MIT (permissive) · 6a417e8bf87cd8fa · report
parse_stories in 5 papers kerasTeam.py unverified MIT (permissive) · 86ebfb268b5ff1d1 · report
parse_stories in 5 papers src/babi_baseline.py unverified MIT (permissive) · 31d3313b31e0ce05 · report
parse_stories in 5 papers src/single_layer_v5.py unverified MIT (permissive) · d59d30f527e3ff33 · report
tokenize in 176 papers kerasTeam.py unverified MIT (permissive) · dbf39005cc117d57 · report
tokenize in 176 papers src/single_layer_v5.py unverified MIT (permissive) · 8ec1ed5d99153049 · report
ishalyminov/memn2n community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
position_encoding in 13 papers memn2n/memn2n.py ran · honoured contract fingerprinted MIT (permissive) · b0ca12d8cc81c8be · report fixture: signature sentence_size:int/0/int, embedding_size:int/0/int · returned ndarray · level recorded 2026-09-22
nbansal90/bAbi_QA community (archive-listed) 2 samples, 0 ran · 2 unverified
get_stories memnn.py unverified no licence file found · pointer only · 67aee3b89ae06d5a · report
parse_stories in 5 papers memnn.py unverified no licence file found · pointer only · 0753ec8f5509e983 · report
prashil2792/Question-Answering-System-Deep-Learning community (archive-listed) 1 sample, 0 ran · 1 unverified
parse_stories in 5 papers memorynetwork.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 · 9d142ef2a5e220be · report

Tasks

Language ModelingLanguage ModellingQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering bAbi End-To-End Memory Networks Accuracy (trained on 10k) 93.4% #6 of 14 Archive leaderboard report
Question Answering bAbi End-To-End Memory Networks Accuracy (trained on 1k) 86.1% #6 of 14 Archive leaderboard report
Question Answering bAbi End-To-End Memory Networks Mean Error Rate 7.5% #6 of 14 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

Introduced by this paper: End-To-End Memory Network

End-To-End Memory NetworkSoftmax

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