Papers › Generating Sentences from a Continuous Space

Generating Sentences from a Continuous Space

19 Nov 2015CONLL 2016 8arXiv:1511.06349archive 2025-07-28

Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew M. Dai, Rafal Jozefowicz, Samy Bengio

The standard recurrent neural network language model (RNNLM) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an RNN-based variational autoencoder generative model that incorporates distributed latent representations of entire sentences. This factorization allows it to explicitly model holistic properties of sentences such as style, topic, and high-level syntactic features. Samples from the prior over these sentence representations remarkably produce diverse and well-formed sentences through simple deterministic decoding. By examining paths through this latent space, we are able to generate coherent novel sentences that interpolate between known sentences. We present techniques for solving the difficult learning problem presented by this model, demonstrate its effectiveness in imputing missing words, explore many interesting properties of the model's latent sentence space, and present negative results on the use of the model in language modeling.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 31 code samples: 30 from 10 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 31: 14 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 17 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 30 samples from 10 repositories, 13 ran (12 with no instrument failure; 1 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 3 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.

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

Chung-I/Variational-Recurrent-Autoencoder-Tensorflow mentioned on GitHubtfSyntology: 6 samples, 0 ran · 6 unverified report
GiuliaLanzillotta/exercises mentioned on GitHubtfSyntology: not harvested report
NicGian/text_VAE mentioned on GitHubtfSyntology: not harvested report
StijnVerdenius/Boosting_Text_Classifiers_by_Generative_Modelling mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
aaronbae/ModifiedSentenceVAE mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
arvind385801/paraphrasegen mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Distributed Representations of Words and Phrases and their Compositionality (arXiv:1310.4546; that paper's own run record: 21 ran (of which 2 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
clutr/clutr mentioned on GitHubpytorchSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
isabelline/Text_VAE_tf mentioned on GitHubtfSyntology: not harvested report
jmtomczak/vae_householder_flow mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving Variational Auto-Encoders using Householder Flow (arXiv:1611.09630; that paper's own run record: 1 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; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
kefirski/pytorch_RVAE mentioned on GitHubpytorchSyntology: 9 samples, 2 ran (1 instrument-failed) · 7 unverified report
pranjalg96/Stylized-Image-captioning mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
ryokamoi/original_textvae mentioned on GitHubtfMITSyntology: not harvested report
sindhusweety/VAE-Generating-Sentences-From-a-Continuous-Space mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
timbmg/Sentence-VAE mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
twairball/keras_lstm_vae mentioned on GitHubMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
wiseodd/controlled-text-generation mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified 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

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

31 samples harvested: 14 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 17 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 · honoured contract
1ran · violated contract
2ran · our draft was wrong
9ran
17unverified

Licence: 19 of the 31 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 10 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. 1 sample is listed last, in a group without a repository. “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: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

Chung-I/Variational-Recurrent-Autoencoder-Tensorflow community (archive-listed) 6 samples, 0 ran · 6 unverified
DiagonalGaussian seq2seq.py unverified no licence file found · pointer only · 3aa0fee32833e525 · report
gaussian_diag_logps seq2seq.py unverified no licence file found · pointer only · 6a3f97eabb0e0593 · report
sample in 167 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
seq2seq.py unverified no licence file found · pointer only · 2ce2edf795968921 · report
sequence_loss in 15 papers seq2seq.py unverified no licence file found · pointer only · 1f47f6d9b3d8e1b4 · report
sequence_loss_by_example seq2seq.py unverified no licence file found · pointer only · 8817ecd42aece095 · report
variational_autoencoder_with_buckets seq2seq.py unverified no licence file found · pointer only · 3efc2abded581bfb · report
StijnVerdenius/Boosting_Text_Classifiers_by_Generative_Modelling community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
GeneralModel models/generators/SentenceVAE.py ran no licence file found · pointer only · 519ea45327d29280 · report fixture: signature current_best:float/0/float, loss:float/0/float, accuracy:float/0/float · returned bool · level recorded 2026-09-24
SentenceVAE models/generators/SentenceVAE.py ran no licence file found · pointer only · 5dcc088a465cd336 · report fixture: signature input_sequence:Tensor/2/int, lengths:Tensor/1/int, step:int/0/int · returned tuple · level recorded 2026-09-24
aaronbae/ModifiedSentenceVAE community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SentenceVAE model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 70ae1759582e14cd · report fixture: returned SentenceVAE · level recorded 2026-09-22
clutr/clutr community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
ClutrEmbedding task_embed/clutr_RVAE/model/rvae.py ran licence not identified · pointer only · 01b38ffbbdc08e19 · report fixture: returned ClutrEmbedding · level recorded 2026-09-22
Encoder in 278 papers task_embed/clutr_RVAE/model/rvae.py ran licence not identified · pointer only · 74b19fb734f820f4 · report fixture: returned Encoder · level recorded 2026-09-22
Highway in 5 papers task_embed/clutr_RVAE/model/rvae.py ran fingerprinted licence not identified · pointer only · e4359767bf930518 · report fixture: returned Highway · level recorded 2026-09-22
kld_coef task_embed/clutr_RVAE/model/rvae.py ran · honoured contract fingerprinted licence not identified · pointer only · cb6715e93952a5b1 · report fixture: signature i:int/0/int · returned float · level recorded 2026-09-22
Decoder in 210 papers task_embed/clutr_RVAE/model/rvae.py unverified licence not identified · pointer only · 91e0f91c79cb5abd · report
RVAE task_embed/clutr_RVAE/model/rvae.py unverified licence not identified · pointer only · c00adaa69df91ca6 · report
kefirski/pytorch_RVAE community (archive-listed) 9 samples, 2 ran (1 instrument-failed) · 7 unverified
f_and model/rvae.py ran · violated contract fingerprinted MIT (permissive) · abef1871f56ceeb2 · report fixture: signature x:bool/0/bool, y:bool/0/bool · returned bool · level recorded 2026-09-22
fold in 10 papers model/rvae.py ran · our draft was wrong MIT (permissive) · 0381de7a8ac5ced5 · report fixture: signature f:callable/0/?, l:list/1/int, a:int/0/int · returned int · level recorded 2026-09-22
Decoder in 210 papers model/rvae.py unverified MIT (permissive) · 8e80e3c35950e569 · report
Embedding in 90 papers model/rvae.py unverified MIT (permissive) · f095a1e3a4e44d91 · report
Encoder in 278 papers model/rvae.py unverified MIT (permissive) · 3f940d9bc8f717e1 · report
RVAE model/rvae.py unverified MIT (permissive) · 7e97f7b2da18a1ab · report
TDNN model/rvae.py unverified MIT (permissive) · 80456d6dd2ae8003 · report
f_or model/rvae.py unverified MIT (permissive) · c13de86adc9e9594 · report
parameters_allocation_check model/rvae.py unverified MIT (permissive) · 8f395eeb81e91562 · report
pranjalg96/Stylized-Image-captioning community (archive-listed) 1 sample, 0 ran · 1 unverified
RNN_VAE SST_files/ctextgen/model.py unverified BSD-3-Clause (permissive) · a431fd85f112cebc · report
sindhusweety/VAE-Generating-Sentences-From-a-Continuous-Space community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VAE in 29 papers model.py ran no licence file found · pointer only · 7e6ae924c7773d3e · report fixture: returned VAE · level recorded 2026-09-22
timbmg/Sentence-VAE community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
SentenceVAE model.py ran no licence file found · pointer only · 30bc598c6cdb8c2a · report fixture: returned SentenceVAE · level recorded 2026-09-22
to_var in 51 papers
census: 12 implementations from 21 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
model.py ran · honoured contract fingerprinted no licence file found · pointer only · 36326e7b5eb789e9 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
twairball/keras_lstm_vae community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
create_lstm_autoencoder lstm_vae/autoencoder.py ran MIT (permissive) · 75924d8b8887223c · report fixture: signature input_dim:int/0/int, timesteps:int/0/int, latent_dim:int/0/int · returned Functional · level recorded 2026-09-26
wiseodd/controlled-text-generation community (archive-listed) 1 sample, 0 ran · 1 unverified
RNN_VAE ctextgen/model.py unverified BSD-3-Clause (permissive) · 1e7396ef5e17180b · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
to_var in 51 papers
census: 12 implementations from 21 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 502c50812b7f31ab · report fixture: signature x:Tensor/2/float, volatile:bool/0/bool · returned Tensor · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

9 assemblies on this paper: 9 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

9 sibling assemblies for rnn-based variational autoencoder generative model (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for rnn-based variational autoencoder generative model (graph method: rnn-based variational autoencoder generative model). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. SentenceVAE entry · level 1 · ran · 70ae1759582e14cd
  2. to_var helper · level 1 · ran · our draft was wrong · 502c50812b7f31ab

harvested Assembly for rnn-based variational autoencoder generative model (graph method: rnn-based variational autoencoder generative model). 6 bricks; individually on a fixture: 0 ran · 6 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. variational_autoencoder_with_buckets entry · level 0 · unverified · 3efc2abded581bfb
  2. sample sampler · level 0 · unverified · 2ce2edf795968921
  3. sequence_loss helper · level 0 · unverified · 1f47f6d9b3d8e1b4
  4. sequence_loss_by_example helper · level 0 · unverified · 8817ecd42aece095
  5. DiagonalGaussian helper · level 0 · unverified · 3aa0fee32833e525
  6. gaussian_diag_logps helper · level 0 · unverified · 6a3f97eabb0e0593

harvested Assembly for rnn-based variational autoencoder generative model (graph method: rnn-based variational autoencoder generative model). 6 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. RVAE entry · level 0 · unverified · c00adaa69df91ca6
  2. ClutrEmbedding helper · level 1 · ran · 01b38ffbbdc08e19
  3. Decoder model · level 0 · unverified · 91e0f91c79cb5abd
  4. Encoder model · level 1 · ran · 74b19fb734f820f4
  5. kld_coef helper · level 1 · ran · honoured contract · cb6715e93952a5b1
  6. Highway helper · level 1 · ran · e4359767bf930518

harvested Assembly for rnn-based variational autoencoder generative model (graph method: rnn-based variational autoencoder generative model). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. SentenceVAE entry · level 1 · ran · 30bc598c6cdb8c2a
  2. to_var helper · level 1 · ran · honoured contract · 36326e7b5eb789e9

harvested Assembly for rnn-based variational autoencoder generative model (graph method: rnn-based variational autoencoder generative model). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 9 siblings

  1. VAE entry · level 1 · ran · 7e6ae924c7773d3e

harvested Assembly for rnn-based variational autoencoder generative model (graph method: rnn-based variational autoencoder generative model). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. RNN_VAE entry · level 0 · unverified · 1e7396ef5e17180b

harvested Assembly for rnn-based variational autoencoder generative model (graph method: rnn-based variational autoencoder generative model). 11 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. RVAE entry · level 0 · unverified · 7e97f7b2da18a1ab
  2. Decoder model · level 0 · unverified · 8e80e3c35950e569
  3. Embedding helper · level 0 · unverified · f095a1e3a4e44d91
  4. Encoder model · level 0 · unverified · 3f940d9bc8f717e1
  5. fold helper · level 1 · ran · our draft was wrong · 0381de7a8ac5ced5
  6. kld_coef helper · level 1 · ran · honoured contract · cb6715e93952a5b1
  7. parameters_allocation_check helper · level 0 · unverified · 8f395eeb81e91562
  8. TDNN helper · level 0 · unverified · 80456d6dd2ae8003
  9. Highway helper · level 1 · ran · e4359767bf930518
  10. f_and helper · level 1 · ran · violated contract · abef1871f56ceeb2
  11. f_or helper · level 0 · unverified · c13de86adc9e9594

harvested Assembly for rnn-based variational autoencoder generative model (graph method: rnn-based variational autoencoder generative model). 2 bricks; individually on a fixture: 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) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. SentenceVAE entry · level 1 · ran · 5dcc088a465cd336
  2. GeneralModel helper · level 1 · ran · 519ea45327d29280

harvested Assembly for rnn-based variational autoencoder generative model (graph method: rnn-based variational autoencoder generative model). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. RNN_VAE entry · level 0 · unverified · a431fd85f112cebc

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1511.06349") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage ModellingSentence

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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