Papers › Generating Sentences from a Continuous Space
Generating Sentences from a Continuous Space
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.
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="1511.06349")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1511.06349", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1511.06349")
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:
- arvind385801/paraphrasegen, community (archive-listed): harvested for another paper, listed under the repository
- jmtomczak/vae_householder_flow, community (archive-listed): harvested for another paper, listed under the repository
- PaddlePaddle/PaddleNLP, 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.
17 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
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.
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.
3aa0fee32833e525 · report
6a3f97eabb0e0593 · report
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
1f47f6d9b3d8e1b4 · report
8817ecd42aece095 · report
3efc2abded581bfb · report
519ea45327d29280 · report
fixture: signature current_best:float/0/float, loss:float/0/float, accuracy:float/0/float · returned bool · level recorded 2026-09-24 5dcc088a465cd336 · report
fixture: signature input_sequence:Tensor/2/int, lengths:Tensor/1/int, step:int/0/int · returned tuple · level recorded 2026-09-24 70ae1759582e14cd · report
fixture: returned SentenceVAE · level recorded 2026-09-22 01b38ffbbdc08e19 · report
fixture: returned ClutrEmbedding · level recorded 2026-09-22 74b19fb734f820f4 · report
fixture: returned Encoder · level recorded 2026-09-22 e4359767bf930518 · report
fixture: returned Highway · level recorded 2026-09-22 cb6715e93952a5b1 · report
fixture: signature i:int/0/int · returned float · level recorded 2026-09-22 91e0f91c79cb5abd · report
c00adaa69df91ca6 · report
abef1871f56ceeb2 · report
fixture: signature x:bool/0/bool, y:bool/0/bool · returned bool · level recorded 2026-09-22 0381de7a8ac5ced5 · report
fixture: signature f:callable/0/?, l:list/1/int, a:int/0/int · returned int · level recorded 2026-09-22 a431fd85f112cebc · report
7e6ae924c7773d3e · report
fixture: returned VAE · level recorded 2026-09-22 30bc598c6cdb8c2a · report
fixture: returned SentenceVAE · level recorded 2026-09-22 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 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 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.
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
- SentenceVAE entry · level 1 · ran ·
70ae1759582e14cd - 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
- variational_autoencoder_with_buckets entry · level 0 · unverified ·
3efc2abded581bfb - sample sampler · level 0 · unverified ·
2ce2edf795968921 - sequence_loss helper · level 0 · unverified ·
1f47f6d9b3d8e1b4 - sequence_loss_by_example helper · level 0 · unverified ·
8817ecd42aece095 - DiagonalGaussian helper · level 0 · unverified ·
3aa0fee32833e525 - 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
- RVAE entry · level 0 · unverified ·
c00adaa69df91ca6 - ClutrEmbedding helper · level 1 · ran ·
01b38ffbbdc08e19 - Decoder model · level 0 · unverified ·
91e0f91c79cb5abd - Encoder model · level 1 · ran ·
74b19fb734f820f4 - kld_coef helper · level 1 · ran · honoured contract ·
cb6715e93952a5b1 - 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
- SentenceVAE entry · level 1 · ran ·
30bc598c6cdb8c2a - 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
- 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
- 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
- RVAE entry · level 0 · unverified ·
7e97f7b2da18a1ab - Decoder model · level 0 · unverified ·
8e80e3c35950e569 - Embedding helper · level 0 · unverified ·
f095a1e3a4e44d91 - Encoder model · level 0 · unverified ·
3f940d9bc8f717e1 - fold helper · level 1 · ran · our draft was wrong ·
0381de7a8ac5ced5 - kld_coef helper · level 1 · ran · honoured contract ·
cb6715e93952a5b1 - parameters_allocation_check helper · level 0 · unverified ·
8f395eeb81e91562 - TDNN helper · level 0 · unverified ·
80456d6dd2ae8003 - Highway helper · level 1 · ran ·
e4359767bf930518 - f_and helper · level 1 · ran · violated contract ·
abef1871f56ceeb2 - 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
- SentenceVAE entry · level 1 · ran ·
5dcc088a465cd336 - 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
- 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
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