Papers › Towards Robust and Semantically Organised Latent Representations for Unsupervised Text...

Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer

4 May 2022NAACL 2022 7arXiv:2205.02309archive 2025-07-28

Sharan Narasimhan, Suvodip Dey, Maunendra Sankar Desarkar

Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. The latent space geometry of such models is organised well enough to perform on datasets where the style is "coarse-grained" i.e. a small fraction of words alone in a sentence are enough to determine the overall style label. A recent study uses a discrete token-based perturbation approach to map "similar" sentences ("similar" defined by low Levenshtein distance/ high word overlap) close by in latent space. This definition of "similarity" does not look into the underlying nuances of the constituent words while mapping latent space neighbourhoods and therefore fails to recognise sentences with different style-based semantics while mapping latent neighbourhoods. We introduce EPAAEs (Embedding Perturbed Adversarial AutoEncoders) which completes this perturbation model, by adding a finely adjustable noise component on the continuous embeddings space. We empirically show that this (a) produces a better organised latent space that clusters stylistically similar sentences together, (b) performs best on a diverse set of text style transfer tasks than similar denoising-inspired baselines, and (c) is capable of fine-grained control of Style Transfer strength. We also extend the text style transfer tasks to NLI datasets and show that these more complex definitions of style are learned best by EPAAE. To the best of our knowledge, extending style transfer to NLI tasks has not been explored before.

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 14 code samples harvested from 1 repository linked to this paper: 11 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 6 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: official repository: 14 samples from 1 repository, 11 ran (4 with no instrument failure; 7 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

sharan21/epaae officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 11 ran (7 instrument-failed) · 3 unverified 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

14 samples harvested: 11 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 3 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
6ran · our draft was wrong
1ran; the contract check could not run
1ran
3unverified

Licence: 14 of the 14 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 sharan21/epaae. “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.

sharan21/epaae official repository 14 samples, 11 ran (7 instrument-failed) · 3 unverified
TextModel model.py ran · metamorphic tier: deterministic no licence file found · pointer only · bb9989b32e830301 · report fixture: returned TextModel · level recorded 2026-09-22
get_anneal_weight model.py ran · honoured contract no licence file found · pointer only · fde366f6463eb000 · report fixture: signature step:int/0/int, args:ArgsConfig/0/? · returned float · level recorded 2026-09-22
get_glove model.py ran · honoured contract no licence file found · pointer only · 2c5ac586d6bbd26e · report fixture: signature vocab:Vocab/0/?, embd_dim:int/0/int · returned ndarray · level recorded 2026-09-22
load_glove in 6 papers model.py ran · our draft was wrong no licence file found · pointer only · f33b25fbebcd0a54 · report fixture: signature embd_dim:int/0/int · returned dict · level recorded 2026-09-22
log_prob in 9 papers model.py ran · honoured contract fingerprinted no licence file found · pointer only · 4ebc241db4d9569d · report fixture: signature z:Tensor/2/float, mu:Tensor/2/float, logvar:Tensor/2/float · returned Tensor · level recorded 2026-09-22
noisy in 5 papers model.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 804024b3e7ec5ab5 · report fixture: signature vocab:Vocab/0/?, x:Tensor/2/int, drop_prob:float/0/float, blank_prob:float/0/float, sub_prob:float/0/float, shuffle_dist:int/0/int · returned Tensor · level recorded 2026-09-22
reparameterize in 38 papers
census: 12 implementations from 17 papers, 5 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 447585e6fedec167 · report fixture: signature mu:Tensor/2/float, logvar:Tensor/2/float · returned Tensor · level recorded 2026-09-22
word_blank model.py ran · our draft was wrong no licence file found · pointer only · 17919456d86a482f · report fixture: signature vocab:Vocab/0/?, x:Tensor/2/int, p:float/0/float · returned Tensor · level recorded 2026-09-22
word_drop model.py ran · our draft was wrong no licence file found · pointer only · 29cab3c8d0e924a4 · report fixture: signature vocab:Vocab/0/?, x:Tensor/2/int, p:float/0/float · returned Tensor · level recorded 2026-09-22
word_shuffle model.py ran · our draft was wrong no licence file found · pointer only · bcb6a0a9acc041dd · report fixture: signature vocab:Vocab/0/?, x:Tensor/2/int, k:int/0/int · returned Tensor · level recorded 2026-09-22
word_substitute model.py ran · our draft was wrong no licence file found · pointer only · e8d1d1068d437816 · report fixture: signature vocab:MockVocab/0/?, x:Tensor/2/int, p:float/0/float · returned Tensor · level recorded 2026-09-22
AAE model.py unverified no licence file found · pointer only · ea8ebd56c7715792 · report
DAE model.py unverified no licence file found · pointer only · 82c5126ce64df11b · report
embd_noise model.py unverified no licence file found · pointer only · 7870307065180eaa · report

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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for EPAAEs (Embedding Perturbed Adversarial AutoEncoders) (graph method: EPAAEs (Embedding Perturbed Adversarial AutoEncoders)). 14 bricks; individually on a fixture: 11 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. AAE entry · level 0 · unverified · ea8ebd56c7715792
  2. DAE model · level 0 · unverified · 82c5126ce64df11b
  3. TextModel helper · level 1 · ran · bb9989b32e830301
  4. embd_noise helper · level 0 · unverified · 7870307065180eaa
  5. get_anneal_weight helper · level 1 · ran · honoured contract · fde366f6463eb000
  6. log_prob helper · level 1 · ran · honoured contract · 4ebc241db4d9569d
  7. noisy helper · level 1 · ran; the contract check could not run (RAISES) · 804024b3e7ec5ab5
  8. reparameterize helper · level 1 · ran · our draft was wrong · 447585e6fedec167
  9. get_glove helper · level 1 · ran · honoured contract · 2c5ac586d6bbd26e
  10. word_blank helper · level 1 · ran · our draft was wrong · 17919456d86a482f
  11. word_drop helper · level 1 · ran · our draft was wrong · 29cab3c8d0e924a4
  12. word_shuffle helper · level 1 · ran · our draft was wrong · bcb6a0a9acc041dd
  13. word_substitute helper · level 1 · ran · our draft was wrong · e8d1d1068d437816
  14. load_glove helper · level 1 · ran · our draft was wrong · f33b25fbebcd0a54

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="2205.02309") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DenoisingSentenceStyle TransferText GenerationText Style TransferUnsupervised Text Style Transfer

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