Papers › A Probabilistic Formulation of Unsupervised Text Style Transfer

A Probabilistic Formulation of Unsupervised Text Style Transfer

10 Feb 2020ICLR 2020 1arXiv:2002.03912archive 2025-07-28

Junxian He, Xinyi Wang, Graham Neubig, Taylor Berg-Kirkpatrick

We present a deep generative model for unsupervised text style transfer that unifies previously proposed non-generative techniques. Our probabilistic approach models non-parallel data from two domains as a partially observed parallel corpus. By hypothesizing a parallel latent sequence that generates each observed sequence, our model learns to transform sequences from one domain to another in a completely unsupervised fashion. In contrast with traditional generative sequence models (e.g. the HMM), our model makes few assumptions about the data it generates: it uses a recurrent language model as a prior and an encoder-decoder as a transduction distribution. While computation of marginal data likelihood is intractable in this model class, we show that amortized variational inference admits a practical surrogate. Further, by drawing connections between our variational objective and other recent unsupervised style transfer and machine translation techniques, we show how our probabilistic view can unify some known non-generative objectives such as backtranslation and adversarial loss. Finally, we demonstrate the effectiveness of our method on a wide range of unsupervised style transfer tasks, including sentiment transfer, formality transfer, word decipherment, author imitation, and related language translation. Across all style transfer tasks, our approach yields substantial gains over state-of-the-art non-generative baselines, including the state-of-the-art unsupervised machine translation techniques that our approach generalizes. Further, we conduct experiments on a standard unsupervised machine translation task and find that our unified approach matches the current state-of-the-art.

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

The archive's official repository (cindyxinyiwang/deep-latent-sequence-model) was not harvested; the 22 samples below come from 2 community repositories, and 3 more are identical to code Syntology harvested from another paper's repository.

Syntology 25 code samples: 22 from 2 repositories linked to this paper, 3 identical to code harvested from another paper's repository. Across all 25: 18 ran (of which 13 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 22 samples from 2 repositories, 15 ran (11 with no instrument failure; 4 where Syntology's instrument failed); 3 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

cindyxinyiwang/deep-latent-sequence-model officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
cindyxinyiwang/TextStyleTransfer mentioned on GitHubpytorchSyntology: 9 samples, 6 ran (3 instrument-failed) · 3 unverified report
kaletap/nlp-experiments mentioned on GitHubpytorchSyntology: not harvested report
martiansideofthemoon/style-transfer-paraphrase mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Reformulating Unsupervised Style Transfer as Paraphrase Generation (arXiv:2010.05700; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
thu-coai/NAST mentioned on GitHubpytorchSyntology: 13 samples, 9 ran (1 instrument-failed) · 4 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.

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

25 samples harvested: 18 ran (of which 13 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 7 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.

5ran · our draft was wrong
2ran; the contract check could not run
11ran
7unverified

Licence: 12 of the 25 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 2 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. 3 samples are 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.

cindyxinyiwang/TextStyleTransfer community (archive-listed) 9 samples, 6 ran (3 instrument-failed) · 3 unverified
Beam in 8 papers src/transformer.py ran no licence file found · pointer only · 2a0fe14622f8497d · report fixture: returned Beam · level recorded 2026-09-22
Hyp src/transformer.py ran no licence file found · pointer only · 9f75aa33a1ccdc32 · report fixture: returned Hyp · level recorded 2026-09-22
PolyNorm src/transformer.py ran no licence file found · pointer only · e2b9062d0b945f4b · report fixture: returned PolyNorm · level recorded 2026-09-22
advcance_ens_beam src/transformer.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · 7a943e0929e23b36 · report fixture: signature hparams:HParams/0/?, word_scores:Tensor/3/float, ens_beam_list:list/1/Beam, step:int/0/int · returned bool · level recorded 2026-09-22
select_active_enc_info src/transformer.py ran · our draft was wrong no licence file found · pointer only · ca8292bfcf4d9b5a · report fixture: signature enc_output:Tensor/2/float, active_inst_idx_list:Tensor/1/int, n_remain_sents:int/0/int, src_seq_len:int/0/int, d_model:int/0/int · returned Tensor · level recorded 2026-09-22
select_active_enc_mask src/transformer.py ran · our draft was wrong no licence file found · pointer only · a97450c4460623c1 · report fixture: signature enc_mask:Tensor/2/float, active_inst_idx_list:Tensor/1/int, n_remain_sents:int/0/int, src_seq_len:int/0/int · returned Tensor · level recorded 2026-09-22
Decoder in 210 papers src/transformer.py unverified no licence file found · pointer only · 7a121f5925381565 · report
Encoder in 278 papers src/transformer.py unverified no licence file found · pointer only · 4e9d07e2d5cbf009 · report
Transformer in 173 papers src/transformer.py unverified no licence file found · pointer only · 30cf69b3b879a328 · report
thu-coai/NAST community (archive-listed) 13 samples, 9 ran (1 instrument-failed) · 4 unverified
DecoderLayer in 43 papers styletransformer/transformer.py ran · metamorphic tier: deterministic MIT (permissive) · f62647ab841d8eac · report fixture: returned DecoderLayer · level recorded 2026-09-22
EmbeddingLayer in 10 papers styletransformer/transformer.py ran · metamorphic tier: deterministic MIT (permissive) · fd281e0df749b749 · report fixture: returned EmbeddingLayer · level recorded 2026-09-22
Encoder in 278 papers styletransformer/transformer.py ran · metamorphic tier: deterministic MIT (permissive) · ac16887aad3c401d · report fixture: returned Encoder · level recorded 2026-09-22
EncoderLayer in 73 papers styletransformer/transformer.py ran · metamorphic tier: deterministic MIT (permissive) · fe38343a20d6cec6 · report fixture: returned EncoderLayer · level recorded 2026-09-22
Generator in 95 papers styletransformer/transformer.py ran · metamorphic tier: deterministic MIT (permissive) · 31ab6deda5fe5457 · report fixture: returned Generator · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
styletransformer/transformer.py ran · our draft was wrong MIT (permissive) · 244df97d092c7e06 · report fixture: signature embedding_dim:int/0/int, eps:float/0/float · returned LayerNorm · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
styletransformer/transformer.py ran MIT (permissive) · b9a5bb409e08cbc8 · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, mask:Tensor/4/bool · returned Tensor · level recorded 2026-09-24
PositionwiseFeedForward in 36 papers styletransformer/transformer.py ran · metamorphic tier: deterministic MIT (permissive) · 94350806140c9d40 · report fixture: returned PositionwiseFeedForward · level recorded 2026-09-22
SublayerConnection in 16 papers styletransformer/transformer.py ran · metamorphic tier: deterministic MIT (permissive) · 3e2638d464cbc25c · report fixture: returned SublayerConnection · level recorded 2026-09-22
Decoder in 210 papers styletransformer/transformer.py unverified MIT (permissive) · dbea3ea139953d0c · report
HiddenDecoder styletransformer/transformer.py unverified MIT (permissive) · 159a44511500802f · report
LengthPredictor styletransformer/transformer.py unverified MIT (permissive) · 6d9d8f5da460708b · report
StyleTransformer styletransformer/transformer.py unverified MIT (permissive) · e73587b60482cbcc · report
Repository not located 3 samples, 3 ran (3 instrument-failed) · 0 unverified
3 samples are 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.
Embedding in 90 papers repository not located ran · our draft was wrong licence of this copy not recorded · cc6417e762730325 · report fixture: signature num_embeddings:int/0/int, embedding_dim:int/0/int, padding_idx:int/0/int · returned Embedding · level recorded 2026-09-22
Linear in 127 papers repository not located ran · our draft was wrong licence of this copy not recorded · 01f0f6d4a6e475b1 · report fixture: signature in_features:int/0/int, out_features:int/0/int, bias:bool/0/bool, uniform:bool/0/bool · returned Linear · level recorded 2026-09-22
scaled_attention repository not located ran; the contract check could not run (RAISES) · metamorphic tier: deterministic licence of this copy not recorded · 97bd0c0f69d68e77 · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, mask:Tensor/3/bool · returned tuple · 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.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for A Probabilistic Formulation of Unsupervised Text Style Transfer (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for A Probabilistic Formulation of Unsupervised Text Style Transfer (graph method: A Probabilistic Formulation of Unsupervised Text Style Transfer). 16 bricks; individually on a fixture: 12 ran (of which 10 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. StyleTransformer entry · level 0 · unverified · e73587b60482cbcc
  2. Decoder model · level 0 · unverified · dbea3ea139953d0c
  3. Embedding helper · level 1 · ran · our draft was wrong · cc6417e762730325
  4. EmbeddingLayer model · level 1 · ran · fd281e0df749b749
  5. Encoder model · level 1 · ran · ac16887aad3c401d
  6. LengthPredictor helper · level 0 · unverified · 6d9d8f5da460708b
  7. DecoderLayer helper · level 1 · ran · f62647ab841d8eac
  8. Generator model · level 1 · ran · 31ab6deda5fe5457
  9. LayerNorm helper · level 1 · ran · our draft was wrong · 244df97d092c7e06
  10. EncoderLayer helper · level 1 · ran · fe38343a20d6cec6
  11. HiddenDecoder helper · level 0 · unverified · 159a44511500802f
  12. MultiHeadAttention model · level 1 · ran · b9a5bb409e08cbc8
  13. PositionwiseFeedForward model · level 1 · ran · 94350806140c9d40
  14. SublayerConnection model · level 1 · ran · 3e2638d464cbc25c
  15. scaled_attention helper · level 1 · ran; the contract check could not run (RAISES) · 97bd0c0f69d68e77
  16. Linear helper · level 1 · ran · our draft was wrong · 01f0f6d4a6e475b1

harvested Assembly for A Probabilistic Formulation of Unsupervised Text Style Transfer (graph method: A Probabilistic Formulation of Unsupervised Text Style Transfer). 9 bricks; individually on a fixture: 6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. Transformer entry · level 0 · unverified · 30cf69b3b879a328
  2. Beam sampler · level 1 · ran · 2a0fe14622f8497d
  3. Decoder model · level 0 · unverified · 7a121f5925381565
  4. Encoder model · level 0 · unverified · 4e9d07e2d5cbf009
  5. Hyp helper · level 1 · ran · 9f75aa33a1ccdc32
  6. advcance_ens_beam helper · level 1 · ran; the contract check could not run (RAISES) · 7a943e0929e23b36
  7. select_active_enc_info helper · level 1 · ran · our draft was wrong · ca8292bfcf4d9b5a
  8. select_active_enc_mask helper · level 1 · ran · our draft was wrong · a97450c4460623c1
  9. PolyNorm helper · level 1 · ran · e2b9062d0b945f4b

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="2002.03912") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DeciphermentLanguage ModellingMachine TranslationStyle TransferText Style TransferTranslationUnsupervised Machine TranslationUnsupervised Text Style TransferVariational Inference

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