Browse State-of-the-Art › Text Style Transfer
Text Style Transfer
93 papers with code · 2 benchmarks · 7 datasets archive 2025-07-28
Text Style Transfer is the task of controlling certain attributes of generated text. The state-of-the-art methods can be categorized into two main types which are used on parallel and non-parallel data. Methods on parallel data are typically supervised methods that use a neural sequence-to-sequence model with the encoder-decoder architecture. Methods on non-parallel data are usually unsupervised approaches using Disentanglement, Prototype Editing and Pseudo-Parallel Corpus Construction.
The popular benchmark for this task is the Yelp Review Dataset. Models are typically evaluated with the metrics of Sentiment Accuracy, BLEU, and PPL.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Yelp Review Dataset (Small) (8 rows) | SAE+Discriminator | Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites | code | Syntology 0 ran · 1 unverified | Compare |
| Yelp Review Dataset (Large) (2 rows) | SentiInc | SentiInc: Incorporating Sentiment Information into Sentiment... | — | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
7 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
3 subtasks in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 186 · with a code link: 93 · where Syntology ran a sample: 15 (12 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (15 of 186 tagged: 12 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 186, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
26 May 2017 12 repositories listed Syntology community repositories only · 6 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; 5 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 6 pointer-only (licence)We demonstrate the effectiveness of this cross-alignment method on three tasks: sentiment modification, decipherment of word substitution ciphers, and recovery of word order.
-
10 Feb 2020 5 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 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 (of 25 harvested samples) · 12 pointer-only (licence)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…
-
6 Dec 2021 4 repositories listedText Style Transfer (TST) aims to alter the underlying style of the source text to another specific style while keeping the same content.
-
14 May 2019 4 repositories listed Syntology community repositories only · 3 ran (of which 2 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)Disentangling the content and style in the latent space is prevalent in unpaired text style transfer.
-
7 Mar 2022 3 repositories listedWe introduce IT5, the first family of encoder-decoder transformer models pretrained specifically on Italian.
-
17 Feb 2021 3 repositories listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)Recent works have demonstrated reasonable success of representation learning in hypercomplex space.
-
29 May 2019 3 repositories listedWe prove that this simple modification guides the latent space geometry of the resulting model by encouraging the encoder to map similar texts to similar latent representations.
-
31 Jan 2019 3 repositories listedText attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content.
-
1 Nov 2018 3 repositories listedThe dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "style".
-
13 Aug 2018 3 repositories listed Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)This paper tackles the problem of disentangling the latent variables of style and content in language models.
-
24 Apr 2018 3 repositories listedWe first learn a latent representation of the input sentence which is grounded in a language translation model in order to better preserve the meaning of the sentence while reducing stylistic properties.
-
31 May 2024 2 repositories listedText style transfer (TST) involves altering the linguistic style of a text while preserving its core content.
-
14 Nov 2023 2 repositories listedLanguage style is necessary for AI systems to understand and generate diverse human language accurately.
-
20 Jun 2022 2 repositories listedText style transfer techniques are gaining popularity in Natural Language Processing, finding various applications such as text detoxification, sentiment, or formality transfer.
-
12 Apr 2021 2 repositories listedMany of the existing style transfer benchmarks primarily focus on individual high-level semantic changes (e. g. positive to negative), which enable controllability at a high level but do not offer fine-grained control…
-
1 Nov 2020 2 repositories listedText style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and many others.
-
24 Oct 2020 2 repositories listedThis article aims to provide a comprehensive review of recent research efforts on text style transfer.
-
24 May 2019 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 4 unverified (of 4 harvested samples)Therefore, in this paper, we propose a dual reinforcement learning framework to directly transfer the style of the text via a one-step mapping model, without any separation of content and style.
-
15 Oct 2018 2 repositories listed Syntology community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)Text style transfer aims to modify the style of a sentence while keeping its content unchanged.
-
18 Nov 2017 2 repositories listedResults show that the proposed content preservation metric is highly correlate to human judgments, and the proposed models are able to generate sentences with higher style transfer strength and similar content…
-
16 Dec 2024 1 repository listedEven with various regulations in place across countries and social media platforms (Government of India, 2021; European Parliament and Council of the European Union, 2022, digital abusive speech remains a significant…
-
1 Oct 2024 1 repository listed Syntology official (archive's flag): 2 ran · 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 (of 3 harvested samples) · 3 pointer-only (licence)Text style transfer (TST) aims to modify the style of a text without altering its original meaning.
-
31 Jul 2024 1 repository listedOne challenge of the task is that the local stroke shapes of artistic text are changeable with diversity and complexity.
-
20 Jul 2024 1 repository listed Syntology official (archive's flag): 1 ran · 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) · 1 unverified (of 2 harvested samples)With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses.
-
21 Jun 2024 1 repository listedThe goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style.
-
17 Jun 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)Numerous recent techniques for text style transfer characterize their approaches as variants of reinforcement learning and preference optimization.
-
9 Jun 2024 1 repository listedWe analyze the performance of large language models (LLMs) on Text Style Transfer (TST), specifically focusing on sentiment transfer and text detoxification across three languages: English, Hindi, and Bengali.
-
12 Feb 2024 1 repository listedThis task contributes to safer and more respectful online communication and can be considered a Text Style Transfer (TST) task, where the text style changes while its content is preserved.
-
11 Jan 2024 1 repository listedText style transfer is increasingly prominent in online entertainment and social media.
-
13 Nov 2023 1 repository listedWe propose STEER: Unified Style Transfer with Expert Reinforcement, a unified frame-work developed to overcome the challenge of limited parallel data for style transfer.
-
23 Oct 2023 1 repository listed
-
19 Sep 2023 1 repository listed
-
17 Aug 2023 1 repository listed Syntology official (archive's flag): 7 ran · 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) · 1 unverified (of 8 harvested samples)
-
8 Aug 2023 1 repository listed
-
12 Jun 2023 1 repository listed
-
5 Jun 2023 1 repository listed
-
2 Jun 2023 1 repository listed
-
31 May 2023 1 repository listed
-
26 Apr 2023 1 repository listed
-
27 Jan 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
20 Dec 2022 1 repository listed
-
14 Nov 2022 1 repository listed
-
29 Aug 2022 1 repository listed
-
1 Aug 2022 1 repository listed
-
1 Jul 2022 1 repository listed
-
25 May 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
24 May 2022 1 repository listed
-
19 May 2022 1 repository listed
-
9 May 2022 1 repository listed
-
4 May 2022 1 repository listed Syntology official (archive's flag): 11 ran · 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 (of 14 harvested samples) · 14 pointer-only (licence)
-
1 May 2022 1 repository listed
-
20 Apr 2022 1 repository listed
-
18 Apr 2022 1 repository listed
-
15 Apr 2022 1 repository listed
-
6 Apr 2022 1 repository listed
-
4 Apr 2022 1 repository listed Syntology official (archive's flag): 5 ran · 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 (of 5 harvested samples)
-
16 Mar 2022 1 repository listed
-
27 Feb 2022 1 repository listed
-
1 Nov 2021 1 repository listed
-
1 Nov 2021 1 repository listed
-
14 Oct 2021 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
6 Oct 2021 1 repository listed
-
19 Sep 2021 1 repository listed
-
16 Sep 2021 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples)
-
1 Aug 2021 1 repository listed
-
29 Jun 2021 1 repository listed
-
15 Jun 2021 1 repository listed
-
4 Jun 2021 1 repository listed Syntology official: harvested for another paper · 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
18 May 2021 1 repository listed Syntology official: no sample here; runs from other or unrecorded repositories · 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 (of 1 harvested sample)
-
1 Feb 2021 1 repository listed
-
1 Dec 2020 1 repository listed
-
27 Nov 2020 1 repository listed
-
24 Oct 2020 1 repository listed
-
10 Oct 2020 1 repository listed
-
8 Oct 2020 1 repository listed
-
2 Sep 2020 1 repository listed
-
1 Jul 2020 1 repository listed
-
12 Jun 2020 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 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) · 2 unverified (of 3 harvested samples)
-
25 May 2020 1 repository listed
-
24 Feb 2020 1 repository listed
-
14 Sep 2019 1 repository listed
-
25 Aug 2019 1 repository listed
-
25 Aug 2019 1 repository listed
-
5 Jun 2019 1 repository listed
-
29 May 2019 1 repository listed
-
28 May 2019 1 repository listed
-
3 May 2019 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
22 Aug 2018 1 repository listed
-
30 May 2018 1 repository listed
-
14 May 2018 1 repository listed
-
19 Apr 2018 1 repository listed
-
Implementing Long Text Style Transfer with LLMs through Dual-Layered Sentence and Paragraph Structure Extraction and Mapping11 May 2025 0 repositories listed
-
Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics?7 Feb 2025 0 repositories listed
-
Predicting Compact Phrasal Rewrites with Large Language Models for ASR Post Editing23 Jan 2025 0 repositories listed
-
Multi-Attribute Constraint Satisfaction via Language Model Rewriting26 Dec 2024 0 repositories listed
-
A Survey of Text Style Transfer: Applications and Ethical Implications23 Jul 2024 0 repositories listed
-
SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning22 Jul 2024 0 repositories listed
-
Text Style Transfer: An Introductory Overview20 Jul 2024 0 repositories listed
Syntology lines on 21 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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