# Text Style Transfer on Yelp (Style, Content, Fluency Metrics)

Source: [Text Style Transfer on Yelp (Style, Content, Fluency Metrics)](<https://www.sota2.com/research/sota/text-style-transfer-on-yelp-style-content-fluency-metrics>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:04:51.108Z

Evaluation of models performing Text Style Transfer on the Yelp dataset, specifically measured using Style, Content, and Fluency scores.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Text Style Transfer |
| Dataset (including any stated split) | Yelp |
| Metric | Style Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Style Score](<https://www.sota2.com/research/sota/text-style-transfer-on-yelp-style-content-fluency-metrics.md?metric=Style%20Score>): Higher is better; unit: SCALAR.

- [Content Score](<https://www.sota2.com/research/sota/text-style-transfer-on-yelp-style-content-fluency-metrics.md?metric=Content%20Score>): Higher is better; unit: SCALAR.

- [Fluency Score](<https://www.sota2.com/research/sota/text-style-transfer-on-yelp-style-content-fluency-metrics.md?metric=Fluency%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Style Score | Result date | Report paper |
| --- | --- | --- | --- |
| RACOLN | 4 | Not recorded | 68fa6a7c1e209131cea28842 |
| Style Transformer | 3.7 | Not recorded | 68fa6a7c1e209131cea28842 |
| Deep Latent | 3.5 | Not recorded | 68fa6a7c1e209131cea28842 |
| ControlledGen | 3.3 | Not recorded | 68fa6a7c1e209131cea28842 |
| Cross-Alignment | 2.6 | Not recorded | 68fa6a7c1e209131cea28842 |

### RACOLN

Style Score: 4. Result ID: 698e3a7affc3901de09bd457.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7c1e209131cea28842.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a7c1e209131cea28842.md>)

Recorded evaluation configuration: {"evaluation\_type":"Human evaluation"}. This record does not assert independent reproduction.

### Style Transformer

Style Score: 3.7. Result ID: 698e3a7affc3901de09bd455.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7c1e209131cea28842.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66361e209131cea0ed33.md>)

Recorded evaluation configuration: {"evaluation\_type":"Human evaluation"}. This record does not assert independent reproduction.

### Deep Latent

Style Score: 3.5. Result ID: 698e3a7affc3901de09bd456.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7c1e209131cea28842.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676f1e209131cea16320.md>)

Recorded evaluation configuration: {"evaluation\_type":"Human evaluation"}. This record does not assert independent reproduction.

### ControlledGen

Style Score: 3.3. Result ID: 698e3a7affc3901de09bd454.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7c1e209131cea28842.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64dd1e209131cea06dcf.md>)

Recorded evaluation configuration: {"evaluation\_type":"Human evaluation"}. This record does not assert independent reproduction.

### Cross-Alignment

Style Score: 2.6. Result ID: 698e3a7affc3901de09bd453.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a7c1e209131cea28842.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63bc1e209131cea00874.md>)

[Implementation](<https://github.com/shentianxiao/language-style-transfer>)

Recorded evaluation configuration: {"evaluation\_type":"Human evaluation"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.