# Semantic Textual Similarity on SemEval Task 1 Spanish 2017 (Track 3)

Source: [Semantic Textual Similarity on SemEval Task 1 Spanish 2017 (Track 3)](<https://www.sota2.com/research/sota/semantic-textual-similarity-on-semeval-task-1-spanish-2017-track-3>)

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

Data updated: 2026-02-26T05:57:44.159Z

Evaluation of Semantic Textual Similarity performance on the Spanish track (Track 3) of the SemEval 2017 Task 1 dataset, typically measured using scaled Pearson correlation.

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 | Semantic Textual Similarity |
| Dataset (including any stated split) | SemEval Task 1 Spanish 2017 (Track 3) |
| Metric | Pearson R (x100) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Pearson R (x100)](<https://www.sota2.com/research/sota/semantic-textual-similarity-on-semeval-task-1-spanish-2017-track-3.md?metric=Pearson%20R%20(x100)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Pearson R (x100) | Result date | Report paper |
| --- | --- | --- | --- |
| ENCU | 85.59 | Not recorded | 68fa6a2a1e209131cea2686a |
| MBERT | 80.19 | Not recorded | 68fa6a2a1e209131cea2686a |
| MBERT | 78.93 | Not recorded | 68fa6a2a1e209131cea2686a |
| Cosine baseline | 71.17 | Not recorded | 68fa6a2a1e209131cea2686a |
| MBERT | 68.16 | Not recorded | 68fa6a2a1e209131cea2686a |
| MBERT | 55.87 | Not recorded | 68fa6a2a1e209131cea2686a |
| MBERT | 54.56 | Not recorded | 68fa6a2a1e209131cea2686a |
| MBERT | 29.38 | Not recorded | 68fa6a2a1e209131cea2686a |

### ENCU

Pearson R (x100): 85.59. Result ID: 698e1c68ffc3901de09ade1a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

Recorded evaluation configuration: {"Rank":"#1"}. This record does not assert independent reproduction.

### MBERT

Pearson R (x100): 80.19. Result ID: 698e1c68ffc3901de09ade20.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Implementation](<https://github.com/galsang/SG-BERT>)

Recorded evaluation configuration: {"Backbone":"MBERT","Training objective":"Contrastive (SG-OPT)"}. This record does not assert independent reproduction.

### MBERT

Pearson R (x100): 78.93. Result ID: 698e1c68ffc3901de09ade1f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Implementation](<https://github.com/galsang/SG-BERT>)

Recorded evaluation configuration: {"Backbone":"MBERT","Training objective":"Contrastive (SG)"}. This record does not assert independent reproduction.

### Cosine baseline

Pearson R (x100): 71.17. Result ID: 698e1c68ffc3901de09ade19.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa638a1e209131ce9ff629.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MBERT

Pearson R (x100): 68.16. Result ID: 698e1c68ffc3901de09ade1e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Implementation](<https://github.com/galsang/SG-BERT>)

Recorded evaluation configuration: {"Backbone":"MBERT","Training objective":"Contrastive (BT)"}. This record does not assert independent reproduction.

### MBERT

Pearson R (x100): 55.87. Result ID: 698e1c68ffc3901de09ade1d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Implementation](<https://github.com/galsang/SG-BERT>)

Recorded evaluation configuration: {"Backbone":"MBERT","Pooling strategy":"WK pooling"}. This record does not assert independent reproduction.

### MBERT

Pearson R (x100): 54.56. Result ID: 698e1c68ffc3901de09ade1c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Implementation](<https://github.com/galsang/SG-BERT>)

Recorded evaluation configuration: {"Backbone":"MBERT","Pooling strategy":"Mean pooling"}. This record does not assert independent reproduction.

### MBERT

Pearson R (x100): 29.38. Result ID: 698e1c68ffc3901de09ade1b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea2686a.md>)

[Implementation](<https://github.com/galsang/SG-BERT>)

Recorded evaluation configuration: {"Backbone":"MBERT","Pooling strategy":"CLS"}. This record does not assert independent reproduction.

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