---
title: Test Sbert Cosine
emoji: ⚡
colorFrom: purple
colorTo: purple
sdk: gradio
sdk_version: 3.19.1
app_file: app.py
pinned: false
tags:
- evaluate
- metric
description: >-
  Sbert cosine is a metric to score the semantic similarity of text generation tasks
  
  This is not the official implementation of cosine similarity using SBERT

  See the project at https://www.sbert.net/ for more information.
---

# Metric Card for SbertCosine

## Metric description

Sbert cosine is a metric to score the semantic similarity of text generation tasks

## How to use 

```python
from evaluate import load
sbert_cosine = load("transZ/sbert_cosine")
predictions = ["hello there", "general kenobi"]
references = ["hello there", "general kenobi"]
results = sbert_cosine.compute(predictions=predictions, references=references, lang="en")
```

## Output values

Sbert cosine outputs a dictionary with the following values:

`score`: Range from 0.0 to 1.0

## Limitations and bias

The [official repo](https://github.com/UKPLab/sentence-transformers) showed that Sbert can capture the semantic of the sentence well

## Citation

```bibtex
@article{Reimers2019,
archivePrefix = {arXiv},
arxivId = {1908.10084},
author = {Reimers, Nils and Gurevych, Iryna},
doi = {10.18653/v1/d19-1410},
eprint = {1908.10084},
isbn = {9781950737901},
journal = {EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference},
pages = {3982--3992},
title = {{Sentence-BERT: Sentence embeddings using siamese BERT-networks}},
year = {2019}
}
```
    
## Further References 
- [Official website](https://www.sbert.net/)