Feature Extraction
sentence-transformers
Safetensors
xlm-roberta
datadreamer
datadreamer-0.35.0
Synthetic
sentence-similarity
text-embeddings-inference
Instructions to use StyleDistance/mstyledistance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use StyleDistance/mstyledistance with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("StyleDistance/mstyledistance") sentences = [ "彼は技術的な複雑さと格闘し、彼の作品は驚くべき視覚的緊張を生み出した。", "Serviste mariscos frescos en el condado de Middlesex y áreas circundantes.", "Él sirvió mariscos frescos en el condado de Middlesex y áreas circundantes." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -33,6 +33,8 @@ widget:
|
|
| 33 |
|
| 34 |
# Model Card
|
| 35 |
|
|
|
|
|
|
|
| 36 |
mStyleDistance is a **multilingual style embedding model** that aims to embed texts with similar writing styles closely and different styles far apart, regardless of content and regardless of language. You may find this model useful for stylistic analysis of multilingual text, clustering, authorship identfication and verification tasks, and automatic style transfer evaluation. The model is described in the paper [StyleDistance/mstyledistance](https://hf.co/papers/2502.15168).
|
| 37 |
|
| 38 |
This model is an multilingual version of the English-only [StyleDistance](https://huggingface.co/StyleDistance/styledistance) model.
|
|
@@ -54,8 +56,20 @@ others = model.encode(["TOCARÁS LA GUITARRA CON TU AMIGO; SERÁ UNA EXCELENTE O
|
|
| 54 |
print(cos_sim(input, others))
|
| 55 |
```
|
| 56 |
|
| 57 |
-
|
| 58 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
---
|
| 61 |
## Trained with DataDreamer
|
|
|
|
| 33 |
|
| 34 |
# Model Card
|
| 35 |
|
| 36 |
+
This repository contains the model introduced in [mStyleDistance: Multilingual Style Embeddings and their Evaluation](https://hf.co/papers/2502.15168).
|
| 37 |
+
|
| 38 |
mStyleDistance is a **multilingual style embedding model** that aims to embed texts with similar writing styles closely and different styles far apart, regardless of content and regardless of language. You may find this model useful for stylistic analysis of multilingual text, clustering, authorship identfication and verification tasks, and automatic style transfer evaluation. The model is described in the paper [StyleDistance/mstyledistance](https://hf.co/papers/2502.15168).
|
| 39 |
|
| 40 |
This model is an multilingual version of the English-only [StyleDistance](https://huggingface.co/StyleDistance/styledistance) model.
|
|
|
|
| 56 |
print(cos_sim(input, others))
|
| 57 |
```
|
| 58 |
|
| 59 |
+
---
|
| 60 |
+
## Citation
|
| 61 |
+
|
| 62 |
+
```latex
|
| 63 |
+
@misc{qiu2025mstyledistancemultilingualstyleembeddings,
|
| 64 |
+
title={mStyleDistance: Multilingual Style Embeddings and their Evaluation},
|
| 65 |
+
author={Justin Qiu and Jiacheng Zhu and Ajay Patel and Marianna Apidianaki and Chris Callison-Burch},
|
| 66 |
+
year={2025},
|
| 67 |
+
eprint={2502.15168},
|
| 68 |
+
archivePrefix={arXiv},
|
| 69 |
+
primaryClass={cs.CL},
|
| 70 |
+
url={https://arxiv.org/abs/2502.15168},
|
| 71 |
+
}
|
| 72 |
+
```
|
| 73 |
|
| 74 |
---
|
| 75 |
## Trained with DataDreamer
|