mStyleDistance: Multilingual Style Embeddings and their Evaluation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913701554028544 |
|---|---|
| author | Qiu, Justin Zhu, Jiacheng Patel, Ajay Apidianaki, Marianna Callison-Burch, Chris |
| author_facet | Qiu, Justin Zhu, Jiacheng Patel, Ajay Apidianaki, Marianna Callison-Burch, Chris |
| contents | Style embeddings are useful for stylistic analysis and style transfer; however, only English style embeddings have been made available. We introduce Multilingual StyleDistance (mStyleDistance), a multilingual style embedding model trained using synthetic data and contrastive learning. We train the model on data from nine languages and create a multilingual STEL-or-Content benchmark (Wegmann et al., 2022) that serves to assess the embeddings' quality. We also employ our embeddings in an authorship verification task involving different languages. Our results show that mStyleDistance embeddings outperform existing models on these multilingual style benchmarks and generalize well to unseen features and languages. We make our model publicly available at https://huggingface.co/StyleDistance/mstyledistance . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15168 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | mStyleDistance: Multilingual Style Embeddings and their Evaluation Qiu, Justin Zhu, Jiacheng Patel, Ajay Apidianaki, Marianna Callison-Burch, Chris Computation and Language Style embeddings are useful for stylistic analysis and style transfer; however, only English style embeddings have been made available. We introduce Multilingual StyleDistance (mStyleDistance), a multilingual style embedding model trained using synthetic data and contrastive learning. We train the model on data from nine languages and create a multilingual STEL-or-Content benchmark (Wegmann et al., 2022) that serves to assess the embeddings' quality. We also employ our embeddings in an authorship verification task involving different languages. Our results show that mStyleDistance embeddings outperform existing models on these multilingual style benchmarks and generalize well to unseen features and languages. We make our model publicly available at https://huggingface.co/StyleDistance/mstyledistance . |
| title | mStyleDistance: Multilingual Style Embeddings and their Evaluation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.15168 |