Investigating the Effect of Parallel Data in the Cross-Lingual Transfer for Vision-Language Encoders
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915447162535936 |
|---|---|
| author | Manea, Andrei-Alexandru Libovický, Jindřich |
| author_facet | Manea, Andrei-Alexandru Libovický, Jindřich |
| contents | Most pre-trained Vision-Language (VL) models and training data for the downstream tasks are only available in English. Therefore, multilingual VL tasks are solved using cross-lingual transfer: fine-tune a multilingual pre-trained model or transfer the text encoder using parallel data. We study the alternative approach: transferring an already trained encoder using parallel data. We investigate the effect of parallel data: domain and the number of languages, which were out of focus in previous work. Our results show that even machine-translated task data are the best on average, caption-like authentic parallel data outperformed it in some languages. Further, we show that most languages benefit from multilingual training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_21681 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Investigating the Effect of Parallel Data in the Cross-Lingual Transfer for Vision-Language Encoders Manea, Andrei-Alexandru Libovický, Jindřich Computation and Language Most pre-trained Vision-Language (VL) models and training data for the downstream tasks are only available in English. Therefore, multilingual VL tasks are solved using cross-lingual transfer: fine-tune a multilingual pre-trained model or transfer the text encoder using parallel data. We study the alternative approach: transferring an already trained encoder using parallel data. We investigate the effect of parallel data: domain and the number of languages, which were out of focus in previous work. Our results show that even machine-translated task data are the best on average, caption-like authentic parallel data outperformed it in some languages. Further, we show that most languages benefit from multilingual training. |
| title | Investigating the Effect of Parallel Data in the Cross-Lingual Transfer for Vision-Language Encoders |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.21681 |