WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects
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_ | 1866912235859738624 |
|---|---|
| author | Deutsch, Daniel Briakou, Eleftheria Caswell, Isaac Finkelstein, Mara Galor, Rebecca Juraska, Juraj Kovacs, Geza Lui, Alison Rei, Ricardo Riesa, Jason Rijhwani, Shruti Riley, Parker Salesky, Elizabeth Trabelsi, Firas Winkler, Stephanie Zhang, Biao Freitag, Markus |
| author_facet | Deutsch, Daniel Briakou, Eleftheria Caswell, Isaac Finkelstein, Mara Galor, Rebecca Juraska, Juraj Kovacs, Geza Lui, Alison Rei, Ricardo Riesa, Jason Rijhwani, Shruti Riley, Parker Salesky, Elizabeth Trabelsi, Firas Winkler, Stephanie Zhang, Biao Freitag, Markus |
| contents | As large language models (LLM) become more and more capable in languages other than English, it is important to collect benchmark datasets in order to evaluate their multilingual performance, including on tasks like machine translation (MT). In this work, we extend the WMT24 dataset to cover 55 languages by collecting new human-written references and post-edits for 46 new languages and dialects in addition to post-edits of the references in 8 out of 9 languages in the original WMT24 dataset. The dataset covers four domains: literary, news, social, and speech. We benchmark a variety of MT providers and LLMs on the collected dataset using automatic metrics and find that LLMs are the best-performing MT systems in all 55 languages. These results should be confirmed using a human-based evaluation, which we leave for future work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12404 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects Deutsch, Daniel Briakou, Eleftheria Caswell, Isaac Finkelstein, Mara Galor, Rebecca Juraska, Juraj Kovacs, Geza Lui, Alison Rei, Ricardo Riesa, Jason Rijhwani, Shruti Riley, Parker Salesky, Elizabeth Trabelsi, Firas Winkler, Stephanie Zhang, Biao Freitag, Markus Computation and Language As large language models (LLM) become more and more capable in languages other than English, it is important to collect benchmark datasets in order to evaluate their multilingual performance, including on tasks like machine translation (MT). In this work, we extend the WMT24 dataset to cover 55 languages by collecting new human-written references and post-edits for 46 new languages and dialects in addition to post-edits of the references in 8 out of 9 languages in the original WMT24 dataset. The dataset covers four domains: literary, news, social, and speech. We benchmark a variety of MT providers and LLMs on the collected dataset using automatic metrics and find that LLMs are the best-performing MT systems in all 55 languages. These results should be confirmed using a human-based evaluation, which we leave for future work. |
| title | WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.12404 |