sfrontull/lld_valbadia-ita-loresmt-R4

Ladin-Val Badia to Italian Translation Model

Description

This model is designed for translating text between Ladin (Val Badia) and Italian. The model was developed and trained as part of the research presented in the paper titled "Rule-Based, Neural and LLM Back-Translation: Comparative Insights from a Variant of Ladin" submitted to LoResMT @ ACL 2024.

Paper

The details of the model, including its architecture, training process, and evaluation, are discussed in the paper:

• Rule-Based, Neural and LLM Back-Translation: Comparative Insights from a Variant of Ladin

License

This model is licensed under the CC BY-NC-SA 4.0 License.

Usage

To use this model for translation, you need to use the prefixes >>ita<< for translating to Italian and >>lld_Latn<< for translating to Ladin (Val Badia).

Citation

If you use this model, please cite the following paper:

@inproceedings{frontull-moser-2024-rule,
    title = "Rule-Based, Neural and {LLM} Back-Translation: Comparative Insights from a Variant of {L}adin",
    author = "Frontull, Samuel  and
      Moser, Georg",
    editor = "Ojha, Atul Kr.  and
      Liu, Chao-hong  and
      Vylomova, Ekaterina  and
      Pirinen, Flammie  and
      Abbott, Jade  and
      Washington, Jonathan  and
      Oco, Nathaniel  and
      Malykh, Valentin  and
      Logacheva, Varvara  and
      Zhao, Xiaobing",
    booktitle = "Proceedings of the The Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.loresmt-1.13",
    pages = "128--138",
    abstract = "This paper explores the impact of different back-translation approaches on machine translation for Ladin, specifically the Val Badia variant. Given the limited amount of parallel data available for this language (only 18k Ladin-Italian sentence pairs), we investigate the performance of a multilingual neural machine translation model fine-tuned for Ladin-Italian. In addition to the available authentic data, we synthesise further translations by using three different models: a fine-tuned neural model, a rule-based system developed specifically for this language pair, and a large language model. Our experiments show that all approaches achieve comparable translation quality in this low-resource scenario, yet round-trip translations highlight differences in model performance.",
}