Bringing Ladin to FLORES+

Recent advances in neural machine translation (NMT) have opened new possibilities for developing translation systems also for smaller, so-called low-resource, languages. The rise of large language models (LLMs) has further revolutionized machine translation by enabling more flexible and context-aware generation. However, many challenges remain for low-resource languages, and the availability of high-quality, validated test data is essential to support meaningful development, evaluation, and comparison of translation systems. In this work, we present an extension of the FLORES+ dataset for two Ladin variants, Val Badia and Gherdëina, as a submission to the Open Language Data Initiative Shared Task 2025. To complement existing resources, we additionally release two parallel datasets for Gherdëina–Val Badia and Gherdëina–Italian. We validate these datasets by evaluating state-of-the-art LLMs and NMT systems on this test data, both with and without leveraging the newly released parallel data for fine-tuning and prompting. The results highlight the considerable potential for improving translation quality in Ladin, while also underscoring the need for further research and resource development, for which this contribution provides a basis.

• Publication year

  2025

• Venue

  Proceedings of the Tenth Conference on Machine Translation

• Publication date

  Unknown publication date

• Fields of study

  Not labeled

• Identifiers
  DOI 10.18653/v1/2025.wmt-1.81
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning

  2025cited by this paper
• Nesciun Lengaz Lascià Endò: Machine Translation for Fassa Ladin

  2024cited by this paper
• SCOI: Syntax-augmented Coverage-based In-context Example Selection for Machine Translation

  2024cited by this paper
• In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation

  2024cited by this paper
• Rule-Based, Neural and LLM Back-Translation: Comparative Insights from a Variant of Ladin

  2024cited by this paper
• BM25S: Orders of magnitude faster lexical search via eager sparse scoring

  2024cited by this paper
• Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Language

  2024cited by this paper
• Traduzione automatica “neurale” per il ladino della Val Badia

  2024cited by this paper
• Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM

  2023cited by this paper
• How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation

  2023cited by this paper
• How to Design Translation Prompts for ChatGPT: An Empirical Study

  2023cited by this paper
• CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation

  2023cited by this paper
• In-context Examples Selection for Machine Translation

  2022cited by this paper
• Language Models are Few-Shot Learners

  2020cited by this paper
• Massively Multilingual Neural Machine Translation

  2019cited by this paper
• Trivial Transfer Learning for Low-Resource Neural Machine Translation

  2018cited by this paper
• A Call for Clarity in Reporting BLEU Scores

  2018influential reference
• Transfer Learning for Low-Resource Neural Machine Translation

  2016cited by this paper
• La pianificazione linguistica: lingue, società e istituzioni

  2004cited by this paper
• Language

  1999influential reference
• Okapi at TREC-3

  1994cited by this paper

• Findings of the WMT 2025 Shared Task of the Open Language Data Initiative

  2025cites this paper