DIETA: A Decoder-only transformer-based model for Italian-English machine TrAnslation
This work addresses machine translation for Italian-English, providing a specialized model and dataset, but it is incremental as it applies an existing decoder-only Transformer approach to a specific language pair.
The authors tackled Italian-English machine translation by developing DIETA, a small decoder-only Transformer model with 0.5 billion parameters, which achieved competitive performance, ranking in the second quartile of a 32-system leaderboard and outperforming most other sub-3B models on four out of five test suites.
In this paper, we present DIETA, a small, decoder-only Transformer model with 0.5 billion parameters, specifically designed and trained for Italian-English machine translation. We collect and curate a large parallel corpus consisting of approximately 207 million Italian-English sentence pairs across diverse domains, including parliamentary proceedings, legal texts, web-crawled content, subtitles, news, literature and 352 million back-translated data using pretrained models. Additionally, we create and release a new small-scale evaluation set, consisting of 450 sentences, based on 2025 WikiNews articles, enabling assessment of translation quality on contemporary text. Comprehensive evaluations show that DIETA achieves competitive performance on multiple Italian-English benchmarks, consistently ranking in the second quartile of a 32-system leaderboard and outperforming most other sub-3B models on four out of five test suites. The training script, trained models, curated corpus, and newly introduced evaluation set are made publicly available, facilitating further research and development in specialized Italian-English machine translation. https://github.com/pkasela/DIETA-Machine-Translation