{"slug": "bm25-augmented-many-shot-translation-for-low-resource-north-eastern-indian", "title": "BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages", "summary": "The University of Florida Gators submitted a BM25-augmented many-shot translation system to the WMT26 Low-Resource Indic Language Translation shared task, translating between English and eleven North-Eastern Indian languages in both directions. The system retrieves similar parallel examples from language-specific training banks and uses Gemini 2.5 Flash to translate without fine-tuning, with a grid search over retrieval and exemplar counts selecting the best configuration for each of the 22 language-direction pairs.", "body_md": "arXiv:2608.13722v1 Announce Type: new\nAbstract: This paper describes the University of Florida Gators submission to the WMT26 Low-Resource Indic Language Translation shared task. We adapt the retrieval-augmented many-shot translation pipeline from our AmericasNLP 2026 system to translate between English and eleven North-Eastern Indian languages in both directions. At inference time, BM25 retrieves the most similar parallel examples from a language-specific training bank, and Gemini 2.5 Flash translates the input conditioned on these examples. No model fine-tuning is involved. Training banks combine official WMT26 data with publicly available corpora such as Samanantar and prior WMT shared task releases. A grid search over retrieval count r and development exemplar count d across all 22 language-direction pairs selects the best configuration for each submission.", "url": "https://wpnews.pro/news/bm25-augmented-many-shot-translation-for-low-resource-north-eastern-indian", "canonical_source": "https://arxiv.org/abs/2608.13722", "published_at": "2026-08-17 04:00:00+00:00", "updated_at": "2026-08-17 04:14:13.257469+00:00", "lang": "en", "topics": ["natural-language-processing", "machine-learning", "artificial-intelligence"], "entities": ["University of Florida Gators", "WMT26", "Gemini 2.5 Flash", "Samanantar"], "alternates": {"html": "https://wpnews.pro/news/bm25-augmented-many-shot-translation-for-low-resource-north-eastern-indian", "markdown": "https://wpnews.pro/news/bm25-augmented-many-shot-translation-for-low-resource-north-eastern-indian.md", "text": "https://wpnews.pro/news/bm25-augmented-many-shot-translation-for-low-resource-north-eastern-indian.txt", "jsonld": "https://wpnews.pro/news/bm25-augmented-many-shot-translation-for-low-resource-north-eastern-indian.jsonld"}}