chrf-8259704e·4 events·first seen Aliases: chrF, ChrF++, CHrF++
Researchers present a systematic study of healthcare-domain neural machine translation for four severely low-resource Arabic-script languages (Dari, Pashto, Sorani Kurdish, Urdu) using Arabic and Persian as higher-resource pivots. Three transfer strategies are evaluated: few-shot in-context learning, minimal supervised adaptation, and zero-data LoRA adapter merging — the last being novel in this setting. Supervised adaptation with just 500 sentences achieves near-pivot quality for Dari, while LoRA adapter merging reaches within 3.5 CHrF++ of supervised adaptation at zero additional data cost. Pashto and Sorani Kurdish remain below clinical deployment thresholds, exposing limits of cross-lingual transfer when structural distance is large.
Researchers introduce a pipeline that uses LLMs to extract grammatical rules, example sentences, and lexicons from descriptive grammar books, then generates synthetic parallel corpora for fine-tuning machine translation models. Validated on three typologically diverse low-resource languages (Kalamang, Tuatschin, Mandan), fine-tuning on synthetic data outperforms seed-data baselines in 59–75% of configurations, with best-case ChrF++ gains up to +8.8. A systematic factorial study across 96 configurations identifies which combinations of target part-of-speech, retrieval granularity, and sample volume drive improvements.
A new arXiv preprint introduces DeltaMerge-LowRes, a method for adapting multilingual encoders to new languages and tasks in low-resource settings by training language and task deltas separately and composing them in weight space at inference. The paper proposes four composition rules including a novel cross-axis TIES variant that adapts the TIES-Merging algorithm to language/task axes rather than task/task axes. Evaluated across four task families and four African languages (158 cells), cross-axis TIES improves summarization by +4 to +7 chrF and QA F1 by +2.32, while sparsity-aware merging reduces calibration error by 36%. The work advances model merging techniques for low-resource multilingual NLP.
Researchers propose an RL-based training approach for translating extremely low-resource or unseen languages by rewarding models for extracting and applying in-context linguistic knowledge (e.g., grammar books) rather than memorizing specific languages. Using chrF as a surface-level reward signal, RL-trained models outperform both in-context learning and supervised fine-tuning on completely unseen languages at test time. The work extends outcome-based RL beyond math and coding reasoning tasks, suggesting broader applicability to language learning from context.