Research
Rosetta at AlexandriaX-2026: LoRA-Adapted NileChat for Context-Aware Dialectal Arabic Dialogue Translation
arXiv:2609.10395v1 Announce Type: new Abstract: This paper describes the Rosetta system for Subtask 1 (Context-Aware English-to-Dialectal Arabic Dialogue Translation) of the AlexandriaX shared task, p
arXiv:2609.10395v1 Announce Type: new Abstract: This paper describes the Rosetta system for Subtask 1 (Context-Aware English-to-Dialectal Arabic Dialogue Translation) of the AlexandriaX shared task, participating in both constrained and unconstrained tracks. The approach fine-tunes a LoRA adapter on NileChat-3B using structured system/user prompts that condition generation on dialect and dialogue context. For the unconstrained track, the adapter is additionally pretrained on MADAR and PADIC. Rosetta ranked 4th in the constrained track (spBLEU 26.10) and 5th in the unconstrained track (spBLEU 25.09). The experimental results demonstrate that external pretraining helps only two of thirteen dialects while slightly hurting overall performance, suggesting negative transfer.
Related
- Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation
- How Much Rank Does LoRA Need? Rank-Error Bounds for Transformer Attention
- MetaHOPE: A Metaphor-Oriented Evaluation Framework for Analysing MT and LLM Translation Errors
Source: arXiv cs.CL | 2026-09-10