Rosetta system improves English to dialectal Arabic dialogue translation
Rosetta at AlexandriaX-2026: LoRA-Adapted NileChat for Context-Aware Dialectal Arabic Dialogue Translation
Computation and Language
Summary
Translating English conversations into Arabic dialects is tricky because each dialect can be very different. The authors created Rosetta, a system that fine-tunes a small, adaptable model called LoRA on an existing chat model to handle these dialects better by using context from the conversation. They also experimented with additional training on other dialect datasets. Their system performed well, placing near the top in a competition, but found that extra training sometimes hurt overall accuracy, showing the challenge of mixing dialects.
What this means in practice
- •For language technology developers: Build better tools for translating English dialogue into various Arabic dialects by adapting models with dialect and conversational context.
- •For multilingual chatbot designers: Improve chatbot responses in Arabic dialects by integrating context-aware dialect translation models for richer user interactions.
Authors
Nada Esmaeil, Fathima Rena, Sibi Subhash, Osama Elgendy, Mina Naguib, Salma Omar, Muhammad Arif
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.