The University of Melbourne WMT 2026 CreoleMT Submission: A Domain-Balanced Approach to Low-Resource Pacific Creole Machine Translation

2026-09-11

AI Summary

本文针对太平洋克里奥尔语的低资源机器翻译问题，采用领域平衡方法，通过预训练、微调及多种数据处理技术提升模型性能。

Abstract

For our submission to the WMT26 Creole Language Translation Shared Task, we focus on machine translation (MT) models for Pacific creoles: Tok Pisin, Bislama, and Solomon Pijin, with particular attention to broad domain performance. After pre-training on a large collection of domain-imbalanced data, we continue fine-tuning on a diverse mix of domain-balanced data. We rely on a number of data collection and preparation techniques, including LLM-assisted respelling and alignment, back-translation, and distillation from Gemini for domains originally not present in training data. Evaluated on Bouquet and a novel test set made of spoken language transcripts, our models beat open model baselines by 3+ chrF++ points in all directions with human-original references. Looking ahead, we plan to develop human-translated test sets for Solomon Pijin and Bislama, and to distil our best models into much smaller ones that retain broad domain coverage.

Problem

• Pacific Creole
• Machine Translation
• Domain Performance
• Low-Resource

Innovation

• domain-balanced approach
• LLM-assisted respelling and alignment
• back-translation
• distillation from Gemini