NMT systems trained on Pre-trained Multilingual Sequence-Sequence (PMSS) models flounder when sufficient amounts of parallel data is not available for fine-tuning. This specifically holds for languages missing/under-represented in these models. The problem gets aggravated when the data comes from different domains. In this paper, we show that intermediate-task fine-tuning (ITFT) of PMSS models is extremely beneficial for domain-specific NMT, especially when target domain data is limited/unavailable and the considered languages are missing or under-represented in the PMSS model. We quantify the domain-specific results variations using a domain-divergence test, and show that ITFT can mitigate the impact of domain divergence to some extent.
@article{arxiv.2306.01382,
title = {Leveraging Auxiliary Domain Parallel Data in Intermediate Task Fine-tuning for Low-resource Translation},
author = {Shravan Nayak and Surangika Ranathunga and Sarubi Thillainathan and Rikki Hung and Anthony Rinaldi and Yining Wang and Jonah Mackey and Andrew Ho and En-Shiun Annie Lee},
journal= {arXiv preprint arXiv:2306.01382},
year = {2023}
}
Comments
Accepted for poster presentation at the Practical Machine Learning for Developing Countries (PML4DC) workshop, ICLR 2023