Leveraging Auxiliary Domain Parallel Data in Intermediate Task Fine-tuning for Low-resource Translation
This addresses domain adaptation challenges in low-resource NMT for under-represented languages, but it is incremental as it builds on existing ITFT methods.
The paper tackles the problem of low-resource domain-specific neural machine translation (NMT) by showing that intermediate-task fine-tuning (ITFT) of pre-trained multilingual sequence-to-sequence models is highly beneficial when target domain data is limited or unavailable, especially for under-represented languages, and it can mitigate domain divergence effects.
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.