In the real-world scenario, a longstanding goal of multilingual neural machine translation
(MNMT) is that a single model can incrementally adapt to new language pairs without …

Incrementally expanding the capability of an existing translation model to solve new domain
tasks over time is a fundamental and practical problem, which usually suffers from …

In the evolving landscape of Neural Machine Translation (NMT), the pretrain-then-finetune
paradigm has yielded impressive results. However, the persistent challenge of Catastrophic …

Although existing multilingual neural machine translation (MNMT) models have
demonstrated remarkable performance to handle multiple translation directions in a single …

A persistent goal of multilingual neural machine translation (MNMT) is to continually adapt
the model to support new language pairs or improve some current language pairs without …

This paper introduces and investigates the problem of Task and Language Incremental
Continual Learning (TLCL), wherein a multilingual model is systematically updated to …

As the applications of large language models (LLMs) expand across diverse fields, the
ability of these models to adapt to ongoing changes in data, tasks, and user preferences …

The recent emergence of various large language models, which can be fine-tuned with
minimal instruction data, has demonstrated impressive performance across various tasks …

In long-term translation projects, like Parliamentary text, there is a desire to build machine
translation systems that can adapt to changes over time. We implement and examine a …

Continual learning is widely used in practical applications of neural machine translation,
which aims to not only achieve good performance on new domains but also preserve the …