Towards Continual Learning for Multilingual Machine Translation via\n Vocabulary Substitution

2021/03/11 by Xavier García, Garcia, Xavier, Noah Constant +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2103.06799

openalex publication_date 2021/03/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a straightforward vocabulary adaptation scheme to extend the\nlanguage capacity of multilingual machine translation models, paving the way\ntowards efficient continual learning for multilingual machine translation. Our\napproach is suitable for large-scale datasets, applies to distant languages\nwith unseen scripts, incurs only minor degradation on the translation\nperformance for the original language pairs and provides competitive\nperformance even in the case where we only possess monolingual data for the new\nlanguages.\n

Related

• Efficiently Upgrading Multilingual Machine Translation Models to Support More Languages
• Continual Learning in Multilingual NMT via Language-Specific Embeddings
• Beyond English-Centric Multilingual Machine Translation
• Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?
• Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data