Beyond english-centric multilingual machine translation
Existing work in translation demonstrated the potential of massively multilingual machine
translation by training a single model able to translate between any pair of languages …
translation by training a single model able to translate between any pair of languages …
Learning language specific sub-network for multilingual machine translation
Adaptive adapters: An efficient way to incorporate BERT into neural machine translation
Large-scale pre-trained language models (eg, BERT) have attracted great attention in recent
years. It is straightforward to fine-tune them on natural language understanding tasks such …
years. It is straightforward to fine-tune them on natural language understanding tasks such …
Parameter differentiation based multilingual neural machine translation
Multilingual neural machine translation (MNMT) aims to translate multiple languages with a
single model and has been proved successful thanks to effective knowledge transfer among …
single model and has been proved successful thanks to effective knowledge transfer among …
Robust optimization for multilingual translation with imbalanced data
Multilingual models are parameter-efficient and especially effective in improving low-
resource languages by leveraging crosslingual transfer. Despite recent advance in massive …
resource languages by leveraging crosslingual transfer. Despite recent advance in massive …