← Search

Jiuyi Li

2 accepted papers

2023

Continual Learning for Multilingual Neural Machine Translation via Dual Importance-based Model Division

EMNLP 2023long main

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 accessing the previous training data. To achieve this, the existing methods primarily focus on preventing catastrophic fo…

Cited by 0SourceScholar
2022

Adaptive Token-level Cross-lingual Feature Mixing for Multilingual Neural Machine Translation

EMNLP 2022main

Multilingual neural machine translation aims to translate multiple language pairs in a single model and has shown great success thanks to the knowledge transfer across languages with the shared parameters. Despite promising, this share-all paradigm suffers from insufficient ability to capture langua…