… We define cross-lingual continual learning as the problem of sequentially fine-tuning a …
task K over a cross-lingual datastream. In this case, a cross-lingual data stream is made of N …

… The longstanding goal of multi-lingual learning has been to develop a universal cross-lingual …
2022) formulate the lifelong learning pretraining challenge, where pertaining language …

… stream cross-lingual tasks … cross-lingual ability, which leads to sub-optimal performance.
To alleviate this problem, we leverage continual learning to preserve the original cross-lingual …

… of recent developments in cross-lingual transfer learning for multilingual natural language
… to multilingual neural machine translation, lifelong learning in cross-lingual settings, and the …

… the performance of cross-lingual transfer learning. XTREME consists of nine tasks derived
from four different categories and uses zero-shot cross-lingual transfer with the English …

Continual Language Learning (CLL) in multilingual translation is inevitable when new
languages are required to be translated. Due to the lack of unified and generalized benchmarks, …

… To demonstrate the advantage of the proposed crosslingual training methodology, we
compare our CSLDaily→Phoenix-2014T model with two baselines: • Phoenix-2014T only. We …

… They compared three approaches for cross-lingual adaptation: (1) retraining only an output
layer; (2) retraining all parameters; (3) randomly initializing weights of the last layer and then …

… or joint training. However, we show that it is competitive with multilingual BERT on standard
cross-lingual … In that regard, our work provides a baseline for multilingual lifelong learning. …

… aimed at building and deploying a cross-modal, cross-lingual, cross-cultural, cross-domain
and cross-site personalised learning platform for Open Educational Resources (OER). …