DataFunSummit
Jan 13, 2022 · Artificial Intelligence
DeltaLM: A Multilingual Pretrained Encoder‑Decoder Model for Neural Machine Translation
DeltaLM is a multilingual pretrained encoder‑decoder model that leverages cross‑lingual transfer from a pretrained encoder and novel decoder architecture, employs span‑corruption and translation‑pair pretraining tasks, and uses a two‑stage fine‑tuning strategy to achieve strong zero‑shot and supervised translation performance across over 100 languages.
DeltaLMZero-shotcross-lingual transfer
0 likes · 12 min read