Skip to content

Latest commit

 

History

History
5 lines (3 loc) · 561 Bytes

2011.214.md

File metadata and controls

5 lines (3 loc) · 561 Bytes

Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT, Chronopoulou et al., 2020

Paper, Code, Tags: #nlp, #machine-translation

The reused monolingual LM is fine-tuned on both languages and then used to initialize a UNMT model. We propose a new vocabulary extension method, RE-LM, that outperforms a competitive cross-lingual pretraining model and also improves translations on a low-resource supervised setup.