Language embeddings learned from a universal NMT model, when used to cluster languages into separate multilingual models, improve BLEU for most of 23 languages compared with language-family or random clustering.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multilingual Neural Machine Translation with Language Clustering
Language embeddings learned from a universal NMT model, when used to cluster languages into separate multilingual models, improve BLEU for most of 23 languages compared with language-family or random clustering.