Understanding Back-Translation at Scale

Sergey EdunovMyle OttMichael AuliDavid Grangier

   Papers with code   Abstract  PDF

An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. This work broadens the understanding of back-translation and investigates a number of methods to generate synthetic source sentences... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
1
Transformer Big + BT
33.89
35.00
RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
1
Transformer Big + BT
37.82
--