Reordering target-side monolingual sentences into source word order and replacing words via a bilingual dictionary improves low-resource NMT for syntactically divergent language pairs.
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
-
Handling Syntactic Divergence in Low-resource Machine Translation
Reordering target-side monolingual sentences into source word order and replacing words via a bilingual dictionary improves low-resource NMT for syntactically divergent language pairs.