Fine-tuning a neural translation model on a small subset of sentences selected by test-set similarity can outperform fine-tuning on the full in-domain corpus.
Adapting neural ma- chine translation with parallel synthetic data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Transductive Data-Selection Algorithms for Fine-Tuning Neural Machine Translation
Fine-tuning a neural translation model on a small subset of sentences selected by test-set similarity can outperform fine-tuning on the full in-domain corpus.