2018 · 98 citations · 16 references
ComputingComputer ScienceCorpus-based Translation StudiesNatural Language ProcessingTranslation TheoryMachine TranslationMultilingual Natural Language ProcessingParallel CorporaEncoder-decoder ArchitecturesMonolingual CorporaMultilingual Machine TranslationMultilingual Parallel CorporaNeural Machine TranslationParallel Text Corpora
A large-scale parallel corpus is required to train encoder-decoder neural machine translation. The method of using synthetic parallel texts, in which target monolingual corpora are automatically translated into source sentences, is effective in improving the decoder, but is unreliable for enhancing the encoder. In this paper, we propose a method that enhances the encoder and attention using target monolingual corpora by generating multiple source sentences via sampling. By using multiple source sentences, diversity close to that of humans is achieved. Our experimental results show that the translation quality is improved by increasing the number of synthetic source sentences for each given target sentence, and quality close to that using a manually created parallel corpus was achieved.
16
Kishore Papineni, Salim Roukos, Todd J. Ward et al. · 2001 · 21.5K citations · Full text
Sequence to Sequence Learning with Neural Networks
Ilya Sutskever, Oriol Vinyals, Quoc V. Le · arXiv (Cornell University) · 2014 · 13.4K citations · Full text
Computing, Computer Science, French +14
On Using Monolingual Corpora in Neural Machine Translation
Çağlar Gülçehre, Kelvin Xu, Kyunghyun Cho et al. · arXiv (Cornell University) · 2015 · 513 citations · Full text
Computing, Computer Science, Corpus-based Translation Studies +12