A single encoder-decoder trained with both decoding directions beats a unidirectional Transformer by 0.8 to 1.3 BLEU and saves about half the parameters of a two-model ensemble.
Towards Neural Phrase-based Machine Translation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this paper, we present Neural Phrase-based Machine Translation (NPMT). Our method explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a recently proposed segmentation-based sequence modeling method. To mitigate the monotonic alignment requirement of SWAN, we introduce a new layer to perform (soft) local reordering of input sequences. Different from existing neural machine translation (NMT) approaches, NPMT does not use attention-based decoding mechanisms. Instead, it directly outputs phrases in a sequential order and can decode in linear time. Our experiments show that NPMT achieves superior performances on IWSLT 2014 German-English/English-German and IWSLT 2015 English-Vietnamese machine translation tasks compared with strong NMT baselines. We also observe that our method produces meaningful phrases in output languages.
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Bidirectional Neural Machine Translation
A single encoder-decoder trained with both decoding directions beats a unidirectional Transformer by 0.8 to 1.3 BLEU and saves about half the parameters of a two-model ensemble.