TY  - GEN
Y1  - 2018///
UR  - https://papers.nips.cc/paper/7409-generative-neural-machine-translation
N2  - We introduce Generative Neural Machine Translation (GNMT), a latent variable architecture which is designed to model the semantics of the source and target sentences. We modify an encoder-decoder translation model by adding a latent variable as a language agnostic representation which is encouraged to learn the meaning of the sentence. GNMT achieves competitive BLEU scores on pure translation tasks, and is superior when there are missing words in the source sentence. We augment the model to facilitate multilingual translation and semi-supervised learning without adding parameters. This framework significantly reduces overfitting when there is limited paired data available, and is effective for translating between pairs of languages not seen during training.
PB  - NIPS Proceedings
TI  - Generative Neural Machine Translation
N1  - This version is the version of record. For information on re-use, please refer to the publisher?s terms and conditions.
ID  - discovery10076152
AV  - public
A1  - Shah, H
A1  - Barber, D
CY  - Montreal, Canada
T3  - Advances in Neural Information Processing Systems
SN  - 1049-5258
EP  - 10
ER  -