Timezone: »

 
Poster
Generative Neural Machine Translation
Harshil Shah · David Barber

Wed Dec 05 02:00 PM -- 04:00 PM (PST) @ Room 210 #17
in Wed Poster Session B »

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.

Keywords: Variational Inference · Semi-Supervised Learning · Representation Learning · Natural Language Processing · Latent Variable Models
[ Paper] 

Author Information

Harshil Shah (UCL)
David Barber (University College London)

More from the Same Authors