Tutorial - A Convolutional Encoder Model for Neural Machine Translation

Abstract

In this tutorial we will demonstrate how to implement a state of the art convolutional encoder sequential decoder (conv2seq) architecture (Published recently at ACL’17. A Convolutional Encoder Model for Neural Machine Translation) for sequence to sequence modeling using Pytorch. While the aim of the tutorial is to make the audience comfortable with pytorch using this tutorial (with a Conv2Seq implementation as an add on), some familiarity with pytorch (or any other deep learning framework) would definitely be a plus.