Sequence-To-Sequence (Seq2Seq) learning was introduced in 2014, and has since been extensively studied and extended to a large variety of domains. Seq2Seq yields state-of-the-art performance on several applications such as machine translation, image captioning, speech generation, or summarization. In this tutorial, we will survey the basics of this framework, its applications, main algorithmic techniques and future research directions.

Code to get started and understand the basics is here.

This tutorial will be given at ICML 2017 (Sydney, Australia) in August 2017.

Here are the slides for the talk.