Recent advances in self-supervised learning have dramatically improved the state of the art on a wide variety of tasks.
In this paper, we propose to explicitly model this one-to-many mapping by conditioning the decoder of a NMT model on a latent variable that represents the domain of target sentences.
We train our model on source code from open source GitHub projects, and show that it can translate functions between C++, Java, and Python with high accuracy.
The use of deep pre-trained transformers has led to remarkable progress in a number of applications (Devlin et al., 2018).
Pre-training text representations have led to significant improvements in many areas of natural language processing.
The use of deep pre-trained bidirectional transformers has led to remarkable progress in a number of applications (Devlin et al., 2018).
Ranked #2 on Conversational Response Selection on DSTC7 Ubuntu