FACEBOOK'S LATEST AI MODEL CAN CONVERT CODE FROM ONE LANGUAGE TO OTHER!
Ever thought how tedious it is to implement the same algorithm in various languages? You might be good at Python but your manager needs Java! Here comes Deep Learning to help to you again!
Facebook AI Research has announced TransCoder, a system that uses unsupervised deep-learning to convert code from one programming language to another. TransCoder was trained on more than 2.8 million open source projects and outperforms existing code translation systems that use rule-based methods.
This has been inspired by NMT(Neural Machine Translation ) based tasks that convert text from say English to French.
TransCoder builds on advances in natural-language processing (NLP), in particular unsupervised NMT. The model uses a Transformer-based sequence-to-sequence architecture which consists of an attention-based encoder and decoder.
In the TransCoder paper, the Facebook AI Research team notes that they intend to release the "code and pretrained models," but have not done so at this time.
We can hopefully expect the release sometime soon.