Paper review: code2seq - generating sequences from structured representations of code

ML on Code is the field of research that attempts to capture statistical properties/patterns in source code using ML models,and apply those patterns for software engineering tasks/tools. Very much like NLP with text embedding, the question of obtaining useful vector representation of programs is at the heart of ML on Code research.


This is a companion discussion topic for the original entry at https://blog.sourced.tech/post/paper-review-code2seq/