Get the latest tech news
ML-Enhanced Code Completion Improves Developer Productivity (2022)
Posted by Maxim Tabachnyk, Staff Software Engineer and Stoyan Nikolov, Senior Engineering Manager, Google Research Update — 2022/09/06: This post...
We treat code similar to language, represented with sub-word tokens and a SentencePiece vocabulary, and use encoder-decoder transformer models running on TPUs to make completion predictions. We use SEs to perform fast semantic correctness checks within a given latency budget (<100ms for end-to-end completion) and use cached abstract syntax trees to enable a “full” structural understanding. Special thanks to Marc Rasi, Yurun Shen, Vlad Pchelin, Charles Sutton, Varun Godbole, Jacob Austin, Danny Tarlow, Benjamin Lee, Satish Chandra, Ksenia Korovina, Stanislav Pyatykh, Cristopher Claeys, Petros Maniatis, Evgeny Gryaznov, Pavel Sychev, Chris Gorgolewski, Kristof Molnar, Alberto Elizondo, Ambar Murillo, Dominik Schulz, David Tattersall, Rishabh Singh, Manzil Zaheer, Ted Ying, Juanjo Carin, Alexander Froemmgen, Maxim Kachurovskiy, and Marcus Revaj for their contributions.
Or read this on Hacker News