Viewing profile — franklsf

Sorry, HN screwed up my URL: https://arxiv.org/abs/1812.01158

Aroma would only surface what it thinks is "idiomatic" coding patterns. So if you have many instances of incorrect code, you might already be in trouble :)

Building models for natural language _and_ code for either NL/intent-based code search or automatically annotating code is indeed another hot research area! I'd argue Aroma solves …

There's a paper describing the approach in detail " rel="nofollow">https://arxiv.org/abs/1812.01158> , but Aroma itself is not open source yet.