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 a different problem in that it surfaces…
There's a paper describing the approach in detail <https://arxiv.org/abs/1812.01158>, but Aroma itself is not open source yet.
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 a different problem in that it surfaces…
There's a paper describing the approach in detail <https://arxiv.org/abs/1812.01158>, but Aroma itself is not open source yet.