News for hackers. Stuff that matters.
Re:Aroma: Using machine learning for code recommendation by patternmaster on Monday April 08, 2019 @05:11PM (#19609082)
Chain a text-to-speech component to tranx and you're done

Paper: https://arxiv.org/pdf/1810.02720v1.pdf

Code: https://github.com/pcyin/tranX

Live demo (try Django out): http://moto.clab.cs.cmu.edu:8081/

Re:Aroma: Using machine learning for code recommendation by sansnomme on Monday April 08, 2019 @05:30PM (#19609247)
This seems to be a lot better those those Seq-to-Seq natural language to SQL networks. Can you elaborate more about them?