Aroma: Using machine learning for code recommendation
ai.facebook.com
Aroma: Using machine learning for code recommendation
1–10 of 62 posts
Re: Aroma: Using machine learning for code recommendation
#2The primary use case I experience for searching for idiomatic usage patterns is to know how to do a higher level refactoring, meaning I don’t want results that have syntax tree similarity to what I’ve got or even the small bit I start from to create the query. I want the intention of my search query but expressed in a better design.
Separately, for very micro-level idiomatic things, like use of a certain data type operation or efficient constructor patterns, I need to search by natural language descriptions of the subtle differences between options. This is what makes Stack Overflow so helpful, the accompanying natural language description of intentionality or special cases, even if the code that is found isn’t precisely what’s needed, it demonstrates directionally what to do.
This tool seems like yet another example of trying to force machine learning solutions to problems nobody actually has.
Considering the idea that I’d need to integrate this into my coding environment, I’ll say No Thanks!
Re: Aroma: Using machine learning for code recommendation
#3It would be very helpful to help figure out how to do things in a large codebase with little documentation.
Re: Aroma: Using machine learning for code recommendation
#4The most interesting (and I think difficult) approach here is properly representing the ASTs as vectors. There is a lot more possible when you get this right.
Re: Aroma: Using machine learning for code recommendation
#5The primary use case I experience for searching for idiomatic usage patterns is to know how to do a higher level refactoring, meaning I don’t want results that have syntax tree similarity to what I’ve got or even the small bit I start from to create the query. I want the intention of my search query but expressed in a better design. Separately, for very micro-level idiomatic things, like use of a certain data type op…
> This is what makes Stack Overflow so helpful, the accompanying natural language description of intentionality or special cases, even if the code that is found isn’t precisely what’s needed, it demonstrates directionally what to do.
You're entirely right, but if you're in an incredibly huge monorepo like Facebook, this information literally doesn't exist; that's part of the problem that Aroma is trying to solve - "how can we show people the Facebook App Way To Do That Thing, even if That Thing doesn't have current documentation"
(Disclaimer: I worked on the coding environment UX for Aroma)
Re: Aroma: Using machine learning for code recommendation
#6The primary use case I experience for searching for idiomatic usage patterns is to know how to do a higher level refactoring, meaning I don’t want results that have syntax tree similarity to what I’ve got or even the small bit I start from to create the query. I want the intention of my search query but expressed in a better design. Separately, for very micro-level idiomatic things, like use of a certain data type op…
> This is what makes Stack Overflow so helpful, the accompanying natural language description of intentionality or special cases, even if the code that is found isn’t precisely what’s needed, it demonstrates directionally what to do. You're entirely right, but if you're in an incredibly huge monorepo like Facebook, this information literally doesn't exist; that's part of the problem that Aroma is trying to solve - "h…
Wouldn’t it make more sense to spend the effort annotating these things? Or building models to provide the annotation? I mean, I work professionally in embedding models for computer vision and NLP, and my reaction to the article is that this seems like totally the wrong approach. You’re putting all this effort to create the embedding model out of the part that is both most superficial and least human interpretable (the AST).
Re: Aroma: Using machine learning for code recommendation
#7If people are interested in this area and not already aware, there has been an Eclipse project that operates in this general area for a while. https://www.eclipse.org/recommenders/
Re: Aroma: Using machine learning for code recommendation
#8That's a pretty cool approach! Thanks for sharing! ;-)
Re: Aroma: Using machine learning for code recommendation
#9Seealso: IntelliCode for Visual Studio.
Re: Aroma: Using machine learning for code recommendation
#10Was anyone able to find a link to Aroma in that document? I found the colours made it very difficult to differentiate the links from the text and I couldn't find it.
A quick search through Facebook's profile on Github turned up nothing.