Unsupervised translation of programming languages

Re:Unsupervised translation of programming languages by lostmsu on Tuesday June 09, 2020 @08:36PM (#23472617)

This is very impressive, but it can not handle large contexts.

E.g. in its current state it would not be able to translate large codebases, even more so using different libraries.

For example, the translator consistently fails to convert Python

  max(arr)

into proper Java. It generates

  Math.max(arr)

instead, which is a non-existent overload of the function.

Another problem is that unless you can port tests too, the code is not very reliable.

[ Parent | on HN ]

Re:Unsupervised translation of programming languages by peteretep on Tuesday June 09, 2020 @09:47PM (#23473000)

I wonder if there's value there for in-IDE snippets. I need to make some changes to some Java code, I know how I'd say it in Python, and this'll do the translation for me?

[ Parent | on HN ]

Re:Unsupervised translation of programming languages by lostmsu on Tuesday June 09, 2020 @11:12PM (#23473523)

Overall I don't think it is a convenient way to program. Besides, you still need to test it.

[ Parent | on HN ]

Re:Unsupervised translation of programming languages by c3534l on Tuesday June 09, 2020 @10:36PM (#23473319)

How do you know this? Do you have access to the program somewhere?

[ Parent | on HN ]

Re:Unsupervised translation of programming languages by lostmsu on Tuesday June 09, 2020 @11:10PM (#23473512)

The max example is listed in the very last paragraph of the paper as one of the failure modes.

[ Parent | on HN ]