Autocompletion with Deep Learning

Re:Autocompletion with Deep Learning by jacob-jackson on Monday July 15, 2019 @03:40PM (#20444401)

As far as I can tell, it suggests one token at a time and uses its model to help rank these tokens. This is useful, but there is a lot to be gained by suggesting multiple tokens at once.

TabNine has always included a logistic regression model to help rank completions. It uses features such as the occurrence frequency of the token and the number of similar contexts in which it occurs.

[ Parent | on HN ]

Re:Autocompletion with Deep Learning by codesushi42 on Monday July 15, 2019 @03:51PM (#20444510)

Intellisense also outputs multiple suggestions.

Also, TabNine mentions they are using transformers, which is not logistic regression. The context will be inferred using attention.

[ Parent | on HN ]

Re:Autocompletion with Deep Learning by jacob-jackson on Monday July 15, 2019 @03:58PM (#20444574)

Sorry, I worded that poorly. What I mean is that each individual suggestion consists of a single token -- at least, that is what I see in https://visualstudio.microsoft.com/services/intellicode/. Compare the videos in https://tabnine.com/blog/deep, where most suggestions consist of multiple tokens.

Deep TabNine (announced today) uses transformers. TabNine (released last year) uses logistic regression.

[ Parent | on HN ]

Re:Autocompletion with Deep Learning by codesushi42 on Monday July 15, 2019 @10:04PM (#20446934)

Interesting, thanks.

[ Parent | on HN ]