[tonmoy]

MS had been experimenting with this for a while[1]. They even included this in Excel 2013 as "FlashFill". It does not use any NN/ML at all. It uses "program synthesis", which by definition can tell you exactly what "program" it has synthesized to convert you data. In fact in you example it would not cheat, rather leave the string unchanged as explained in the paper.

[1] https://www.microsoft.com/en-us/research/publication/automat...

[randomsearch]

More generally, anything by Sumit Gulwani's group at MSR should be of interest.

[teddyh]

But maybe I did want it to remove the middle character! Using my training data, there’s no way for the system to actually know for sure what I meant. There is also no way (in general) for it to detect “outliers” and ask me about them, because there is no good way to know what is an outlier and what is not.

[vanderZwan]

You can modify the output of the program synthesis to fit your needs. See this CurryOn! talk from 2015 by Sumit Gulwani

https://www.youtube.com/watch?v=uqV9BlxEG5s

[TuringTest]

This is why this kind of software should have an interactive 'feedback' function that allows the user to select among several, equally likely rules.

The experimental Lapis editor[1] did exactly this, by the way.

[1] https://en.wikipedia.org/wiki/Lapis_(text_editor)