Interesting work, isn't the disambiguation of a move contextual to the state of the board though? It would be interesting to see what happens if you trained a masked model for processing the games and then compared the contextualized vectors, given the state of the board in order to determine move similarity.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store