News for hackers. Stuff that matters.
Re:A computational linguistic farce in three acts by vedant on Sunday June 11, 2017 @03:16PM (#14533298)
One reason is that the amount of training data is many many orders of magnitude smaller.

FWIW it seems the structure you're talking about exploiting is at a morphological and syntactic level, which modern language models tend to effectively handle. Semantics are a much harder problem.

There are no comments on this comment yet.