2021/03/26 by Toumi, Alexis, Koziell-Pipe, Alex
#Category Theory (math.CT) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Mathematics
paper · doi:10.48550/arxiv.2103.14411
We introduce functorial language models: a principled way to compute probability distributions over word sequences given a monoidal functor from grammar to meaning. This yields a method for training categorical compositional distributional (DisCoCat) models on raw text data. We provide a proof-of-concept implementation in DisCoPy, the Python toolbox for monoidal categories.