Viet-Anh on Software Logo

What is: Neural Probabilistic Language Model?

Year2003
Data SourceCC BY-SA - https://paperswithcode.com

A Neural Probablistic Language Model is an early language modelling architecture. It involves a feedforward architecture that takes in input vector representations (i.e. word embeddings) of the previous nn words, which are looked up in a table CC.

The word embeddings are concatenated and fed into a hidden layer which then feeds into a softmax layer to estimate the probability of the word given the context.