May 2019
Intermediate to advanced
272 pages
7h 19m
English
Within the field of Natural language understanding (NLU), Natural language generation is one of the most challenging tasks in machine learning. Broadly speaking, it is easier to estimate the parameters of a discriminative model than a generative model. On Quora (https://www.quora.com/Why-are-generative-models-harder-to-create-than-discriminative-models), Ian Goodfellow gives a good informal explanation that can be generalized to language:
The task of modeling language has been approached with rule-based ...
Read now
Unlock full access