Statistical Language Models

From simple to ++, with use cases, examples & code snippets

Arun Jagota
Towards Data Science
22 min readNov 3, 2020

--

Photo by Kelly Sikkema on Unsplash

In NLP, a language model is a probability distribution over strings on an alphabet. In formal language theory, a language is a set of strings on an alphabet. The NLP version is a soft variant of the one in formal language theory.

--

--

PhD, Computer Science, neural nets. 14+ years in industry: data science algos developer. 24+ patents issued. 50 academic pubs. Blogs on ML/data science topics.