---
tags: 298 NLP
---

# Introduction to Statistical NLP

## Why?

Here are some links of what statistical NLP can do today.

- [OpenAI Codex Live Demo](https://www.youtube.com/watch?v=SGUCcjHTmGY#t=13m8s)

## What is a Language Model?

https://en.wikipedia.org/wiki/Language_model

## References

The book [Supervised Machine Learning for Text Analysis in R](https://smltar.com/) has a lot of good material about topics we will not discuss, such as the importance of tokenizing, stop words, stemming, bias in data. You can also find a good account of word embeddings.

If you want to see the math background of the language model of $n$-grams, have a look at Chapter 3.1 of [Speech and Language Processing](https://web.stanford.edu/~jurafsky/slp3/) by Jurafsky and Martin.

This [podcast with Ilya Sutskever](https://www.youtube.com/watch?v=13CZPWmke6A) for the deep learning side of things.