Simple Language Models

N-Gram Language Model

A fairly naive C++ implementation of the N-Gram language model.

To learn more about N-Gram language models generally, see: https://web.stanford.edu/~jurafsky/slp3/3.pdf

Vectorized Word Embeddings

A simplified version of Word2Vec to produce word embeddings with linear relationships.

The implementation is similar to the "bag of words" model presented here:

https://arxiv.org/abs/1301.3781

https://www.youtube.com/watch?v=rmVRLeJRkl4&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4