wecet/Building-a-NLP-Language-Model
The project generates a sentence given a pre-defined starting phrase from the user such as "Ilbierah kont" and the script attempts to build a sentence off of that phrase. Structurally, the generator works in an n-gram fashion but the main structures used to generate the sentences were the unigram, bigram and trigram. The perplexity for each n-gram model was also calculated
Jupyter Notebook
No issues in this repository yet.