Natural Language Processing course assignments
The course assignmets included topics like n-grams, tf-idf, word2vec, doc2vec using word2vec combined with stemming and lemmatization and removing stop words if need to improve accuracy.
You need to download some python packages so you will be able to run this.
nltk
genism
sklearn
matplotlib
Assignmet PDF isn't listed, the assignment was to learn how to use n-grams (3-grams in this case) to train on an arabic econonmy courps and predict the 2 or 1 word based on the input. The courps was collected manualy from different websites.
Assignment 2 folder contains both assignment 2 and 3 codes. You can find the details and the datasets used in assignments PDFs listed. We used logistic regression as a proof of concept but you can insert your own algorithm. Running text classification will run all the three models and tf-idf model will run twice one with word summation and one with word average.