NLP-Distributional-Semantics

Third Assignment in 'NLP - Natural Languages Processing' course by Prof. Yoav Goldberg, Prof. Ido Dagan and Prof. Reut Tsarfaty at Bar-Ilan University.

Goal:
The goal of this assignment is to compute distributional similarities for words based on corpus data and to assess and evaluate those similarities.

The assignment consists of the following parts:

• The first parts are about computing word similarity using vectors in the original feature space, which I built using corpus statistics.
• Then, in the last part, I computed similarities in an analogous manner using pre-trained word2vec word embeddings.

Score: 100