This repository is made of two sections gathering the skills I acquired in Natural Language Processing (NLP) at the MVA master (2020).
The first one focuses more on embedding techniques (BagOfWords, BagOfVectors, etc...) whereas the second one contains the implementation of a probabilistic parser for French based on the CYK algorithm and the PCFG model. Taking into account OOV (Out-Of-Vocabulary) words, this basic parser is also robust to unknown words.