Contains Jupyter notebooks of tasks done in NLP class
Find links of notebooks along with their descriptions below:
-
13-12.ipynb - Doing basic stuff with the Brown and Inaugural corpora.
-
19-12.ipynb - Exploring different language versions of the Stopwords corpus, playing around with the Wordnet and CMUDict lexicons, and using the Tweet Tokenizer.
-
10-01.ipynb - Working with the Porter Stemmer, Snowball Stemmer, Lancaster Stemmer, RegExp Stemmer and WordNet Lemmatizer
-
NLP_26_02.ipynb - Using Porter Stemmer on random text, using the WordNet Lemmatizer, viewing the applications of CountVectorizer, TfidfVectorizer and Cosine Similarity and installing the Spacy library
-
NLP_26_02_and_28_02.ipynb - The same as NLP_26_02.ipynb, in addition to finding cosine similarities for collections of text (texts are collected from 3 National Geographic magazine articles)
-
CRF.ipynb - Sequence Labeling on a NER (Named Entity Recognition) model using CRF in Python