NATURAL LANGUAGE PROCESSING TASKS
SIDDHARTHA VARMA, 18BCE0865
- learnt basic string processing with python
- learnt about nltk
- learnt about COCA
- saw mentions of a celebrity
- analysed the chart of mentions of the celebrity
- learnt about corpora
- downloaded nltk
- explored brown corpus
- explored inaugural corpus
- downloaded a text from ANC
- analysed the text
- explored project gutenberg
- basic tokenisation
- what are stopwords
- difference between word and sentence tokenizaton
- tweet tokenization
- explored the differences between stemming and lemmatization
- porter stemmer
- lancaster stemmer
- regexp stemmer
- wnowball stemmer
- wordnet lemmatizer
- tokenization
- pos tagging
- punkt
- parse tree
- gender features
- classification
- naive bayes classification
- NLP with tensorflow