NLP is one of the components of Artificial intelligence which is the ability of a computer program to understand the human speech.
Now, let's dig deep to learn how we can make a fully fledged model to understand textual data.
In today's lecture we learned some of the core concepts invloved in Natural language processing such as :-
- Sentence Splitter
- Tokenization
- POS (part of speech tagging)
- Stop-word Removal
- Stemming
- Lemmatization
- Chunking
- Deep Parsing
- Word Cloud
- TF-IDF
Lets review some of the concepts taught in the class. At the end of the assignment you'll be able to:
- Implement the necessary preprocessing steps required while processing natural language.
- Show contextual understanding learned by machine.
For this exercise, we will use the Twenty Newsgroups Data Set,which comprises of 20000 messages taken from 20 newsgroups.