This repository documents my self-learning journey in Natural Language Processing (NLP) using Python.
The materials and implementations in this repository are primarily based on the book:
The goal is to understand NLP concepts through practical methods, hands-on coding, and experimentation.
NLP Basic
- Dividing text into sentences
- Dividing sentences into words (Tokenization)
- Part-of-Speech (POS) tagging
- Word stemming
- Lemmatization (combining similar words)
- Stopword removal
Playing with Grammar
- Counting nouns (singular and plural)
- Dependency parsing
- Splitting sentences into clauses
- Extracting noun chunks
- Extracting entities and relations
- Extracting subjects and objects
- Anaphora resolution (reference finding)
NLTK documentation: https://www.nltk.org/index.html
spaCy documentation: https://spacy.io/usage/processing-pipelines
