This repository contains a collection of Natural Language Processing (NLP) assignments.
| Assignment | Description |
|---|---|
| Assignment 1 | A Python program to read a paragraph, tokenize it into words, find the frequency of each word, and print each word along with its frequency. |
| Assignment 3 | Implements manual Part-of-Speech (POS) tagging from scratch without using external libraries like NLTK. |
| Assignment 4 | Focuses on Information Extraction from text. |
| Assignment 5 | Preprocesses a text file containing a Wikipedia article about Thiruvananthapuram. |
| Assignment 6 | This assignment appears to be about data analysis and visualization, likely using pandas and other libraries. It includes steps for importing libraries, loading data, and creating visualizations. |
| Assignment 7 | Implements a Word2Vec Skip-Gram model using a Bag of Words (BoW) representation. |
| Assignment 9 | This notebook implements a Part-of-Speech (POS) tagger using a Support Vector Machine (SVM) model. It uses the treebank corpus from NLTK for training and evaluation. |
| Assignment 10 | Implements an SVM-like Part-of-Speech (POS) tagger from scratch. It uses simple binary features and manually assigned weights to predict the POS tag for each word. |
| Assignment 11 | This notebook contains two sections. Section A implements a Naive-Bayes classifier to determine the sentiment (positive or negative) of test sentences. |