BNLP is a natural language processing toolkit for Bengali Language.

a robust AI library for detecting profanity in russian language (regex/SVM based), библиотека для детекции нецензурных слов в русском языке

Principles Of AI Lab Exercises

Transform AI-generated text into formal, human-like, and academic writing with ease, avoids AI detector!

Know-Genius an AI Chatbot who's a General Knowledge Genius!

Amazon Product Reviews: Sentiment Analysis with NLP

This project is a Python-based web scraper and data analyzer that extracts quotes, authors, and associated tags from the website Quotes to Scrape. It processes the data to create structured CSV files and includes functionalities for filtering and analyzing quotes by tags.

This repository implements a Next Word Prediction model using BiLSTM in PyTorch. It is trained on a dataset of Medium article titles and predicts the next word based on context. The project includes data preprocessing, model training, and Prediction.

The Duolingo for certifications instead of languages!

🤖 Automation Bot which can do textual extraction from a URL and perform text analysis and store into a file.

👨‍💻👨‍💻 Movie Recommendation system , this model is projecting five similar movies to user according to user input.

An innovative system for filtering and categorizing movie reviews

Machine learning model for classifying news articles based on their headlines.

Text Classification for Resumes: Conducted Exploratory Data Analysis (EDA) on a vast collection of resumes. Organized the data using Bag of Words (BoW) and TF-IDF techniques. Built and evaluated multiple models, with Logistic Regression delivering standout performance. Created Word Clouds and Histograms.

The objective of this assignment is to extract textual data articles from the given URL and perform text analysis to compute variables that are explained

The objective of this assignment is to extract textual data articles from the given URL and perform text analysis to compute variables.

Basic Building block of NLP application is Text Preprosessing.

This repository features two Jupyter Notebooks: one for text preprocessing and the other showcasing topic modeling using the OCTIS library with Latent Dirichlet Allocation (LDA) applied to the ChiLit Corpus. Dive into the README for detailed instructions, citations, and links to the datasets and libraries used in this project.