Demonstrating expertise in Python and Django, TubeDigest is a robust web application that leverages NLTK and YouTube API for AI-powered video summarization.
-
Updated
Aug 1, 2024 - Python
Demonstrating expertise in Python and Django, TubeDigest is a robust web application that leverages NLTK and YouTube API for AI-powered video summarization.
Search engine for the Lex Fridman Podcast 🎤
A utility library for comparing strings via Cosine Similarity
This project aims to simplify and summarize scientific data , convert it to a audio format as a podcast , and create a power point presentation from the paper. This helps researchers, academics and students altogether.
The "Questions" project, part of Harvard's CS50 AI course, develops an AI system for answering questions by retrieving documents and passages from a text corpus using tf-idf. It aids in understanding natural language processing (NLP) and information retrieval techniques.
Sentence embeddings for unsupervised event detection in the Twitter stream: study on English and French corpora
AI Book recommendation system
Search anything, instantly
This project aims to analyze the sentiment of reviews by implementing a review polarity classification system. I will compare the performance of three different feature representations, namely Bag of Words, TFIDF, and Word2Vector using KNN Algorithms
Text2Text: Crosslingual NLP/G toolkit
Search system for the Reuters 21578 Corpus.
Experiments with Sophoclean language in vector space
Sentiment Analysis on movie reviews using NLP
This project involves developing a machine learning model to predict user preferences in chatbot conversations, using a dataset of head-to-head responses from various large language models. The goal is to enhance chatbot-human interactions by aligning chatbot responses more closely with human preferences.
Baseline models for searching for movie plots from Wikipedia articles. Techniques include BM25 (lexical search), bi/cross-encoding (semantic search), and retrieval-augmented generation (RAG) using Mistal 7B through Fireworks.ai.
Explore text classification with Logistic Regression and Naive Bayes models. Implementing from scratch, we compare feature engineering techniques like Bag-of-Words, TF-IDF, and Word Embedding for accurate labeling
A university project with several different phases in which a search engine is designed to retrieve information and documents
The greynir.is Icelandic natural language processing API and website.
GROUP 4. This repository contains the implementation of a Transformer-based model for abstractive text summarization and a rule-based approach for extractive text summarization.
Add a description, image, and links to the tf-idf topic page so that developers can more easily learn about it.
To associate your repository with the tf-idf topic, visit your repo's landing page and select "manage topics."