An internet search engine written mostly in python. Currently TF-IDF based.

Search anything, instantly

NLP toolkit for those nonsensical ontologies

Towards evaluation of fairness in MDD models: Automatic analysis of symptom differences for gender groups in the D-vlog dataset

NLP use cases using popular solutions: Frequency Embeddings, Word embedding (word2vec, doc2vec, Glove), RNN,LSTM, Transformers-BERT, Sentence_Transformers etc. PyTorch

This repository contains the three projects completed as part of a data structures and algorithms course.

Language-Detection

Utilizing advanced NLP techniques, our project analyzes and summarizes Indian cricket players' Wikipedia content using transformer models and Word2Vec embeddings. Evaluate summaries with ROUGE scores. Enhance decision-making and knowledge extraction with efficient text analysis

Cereja is a bundle of useful functions we don't want to rewrite and .. just pure fun!

Unlock personalized content recommendations on Netflix with my cutting-edge ML project. Say goodbye to aimless scrolling and elevate your binge-watching experience with our user-centric content-based recommender system.

An Autogen-based Multi-LLM System capable of answering research related questions on ACL 2023 Articles to identify gaps and limitations

This script enhances data integration by fuzzy matching company names across datasets using text preprocessing and efficient search algorithms, ideal for reconciling customer and financial data.

Using a modified TF-IDF approach based on Flynn and Sastry's "Attention Cycles," this suite quantifies corporate focus on specific topics through attention scores, aiding economic and financial research.

Crafting personalized shopping experiences at Sephora with innovative data-driven recommendations tailored to individual preferences leveraging tools like CHEMBERT, TF-IDF, and BERT embeddings for precise product insights.

This project is a SMS spam classifier which detect whether the SMS is spam or ham using the multinomial Naive Bayes algorithm along the side of BOW/TF-IDF in NLP

Text Summarization using TF-IDF technique in Python.

BERT, LDA, and TFIDF based keyword extraction in Python

rank_bm25 for C++

Projet de fin de cycle de licence 2023 à l'USTHB portant sur l'analyse et la comparaison de méthodes statistiques non-supervisées pour l'extraction terminologique.

YASE is a search engine based on the MS Marco document collection, and composed by an indexer and a query processor