N

NLP(Natural Language Process)

🤖 A starting point for developing your own Chrome extension using chatgpt.js (including pop-up menu + settings management)

CVerify is a production-ready AI recruitment platform that analyses CVs through a 3-phase ML pipeline, recommends matching jobs from 20 000+ real job postings, and provides a full recruiter/candidate/admin web interface with an integrated AI chatbot.

A modular Clinical NLP Pipeline built to process and analyze unstructured medical text using both traditional machine learning and transformer-based approaches.

The project combines multiple components including OCR, text preprocessing, feature engineering, classification, named entity recognition, and visualization into a single end-to-end pipeline. It supports extracting clinical insights from raw documents and predicting medical categories using both TF-IDF + SVM and BERT-based models.

The system was designed and implemented as a structured Python project, with each stage separated into independent modules for scalability and maintainability.

Key Highlights

Built an end-to-end NLP pipeline for clinical text processing. Implemented SVM (≈51% accuracy) and BERT (≈77% accuracy) models. Integrated OCR for extracting text from medical documents. Performed Named Entity Recognition (NER) on clinical data. Designed modular architecture (src/) for clean code organization. Exported outputs for visualization and dashboard integration.

This project focuses on binary sentiment classification of movie reviews from the IMDb Reviews dataset, using three distinct models: a multilayer perceptron, a Word2Vec-based model and a recurrent neural network (RNN). Each model is designed to classify reviews as positive or negative, leveraging advanced techniques in natural language processing. The word embeddings generated by each model are visualized using dimensionality reduction techniques (PCA, t-SNE), providing an intuitive representation of the semantic space.

Models are assessed using confusion matrices to analyze classification accuracy and ROC curves to evaluate the trade-off between true positive and false positive rates. The project compares the performance of MLP, Word2Vec, and RNN in capturing sentiment from text data.

A unified Python interface to select and use multiple Large Language Model (LLM) providers through a common API.

Plain text boilerplate removal using character n-gram frequency across a corpus. Builds a template model from a sample, filters files in a single linear pass, and validates automatically. Includes an obfuscated mode where the model is a set of integers and output filenames are hashed: the operator never reads the content. AWK for character processing, Bash for orchestration, Lisp layer planned for positional classification.

Project written in Python 3 that can be used to extract, analyze and prepare data from sources to bring information and finally knowledge into a visual and reusable format like word cloud.

My Health Lab is a personal, browser-based reflection tool designed to help users notice patterns in their own language over time.

this is the backend of wordly project

可以训练和使用根据语种的姓名分类和生成模型

The NLP powerhouse of the Oremi personal assistant, revolutionizing interaction through advanced natural language understanding.

https://demsking.gitlab.io/oremi-injini/

O projeto consiste em dois scripts que servem como base para complementar o fluxo da aplicação como um todo. Ambos os scripts são utilizados para facilitar e acelerar o processo de criação de quizzes e a ordenação das próximas palavras na revisão de um flashcard. São utilizadas bibliotecas como gensim e keras para a implementação dos scripts

Terminal embedding client for Hugging Face's hosted embedding models written in Go

Terminal Chat Completion client for OpenAI's LLMs written in Go

Terminal Chat Completion client for Mistral's AI models written in Go

Generate ALT text (captions for low vision website users or book readers).