natual-language-processing

Create an AI companion for Minecraft that reduces loneliness through intelligent, interactive gameplay.

A minecraft mod which aims to add a "second player" into the game which will actually be intelligent.

Retrieve sets of tools for LLM agents using query-conditioned hyperedge prediction.

Sentiment Analysis of Solar Energy Using Bidirectional Encoder Representations from Transformers

Content-based Tech Stack Recommendation Engine using TF-IDF and Cosine Similarity to rank personalized technology stacks from user preferences, with Top-N filtering and cold-start handling.

Study Guide for AI-900 Microsoft certification. Check the official Microsoft documentation for official materials.

Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction

[TKDE2025] Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on large language model-based text-to-SQL.

Stanford's CS224N: Natural Language Processing with Deep Learning (Winter/Spring 2024).

Dashboard for documents using glove vectors as a search assistant.

End to end implementation of ML pipeline and experimenting around it using DVC for Experiment Tracking and Data versioning using AWS S3

End-to-End ETL Pipeline to Build a Biomedical Knowledge Graph from Biomedical Articles.

[TMM 2026] Vision-Controllable Language Model for Image-guided Story Ending Generation

Custom multi-task DistilBERT model that predicts driving intent, emotion, and adaptive driving modes from natural language for intelligent vehicle systems.

Resume Matcher for the command line, currently powered by Codex CLI.

Sentiment analysis of Yelp reviews using DistilBERT and Groq AI for business insights

This is project for sequence to sequence NLP task. We developed a custom model to understand the process of task using PyTorch. We also fine tuned pre-trained transformer models to improve the performance of translation task.

NLP-based sentiment analysis web app | Trained on 50K IMDB reviews | 89% accuracy | Python, Flask, Scikit-learn

O Nexus é um aplicativo desktop completo que fornece recomendações de filmes com base em descrições do usuário. Ele utiliza um frontend em Next.js e Electron, e um backend em Python e FastAPI com recursos de IA para identificar filmes.

Production-ready sentiment analysis system using classical NLP (TF-IDF + Logistic Regression) with FastAPI and Streamlit. Part of my pre-transformer NLP project series.