Transformer(Attention Is All You Need) Implementation in Pytorch

JAX implementation of the bart-base model

JAX implementation of the T5 model: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Spacy NLP Model for the Catalan language

Censored tweets annotated for specificity; AAAI 2019 paper: Predicting and Analyzing Language Specificity in Social Media Posts

A NLP algorithm I developed to determine the similarity or relation between two documents/Wikipedia articles. Inspired by the cosine similarity algorithm and built from WordNet.

Train a T5 model to generate simple Fake News and use a RoBERTa model to classify what's fake and what's real.

An interactive application that leverages a pre-trained language model (GPT-2) to generate human-like text based on user prompts. The application can produce various types of text, such as stories, reports, or dialogues, making it a versatile tool for creative writing, brainstorming, or content generation.

Advanced NLP model implementation in PyTorch featuring transformer architecture, multi-head attention, and comprehensive training pipeline with mixed precision, gradient accumulation, and dynamic learning rate scheduling.

Transform emoticon to text, e.g., :) => Smile.

NLP models

Python Script to train a spacy model.

A Streamlit-based spam classifier that predicts whether a message is spam or not spam using machine learning.

청와대 국민 청원 분류 model