Rafael Macario
@rmaacarioComputational Linguist | Technical Writer | EN>PT/ES Translator | Ph.D. Student | NLP, LQA & LLMs | Low-Resource Language Development
Language Breakdown
Lines of code distribution across 15 owned repositories
I-Shaped Developer
I-shapedSpecialist — deep expertise in TeX
Collaboration Network
Global Impact visualization
Repos
17
PRs
0
Growth
+18%
Top Collaborators
No collaborator data yet.
Coding Streak
Contribution activity over the past year
Minh Duc Bui
@MinhDucBui
Rolando Coto
@rolandocoto
Thu
@thu-vu92
Santiago Góngora
@sgongora27
Luis Chiruzzo
@luischir
Top Repositories
Bilingual parallel corpus pipeline for Portuguese-Nheengatu constitution text (5,028 sentence pairs)
This repo is an adaptation of UC Berkeley's project and focuses on developing search algorithms and reinforcement learning techniques for artificial agents. The code covers related topics and can be used for further exploration in the field of AI.
AmericasNLP 2026 Shared Task - USP submission. Fine-tuning NLLB-200 for Guarani, Wixarika, Nahuatl, Bribri.
Code and data from the master’s thesis “Decoding Spatial Semantics”. Analyzes and compares open-source LLMs and NMT systems in translating spatial prepositions from English to Brazilian Portuguese. Includes preprocessing scripts, datasets, and evaluation metrics.
Este projeto é uma ferramenta simples de correção ortográfica desenvolvida como parte do curso de Processamento de Linguagem Natural (NLP) na Alura. O objetivo é construir um verificador ortográfico básico em Python, utilizando técnicas de processamento de texto e cálculos de probabilidade. 🐍🚀
This repo contains a hands-on Python Pandas challenge. Explore UFRN library loan data, analyze trends, and create an HTML table with custom styling. Join for a week of coding to refine data analysis skills! 🚀🐍
Open Source Impact
Contributions to external projects
No external contributions found.