Antonio Barone
Associate Researcher
City of Edinburgh, Scotland, United Kingdom
Summary
👤
Senior🎓
Top SchoolAntonio Barone is an associate researcher at the University of Edinburgh with a decade of experience at the intersection of NLP, machine learning and emerging quantum computing methods. He holds a PhD from Università di Pisa on syntax-based machine translation using dependency grammars and discriminative learning, and has translated that academic depth into practical contributions to open-source NMT—refactoring core Nematus components to improve validation, sampling and domain interpolation. Based in Edinburgh, he combines rigorous research with hands-on engineering, bridging legacy syntactic approaches and modern neural models. Colleagues value his ability to convert theoretical insights into production-ready code and to navigate both academic and software ecosystems.
10 years of coding experience
Università degli Studi di Palermo
Italian, English
Github Skills (8)
sequence-to-sequence10
machine-translation10
tensorflow10
neural-machine-translation10
nmt10
python10
deep-learning9
theano7
Programming languages (6)
Github contributions (5)
EdinburghNLP/nematus
Sep 2016 - May 2019
Open-Source Neural Machine Translation in Tensorflow
Role in this project:
ML Engineer
ML EngineerContributions:11 commits, 12 PRs, 79 pushes in 2 years 9 months
Contributions summary:Antonio primarily focused on refactoring and enhancing the neural machine translation (NMT) model within the Nematus framework. Their contributions included modifications to the core `nmt.py` file, indicating a deep understanding of the model's architecture and components. These changes likely aimed at improving the model's performance, efficiency, or adding new features related to domain interpolation, validation, and sampling techniques.
neural-machine-translationtensorflowsequence-to-sequencemachine-translationnmt
EdinburghNLP/code-docstring-corpus
Apr 2017 - Jul 2020
Preprocessed Python functions and docstrings for automated code documentation (code2doc) and automated code generation (doc2code) tasks.
Contributions:13 commits, 4 PRs, 28 pushes in 3 years 3 months
code-documentationcode-generationdocstringspython-functionscorpus
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.