Giter Club home page Giter Club logo

Welcome! 🙌

Portfolio Huggingface Hub Twitter LinkedIn Google Scholar

I am a PhD student at the University of Groningen GroNLP Lab and part of the project InDeep: Interpreting Deep Learning Models for Text and Sound, working mainly on interpretability for neural machine translation. Previously, I was a research intern at AWS AI Labs NYC, a research scientist at Aindo, a student in the Data Science MSc at University of Trieste & SISSA and a founding member of the AI Student Society.

My research focuses on interpretability for NLP models, particularly to the benefit of end-users and by leveraging human behavioral signals. I am also very passionate about open-source collaboration :octocat: and I currently lead the development of the Inseq toolkit for interpreting generative language models.

Gabriele Sarti's Projects

cancer-detection icon cancer-detection

Team Capybara final project "Histopathologic Cancer Detection" for the Statistical Machine Learning course @ University of Trieste

csrankings icon csrankings

A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.

divemt icon divemt

Materials for "DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages" at EMNLP'22 🗺️

etc-nlg icon etc-nlg

Materials for "ETC-NLG: End-to-end Topic-conditioned Natural Language Generation" at NL4AI 2020

gradio icon gradio

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

hpc icon hpc

Material for the Foundation of High Performance Computing Course in the Data Science program @ University of Trieste

ik-nlp-tutorials icon ik-nlp-tutorials

Lab tutorials for the MSc NLP course at the University of Groningen 🐮

interpreting-complexity icon interpreting-complexity

Materials for the MSc Thesis "Interpreting Neural Language Models for Linguistic Complexity Assessment" and related works.

it5 icon it5

Materials for "IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation" 🇮🇹

lambda-bert icon lambda-bert

A 🤗-style implementation of BERT using lambda layers instead of self-attention

lcl23-xnlm-lab icon lcl23-xnlm-lab

Materials for the Lab "Explaining Neural Language Models from Internal Representations to Model Predictions" at AILC LCL 2023 🔍

masters-thesis icon masters-thesis

Bookdown for my thesis "Interpreting NLMs for LCA" using the AI2S Thesisdown template.

melts icon melts

Space Apps Hackaton Material for Team MelTS

mlda-course-units icon mlda-course-units

Material from the Machine Learning and Data Analytics course of DSSC MSc @ UniTS/SISSA

newscrapy icon newscrapy

Batch-scrape articles from newspaper archives 📰 ⛏️

nlp-sig icon nlp-sig

Information related to the meetings of the Natural Language Processing SIG of the Netherlands eScience Center

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.