Gabriele Sarti
Avatar

Gabriele Sarti

PhD in Natural Language Processing

CLCG, University of Groningen

About me

Welcome to my website! 👋 I am a PhD student at the Computational Linguistics Group of the University of Groningen and member of the InDeep consortium, working on user-centric interpretability for neural machine translation. I am also the main developer of the Inseq library. My supervisors are Arianna Bisazza, Malvina Nissim and Grzegorz Chrupała.

Previously, I was a research intern at Amazon Translate, a research scientist at Aindo, a student in the Data Science MSc at the University of Trieste and a co-founder of the AI Student Society. My master’s thesis with the ItaliaNLP Lab discussed the study of linguistic complexity using gaze recordings and neural language models.

My research currently focuses on interpretability for NLP models, in particular to the benefit of end-users and by leveraging human behavioral signals. I am also passionate about social applications of machine learning, causality topics, and open source collaboration.

Interests

  • Conditional Text Generation
  • Interpretability for Deep Learning
  • Behavioral Data for NLP
  • Causality and Uncertainty Estimation

Education

Experience

🗞️ News

 

Selected Publications

 

DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages

We introduce DivEMT, the first publicly available post-editing study of Neural Machine Translation over a typologically diverse set of …
Published in: EMNLP 2022
PDF ArXiv Dataset Code Demo

IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation

We present IT5, the first family of encoder-decoder transformer models pretrained specifically on Italian on more than 40 billion …
Published in: Arxiv
PDF ArXiv Models Code Demo

Contrastive Language-Image Pre-training for the Italian Language

We present the first CLIP model for the Italian Language (CLIP-Italian), trained on more than 1.4 million image-text pairs.
Published in: Arxiv
PDF Project ArXiv Model Code Demo

Teaching NLP with Bracelets and Restaurant Menus: An Interactive Workshop for Italian Students

We developed an interactive workshop designed to illustrate the basic principles of NLP and computational linguistics to high school …
Published in: In TeachingNLP 2021
PDF Code Video DOI Annex

That Looks Hard: Characterizing Linguistic Complexity in Humans and Language Models

This paper investigates the relationship between two complementary perspectives in the human assessment of sentence complexity and how …
Published in: In CMCL 2021
PDF Code DOI
See all publications

Blog posts

 

ICLR 2020 Trends: Better & Faster Transformers for Natural Language Processing

A summary of promising directions from ICLR 2020 for better and faster pretrained tranformers language models.
May 3, 2020 14 min read

Recent & Upcoming Talks

Towards User-centric Interpretability of Machine Translation Models
Oct 20, 2022 Harmonie Building, University of Groningen CLCG Linguistics Lunch
Towards User-centric Interpretability of NLP Models
May 18, 2022 Online Tech Talk at Translated
Empowering Human Translators via Interpretable Interactive Neural Machine Translation
Dec 14, 2021 Online XAI4Debugging Workshop at NeurIPS 2021
See all talks

Projects

 

Inseq: An Interpretability Toolkit for Sequence Generation Models

An open-source library to democratize access to model interpretability for sequence generation models

Contrastive Image-Text Pretraining for Italian

The first CLIP model pretrained on the Italian language.

Covid-19 Semantic Browser

A semantic browser for SARS-CoV-2 and COVID-19 powered by neural language models.

AItalo Svevo: Letters from an Artificial Intelligence

Generating letters with a neural language model in the style of Italo Svevo, a famous italian writer of the 20th century.

Histopathologic Cancer Detection with Neural Networks

A journey into the state of the art of histopathologic cancer detection approaches.