Gabriele Sarti

232 Followers
343 Following
27 Posts
PhD Student in Explainable NMT at @gronlp & Core Dev @inseq. Interpretability ∩ #NLG #NLProc. Prev: AWS AI, Aindo, ItaliaNLP Lab
LocationGroningen, Netherlands
Websitehttps://gsarti.com
Twitterhttps://twitter.com/gsarti_
Githubhttps://github.com/gsarti
We are on Mastodon! As of today, we will be regularly posting about our research, education and other news. Follow us and stay up to date! 😀 ✅

Yesterday @andreasvc and @RikVanNoord were invited to discuss #ChatGPT during the strategic meeting of the University Council and the Board of the University.

The University of Groningen is clearly on top of the developments in AI and NLP! #ResponsibleAI

Event slides: gronlp.github.io/BoUChatGPT.pdf

My INCREC project was awarded an ERCCoG grant to look at the translation process when working with MT in audiovisual and literary translation for the next five years!

Soon I'll be looking for collaborators!!!

https://www.rug.nl/news/2023/01/major-european-grant-for-ana-guerberof-arenas-and-tina-kretschmer

@gronlp #erccog @ERC_Research #MT #xl8 #literary #avt

Grote Europese beurzen voor Ana Guerberof Arenas en Tina Kretschmer

Ana Guerberof Arenas en Tina Kretschmer van de Rijksuniversiteit Groningen hebben beiden een ERC Consolidator Grant toegekend gekregen. De Europese...

Rijksuniversiteit Groningen

Implicit in Explainable AI is the question -- "explainable to whom?"

Who opens the black box of AI is just as important as, if not more, opening the black box.

#AI #ML #academia #academicchatter #XAI #ExplainableAI #HCI #HCXAI

Had a great time meeting people at #BlackboxNLP and #EMNLP2022 last week. You can see my talk as well as great talks by Lena Voita and Catherine Olsson on youtube here:

https://youtube.com/@blackboxnlp

BlackboxNLP

Teile deine Videos mit Freunden, Verwandten oder der ganzen Welt

YouTube
toot toot!
Just getting started here. Start following us for updates.
#BlackboxNLP YouTube channel already has 170 subscribers, thank you! 🎉 You can now watch Jenny Kunz's talk which received best paper award at the workshop: https://youtu.be/3GKjFdNwEI0 #nlp #nlproc #xai
Jenny Kunz - Human Ratings Do Not Reflect Downstream Utility: A Study of Free-Text Explanations [..]

YouTube

The faculty of arts at the University of Groningen is hiring 24(!) Assistant Professors in the Humanities! 🇳🇱

Themes include:
- Humane AI
- Material and Intangible Heritage
- Creative Industries,
- Media and Popular Culture, etc.

https://www.rug.nl/about-ug/work-with-us/job-opportunities/?details=00347-02S0009TKP

#academicJobs #language #linguistics @UnivGroJobs #languageLearning #SLA #L2Learning

Vacatures bij de RUG

Rijksuniversiteit Groningen

After a year of restless development, I'm finally happy to announce Inseq, a new tool to democratize post-hoc #interpretability of sequence #generation models 🐛 https://github.com/inseq-team/inseq #nlproc #xai

Inseq supports most Hugging Face decoder-only and seq2seq models, with a variety of attribution methods already baked in, and many more to come! 🚀 Visualizing MetaAI's Galactica writing LaTeX or GoogleAI Flan-T5 doing commonsense reasoning takes only 3 lines of code 🤯

GitHub - inseq-team/inseq: Interpretability for sequence generation models 🐛 🔍

Interpretability for sequence generation models 🐛 🔍 - GitHub - inseq-team/inseq: Interpretability for sequence generation models 🐛 🔍

GitHub
Not quite the most plausible explanation, but still mind-blowingly fluent 🤯 hats off to OpenAI