←
Giannis Karamanolakis173 posts
Giannis Karamanolakis avatar

Giannis Karamanolakis

@gkaraml

Senior Applied Scientist @Amazon AGI. Previously @MSFTResearch, @Columbia, @behaviorsignals.

◷ Joined October 2013▧ 8 Photos and videos
Giannis Karamanolakis avatar
Giannis Karamanolakis@gkaraml·3 Dec 2024

Excited to share our Amazon Nova Foundation Models! Proud to be part of the team bringing Nova models to our customers and excited for what lies ahead. aws.amazon.com/ai/generative… #amazon #nova #llm

Giannis Karamanolakis avatar
Giannis Karamanolakis@gkaraml·21 Apr 2022

Check out Natural Instructions v2, a benchmark with 1600+ #NLProc tasks and their natural language instructions. Excited to be part of this effort!

Is it possible to solve NLP tasks by simply following instructions that define the tasks? How can we measure the progress? Excited to announce Natural Instructions v2, a collection of 1600+ diverse language tasks and their expert-written instructions! 📜arxiv.org/abs/2204.07705

Antonis Anastasopoulos @EMNLP avatar
⟳ Giannis Karamanolakis retweeted
Antonis Anastasopoulos @EMNLP@anas_ant·19 Jan 2022

Are you #PhDone (or close)? Would you like to live in the Washington, DC area and be part of the *exciting* @GMUCompSci dept, working on Machine Translation and #nlproc for low-resource languages? I'm looking for a postdoc (ideally starting in 2022) -- do reach out if interested!

Giannis Karamanolakis avatar
Giannis Karamanolakis@gkaraml·7 Jun 2021

Our weak supervision method, ASTRA, leverages domain-specific rules, unlabeled data, and few labeled data through self-training. If you are attending #NAACL2021 today, join our paper's presentation and Q&A at Session 3B. Happy to chat :)

(((ل()(ل() 'yoav))))👾 avatar
⟳ Giannis Karamanolakis retweeted
(((ل()(ل() 'yoav))))👾@yoavgo·18 Jul 2020

initial attempts: very impressive QA results (check out the coref in the gates questions!) but also has some glitches.

Post attachment
Giannis Karamanolakis avatar
Giannis Karamanolakis@gkaraml·8 Jul 2020

If you are attending #acl2020nlp, then join my talk & Q/A at virtual.acl2020.org/paper_ma…. If not, you can find our slides here: tinyurl.com/y8tpb4mt. @ColumbiaCompSci also summarizes TXtract among other great papers by @Tuhin66978276, @chridey and others: cs.columbia.edu/2020/acl-202…