2nd paper! Introducing: Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages, work with Adam Lopez, @roiblanco, @DieEmme! https://t.co/jK7rTfZtQO. Presenting at #ACL2023 Findings Spotlight Mon 10/07 (talk), and @trustnlp Fri 14/07 (poster)!🧵
🌍Few-shot learning beyond English🌏
📢 Announcing XGLMs, a series of multilingual autoregressive languages models setting new SoTA on few-shot learning and outperforming English-centric models (e.g. GPT-3).
Paper: https://t.co/nn4YD5bwFd
Models and code: https://t.co/ob0HkhnAP4
Graph neural networks are driving lots of progress in machine learning by extending deep learning approaches to complex graph data and applications.
Let’s take a look at a few methods ↓
Prima copia arrivata! Rigore di testa racconta le scorribande calcistiche che facciamo con la nostra startup Playerank. Tra Darko pancev, Ronaldo il fenomeno e tutti quelli che rendono la vita impossibile agli algoritmi. Prima presentazione: domenica al @SalonedelLibro
The deadline for the PhD position on generalization in NLP with @wilkeraziz and me is in 2 weeks, "position #4" in the ad below (if you're not into NLP, there are other very interesting positions in the call, causal modeling, search, etc) @AmsterdamNLP https://t.co/VFZ9lEpm8V
Big thank you to @YejinChoinka, @HinrichSchuetze,
and Yulia Tsvetkov for the very interesting talks at @ELLISforEurope NLP workshop! You can watch them online at https://t.co/w6L37FXQdY
We're pleased to announce the 22 recipients from the 2020 Q1/Q2 AWS Machine Learning Research Awards, who represent 21 universities in six countries. The awards aim to advance ML by funding research and open-source projects, and more. #AmazonResearchAwards https://t.co/94xEy3ud4h
Hey, my team in Barcelona is looking for interns for 2021!
If you'd like to work with us on hard/fun NLP problems, please apply.
https://t.co/ilURe51v5X
#EMNLP2020 We’ve released 1.2 million reviews in 6 languages in the Multilingual Amazon Reviews Corpus (MARC)! w/ Y. Lu G. Szarvas @nlpnoah https://t.co/OtoJaZqmvU
The dataset was carefully cleaned and is balanced across star ratings. Try it out at https://t.co/GxvB3cAwh5 1/3