Yarden Tal

MSc in computer science, @nlphuji lab at @CseHuji. #NLProc

[Yarden Tal @YardenTal2]

What is the connection between model size and gender bias?
📢Excited to introduce my first paper “Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias” with @inbalmagar and @royschwartzNLP
at the #GeBNLP workshop at #NAACL2022 https://t.co/0UNaEsKuk0
1/n

[Aviv Slobodkin @NeurIPS @lovodkin93]

Ever skimmed an article, pinpointing key info, and wished for a tailor-made summary without crafting it yourself?🤔
Introducing SummHelper: your go-to for personalized summarization. 📜✏️

w/ Niv Nachum @pyshmulik @obspp18 Ido Dagan

1/n

[Yuval Reif @YuvalReif]

Is dataset debiasing the right path to robust models?

In our work, “Fighting Bias with Bias”, we argue that in order to promote model robustness, we should in fact amplify biases in training sets.

w/ @royschwartzNLP
In #ACL2023NLP Findings
Paper: https://t.co/zYP6FuVpe9
🧵👇

[Daniel Rotem @Dayman332]

Excited to present our new work on Adaptive Inference methods at #ACL2023NLP! Our paper uncovers fascinating insights about the Multi-Model and Early-Exit approaches.
Work done with @MichaelHassid, @Jonatha25240734 and @royschwartzNLP.
🧵1/9
https://t.co/y3IX4Cue3x

[Asaf Yehudai @ACL 🇺🇲 @AsafYehudai]

Looking for a new SOTA few-shot classifier?

We present QAID!
QAID uses batch contrastive learning with BERTScore &
classifies by retrieving the intent name.

SOTA on few-shot Intent Detection! 🎉
https://t.co/bMxNHwO0gc

Accepted to @iclr_conf 2023 🥳
#NLProc #NLP #ML

[Yonatan Bitton @YonatanBitton]

Happy to share our #AAAI23 paper
VASR: Visual Analogies of Situation Recognition.
https://t.co/YLevdOuc6y

Man:king :: man:woman. Now, with images.
Which candidate best solves the analogy?

w. @ron_yosef @StrugoEli @HyadataLab @royschwartzNLP @GabiStanovsky
🧵1/8

[Leshem (Legend) Choshen 🤖🤗 @ACL @ICML @LChoshen]

We want to pretrain🤞
Instead we finetune🚮😔
Could we collaborate?🤗

ColD Fusion:
🔄Recycle finetuning to multitask
➡️evolve pretrained models forever

On 35 datasets
+2% improvement over RoBERTa
+7% in few shot settings
🧵

#NLProc #MachinLearning #NLP #ML #modelRecyclying

[Yonatan Bitton @YonatanBitton]

Attending #NeurIPS2022 in New Orleans 😀

We will present our paper WinoGAViL (https://t.co/aA7vBh6i8l) in Poster Session 1 (https://t.co/4GwL0Vo3Dv).

The paper was selected as a featured presentation, on Dec 7, 5-7 p.m (similar to our oral presentation in previous years).

[Daniel Rotem @Dayman332]

How much does Attention actually attend? Apparently, not as much as you might have thought.
New paper in Findings of EMNLP with Michael Hassid, @haopeng_nlp @wittgen_ball @ivanspmontero @nlpnoah @royschwartzNLP
https://t.co/uiKdi5oJou
#EMNLP_2022
(1/n)

[Leshem (Legend) Choshen 🤖🤗 @ACL @ICML @LChoshen]

I don’t train from scratch, I use RoBERTa🧐
Wait…
Why not cross-encoder/stsb-roberta?facebook/muppet-roberta?

We automatically identify the best models on 🤗(periodically)

Just pick the best one
and finetune on your task

https://t.co/TO92t2hl2a
https://t.co/Y5FKjfEZk1

[Dan Ofer (✈️ ICML-26 Was @Worldcon) @danofer]

Can an AI joke & win Cards Against Humanity?

#emnlp2022 findings short paper (#3479):
"Cards Against AI: Predicting Humor in a Fill-in-the-blank Party Game"

w/ @HyadataLab

Paper: https://t.co/ZxZ2L6exYX
Code: https://t.co/moAwJqqEVk
Data: @CAH labs
1/

#CAH #NLP

[Oren Sultan @oren_sultan]

Analogies are everywhere!
We Gotta Catch 'Em All! ◓😎

📣 #emnlp2022 (main conference) long paper 🎉:
🎪 Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes 🤡

w/ @HyadataLab

paper: https://t.co/612xuJdifn
🧵 1/

[Leshem (Legend) Choshen 🤖🤗 @ACL @ICML @LChoshen]

Machine Translation often fails on syntax

We trained the model to extract syntax
and reencode the predicted syntax

https://t.co/9b2k4KeQIx
me @oabend
#conll2020 #NLProc

[Leshem (Legend) Choshen 🤖🤗 @ACL @ICML @LChoshen]

Transformers are not Seq2Seq
Given a context
They predict a single token

We use this to update representations between predicted tokens
& feed a changing graph relevant to the current token

https://t.co/9b2k4KeQIx
me @oabend
#conll2020 #NLProc

[Yonatan Bitton @YonatanBitton]

Happy to share that our paper was accepted to #NeurIPS2022, Datasets and Benchmark :)
Camera-ready version is available here: https://t.co/krJPClGNXp
Also, check out the Huggingface integration + Colab: https://t.co/8XgK1WYeYK
We'd be there in person and would love to talk!

[Avihu Dekel @AvihuDekel]

Every machine learner knows that the dataset quality is crucial.
Active learning detects the most valuable samples for annotation.

Our #NeurIPS2022 paper proposes a theoretically grounded (and effective!) approach to low-budget active learning.
https://t.co/XFnPCaGTPV

[Daniel Khashabi 🕊️ @DanielKhashabi]

For my first course at @jhuclsp, I am leading a class on recent developments in "self-supervised models." Here is the list of the papers and slides we cover: https://t.co/zDjxlNXL2L Would love to hear Twitter's suggestions for additional exciting developments to discuss!🤗

[Or Tal @Or__Tal]

Excited to share that next week I will be giving an oral presentation of our recently published paper @ Interspeech 22.
🌟Presentation video🌟: https://t.co/ts10cotSOF
📜🐍🔊full paper, code and audio: https://t.co/ovFcoXuLhN

@MosheMandel1 @FelixKreuk @adiyossLC

[Roy Schwartz @royschwartzNLP]

Efficiency is becoming a central theme in #NLProc. But there are so many different aspects of efficiency! Our recent paper surveys the wealth of approaches on the topic, providing a taxonomy of ideas, and outlining important open problems. https://t.co/2G1fjI0yyP 1/3

[Yonatan Bitton @YonatanBitton]

Which images best fit the cue werewolf? Did you know V&L AI models only get ~50% on our challenging WinoGAViL association task but humans get 90%?

w. Nitzan Ron Yuval @mohitban47 @GabiStanovsky @royschwartzNLP

Paper: https://t.co/1yiJuXN1Hi
Website: https://t.co/wJv1bIrNCp
🧵

[Or Tal @Or__Tal]

Using Phonetic Features is becoming a commonly used methodology for improving model performance in various speech-related applications.
🌟Check out our work🌟@ISCAInterspeech
💡Project Page: https://t.co/Gl8mBiTmmu
📜Paper: https://t.co/xFUHf5LtkZ
🐍Code: https://t.co/xZhP1wfwM1