It's going to be in Lisbon, on June. Website: analogiae.tecnico.ulisboa.pt… ,
Application form: forms.gle/N7wrS6VeyyTevLno7
(This is invitation-only, to keep the event effective)
I don't want it to be a regular talks-and-posters workshop. It's supposed to be more of a collaboration space between researchers from different disciplines who are passionate about analogies. Know someone like this? Pass this along!
Happy to announce that we are starting a new workshop on Computational Analogy, called Principia Analogiae (Yeah, the name is a bit megalomaniac. I like it this way. :) ).
Keynote speakers:
* IARML: Zied Bouraoui, Emiliano Lorini
* Analogy-ANGLE: @KenForbus and Tony Veale
Deadline is the same, and fast approaching (May 10th), number of pages is quite different (short/long: 2/12 vs. 4/7). Both will consider some form of already-published papers.
Analogy-ANGLE (analogy-angle.github.io ): new kid on the block. The focus is more on interdisciplinary research informed by cognitive science and psychology, and also on the notion of analogical _abstraction_.
IARML (iarml2024-ijcai.loria.fr ): this is the 3rd edition. Aiming more for the CS/ML crowd. Last year there was a lot of talk about LLMs, deep learning and applications, but also several more theoretical talks.
[shaking off the dust of this account; crazy times]
Fellow analogy enthusiasts -- this year there are *two* analogy workshops at IJCAI. 🎉
If you're considering submitting (or attending), let me try and break down their differences.
Yeah. Figured a way to use university credit card with a strict monthly cap (and sending them the invoice the second I get it).
Replying to @VeredShwartz
I've had that. I've also had journalists attributing what I said to other people (and once or twice attributing to me stuff I don't think I said🤷♀️). I now ask to go over the piece before publication if possible.
Hyadata Lab (Dafna Shahaf) retweeted
Happy to share our #AAAI23 paper
VASR: Visual Analogies of Situation Recognition.
arxiv.org/abs/2212.04542
Man:king :: man:woman. Now, with images.
Which candidate best solves the analogy?
w. @ron_yosef @StrugoEli @HyadataLab @royschwartzNLP @GabiStanovsky
🧵1/8
The Lean Data Scientist (or: what to do when you can't just "throw more data at it"), soon to appear at @CACMmag and at @WiMLworkshop @NeurIPS.
Ever wanted to train a model but didn't have enough data and/or labels? We surveyed the lit and summarized methods to overcome this data bottleneck problem in a practitioner-centric taxonomy Accepted at CACM & WiML@NeurIPS
arxiv.org/pdf/2211.07959.pdf
@jonzarecki @HyadataLab @CseHuji
Replying to @gilibugg
הזכרת לי מאמר (חישובי) בדיוק על זה, עם שם חינני:
Cockamamie Gobbledegook for Nincompoops
proceedings.mlr.press/v97/gu…
Replying to @Lielisal
המון אנשים אומרים תודה ובבקשה, חלק גם שואלים איך היה היום שלה או מספרים לה על שלהם.🤷♀️
Computers will never beat people at ________.
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: arxiv.org/abs/2210.13016
Code: github.com/ddofer/CAH
Data: @CAH labs
1/
#CAH #NLP
Also, congrats to @oren_sultan for having his first two(!) papers ever accepted (on the first try!). 🦾
#EMNLP2022
Fun work suggesting a new challenging setup for computational analogy -- natural-language texts describing situations or processes (how the heart works/how a pump works). Take a look if you've had enough of the king:queen::man:? example.😋
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: arxiv.org/abs/2210.12197
🧵 1/
Replying to @Shwekster
לקחתי שתי ילדות בנות חמש לביקור קצרצר (זירת חרבות, משחק קופסה חדש בשבילן, ספרים של עוץ וצילום עם כמה דמויות שהן מכירות).








