Gemma Boleda

Behind every medical advance, social study or cultural insight, there is research.

#ICREAcall supports researchers with 20 permanent positions in Catalonia's research system: 

🧑‍🤝‍🧑 Social & Behavioural Sciences 
📚 Humanities 
🔬 Life Sciences & Medicine

https://www.icrea.cat/icrea-call/

Per molts anys i gràcies #comunitatICREA / Happy anniversary and thank you ICREA. Becoming part of this community of researchers was a dream come true.

🎉 Avui és un dia especial! Celebrem els #25anysICREA al CCCB.

Ens trobem més de 320 persones per celebrar un quart de segle de recerca d'excel·lència que ha transformat Catalunya i l'ha projectat al món.

Avui, més que mai, tots #SomICREA.

Sample ManyNames images with associated names, in English and Mandarin Chinese

Releasing v. 2.3 of ManyNames, an object naming dataset with 25K objects in real world images (English, plus partial coverage in Catalan and Mandarin Chinese). Check it out!

amore-upf.github.io/manynames/

(New in this version: further data cleaning, speaker ID, more lexical info)

Presented at #DLBCN, a very nice yearly event showcasing what is done around Deep Learning in Barcelona. Come to the next edition!

There’s more to Neural Nets than big fat LLMs!

We’ve built a NN-agent framework to simulate how people choose the best word in a given communication context (i.e. pragmatic naming behavior).

With @yuqing0304.bsky.social, @ecesuurker.bsky.social, Tessa Verhoef, @gboleda.bsky.social

Happy to announce a keynote lecture by @gboleda.bsky.social on "Why are Large Language Models so good at language?" at our Leibniz MMS Days next March (registration open until 7 January):
www.wias-berlin.de/workshops/MM...
www.wias-berlin.de/workshops/MM...

Ever wondered how our words change their meanings over time, and why languages keep both broad terms (“dog”) and specific ones (“Dalmatian”)?
Our new paper asks that question, but instead of asking humans, we ask neural agents 🤖
🧵👇

It's partially the former, partially the latter. We understand some aspects of how LLMs work, but there's A TON that we still don't understand. This is a super active area of research at the moment (keywords: explainable AI, interpretability).

Sigmoid function. Non-linearities in neural network allow it to behave in distributed and near-symbolic fashions.

New paper! 🚨 I argue that LLMs represent a synthesis between distributed and symbolic approaches to language, because, when exposed to language, they develop highly symbolic representations and processing mechanisms in addition to distributed ones.
arxiv.org/abs/2502.11856

CoNLL is over! Here’s most of the organizing team, next to the Danube in Vienna (missing
‪@nvshrao.bsky.social and Snigdha Chaturvedi). #conll2025 @conll-conf.bsky.social @microth.bsky.social @emcheng.bsky.social

Announcing the COLT Symposium on June 2nd!

𝗘𝗺𝗲𝗿𝗴𝗲𝗻𝘁 𝗳𝗲𝗮𝘁𝘂𝗿𝗲𝘀 𝗼𝗳 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗶𝗻 𝗺𝗶𝗻𝗱𝘀 𝗮𝗻𝗱 𝗺𝗮𝗰𝗵𝗶𝗻𝗲𝘀

What properties of language are emerging from work in experimental and theoretical linguistics, neuroscience & LLM interpretability?

Info: tinyurl.com/colt-site
Register: tinyurl.com/colt-register

🧵1/3

🚨 Guest Speaker Alert! 🚨

We’re thrilled to announce that #CoNLL2025 will feature: 🥁

Raquel Fernández (University of Amsterdam)
&
Jean-Rémi King (@jeanremiking.bsky.social, CNRS / Meta AI)!
🎤✨

Check out their awesome work!👇

📢 Upcoming Seminar

Words are weird? On the role of lexical ambiguity in language
🗣 Gemma Boleda (Universitat Pompeu Fabra, Spain)
Why is language so ambiguous? Discover how ambiguity balances cognitive simplicity and communicative complexity through large-scale studies.
📍 UniMiB, Room U6-01C, Milan

LLMs as a synthesis between symbolic and continuous approaches to language Since the middle of the 20th century, a fierce battle is being fought between symbolic and continuous approaches to language and cognition. The success of deep learning models, and LLMs in particular,...

new pre-print: LLMs as a synthesis between symbolic and continuous approaches to language arxiv.org/abs/2502.11856

📢 The Computational Linguistics Seminar series: the Interplay between Language and Reasoning is scheduled for Thursday, February 6th, 2025 (16:30) and will feature Raffaella Bernardi, University of Trento ✨

📍 L0.06 of LAB42 UvA (live streaming on Zoom 🌍)

📎 projects.illc.uva.nl/LaCo/CLS/

CoNLL 2025 Call for Papers 😀!
#CoNLL2025
conll.org
🔴 Co-located w/ ACL 2025 (July 31 - August 1)
⚪️ This year CoNLL will only accept direct submissions (ddl: March 14 2025)
⚫️ CoNLL will accept both non-archival and archival submissions!

This year, CoNLL will be accepting *non-archival* (as well as archival) submissions! www.conll.org #CoNLL2025

Follow CoNLL at
@conll-conf.bsky.social

🔊New EMNLP paper from Eleonora Gualdoni & @gboleda.bsky.social !

Why do objects have many names?

Human lexicons contain different words that speakers can use to refer to the same object, e.g., purple or magenta for the same color.

We investigate using tools from efficient coding...🧵

1/3

Can I be added? (Gemma Boleda, Barcelona, gboleda.github.io). Thanks!