Gemma Boleda
@gboleda.bsky.social
linguistics x artificial intelligence x cognitive science | computational linguistics, NLP | COLT Research Group @colt-upf.bsky.social, ICREA @icreacommunity.bsky.social, Universitat Pompeu Fabra @upf.edu, @traduccioupf.bsky.social
gboleda.github.io
gboleda.github.io
Reposted by Gemma Boleda
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 🤖
🧵👇
Our new paper asks that question, but instead of asking humans, we ask neural agents 🤖
🧵👇
November 6, 2025 at 1:52 PM
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 🤖
🧵👇
Our new paper asks that question, but instead of asking humans, we ask neural agents 🤖
🧵👇
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
arxiv.org/abs/2502.11856
September 30, 2025 at 1:16 PM
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
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
@nvshrao.bsky.social and Snigdha Chaturvedi). #conll2025 @conll-conf.bsky.social @microth.bsky.social @emcheng.bsky.social
August 3, 2025 at 1:18 PM
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
@nvshrao.bsky.social and Snigdha Chaturvedi). #conll2025 @conll-conf.bsky.social @microth.bsky.social @emcheng.bsky.social
Reposted by Gemma Boleda
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
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
May 13, 2025 at 9:00 AM
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
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
Reposted by Gemma Boleda
🚨 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!👇
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!👇
March 4, 2025 at 4:02 PM
🚨 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!👇
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!👇
Reposted by Gemma Boleda
📢 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
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
March 3, 2025 at 1:41 PM
📢 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
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
new pre-print: LLMs as a synthesis between symbolic and continuous approaches to language arxiv.org/abs/2502.11856
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,...
arxiv.org
February 24, 2025 at 4:29 PM
new pre-print: LLMs as a synthesis between symbolic and continuous approaches to language arxiv.org/abs/2502.11856
Reposted by Gemma Boleda
📢 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/
📍 L0.06 of LAB42 UvA (live streaming on Zoom 🌍)
📎 projects.illc.uva.nl/LaCo/CLS/
Computational Linguistics Seminar Series at ILLC
projects.illc.uva.nl
February 4, 2025 at 3:33 PM
📢 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/
📍 L0.06 of LAB42 UvA (live streaming on Zoom 🌍)
📎 projects.illc.uva.nl/LaCo/CLS/
Reposted by Gemma Boleda
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!
#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!
CoNLL 2025 | CoNLL
conll.org
February 7, 2025 at 9:28 PM
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!
#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
Follow CoNLL at
@conll-conf.bsky.social
CoNLL 2025 | CoNLL
www.conll.org
February 5, 2025 at 2:15 PM
This year, CoNLL will be accepting *non-archival* (as well as archival) submissions! www.conll.org #CoNLL2025
Follow CoNLL at
@conll-conf.bsky.social
Follow CoNLL at
@conll-conf.bsky.social
Reposted by Gemma Boleda
🔊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
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
December 2, 2024 at 10:43 AM
🔊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
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