I'm using mostly Linkedin now for sharint professional updates, please feel free to connect with me there if you'd like to stay in touch:
linkedin.com/in/duygu-atama…
English
Duygu Ataman
516 posts
Duygu Ataman
@_dataman_
Scientist/engineer working on computational models for language understanding and reasoning. Assistant professor @MetuCogSci.
Ankara, Turkey Se unió Ağustos 2012
446 Siguiendo1.1K Seguidores
Duygu Ataman retuiteado
I'm honored and humbled that Jonne Sälevä, Duygu Ataman (@_dataman_) and I received the best paper award at @aaclmeeting for our work on evaluation in multilingual/multitask benchmarks. I never expected an eval paper could make it this far! More info here: github.com/j0ma/reuben
English
I’ll be at #NeurIPS2025 this week to present some work on spurious correlations! Catch us at the poster session on 12/3 😊
Chantal@ChantalShaib
Syntax that spuriously correlates with safe domains can jailbreak LLMs -- e.g. below with GPT4o mini Our paper (co w/ @VMSuriyakumar) on syntax-domain spurious correlations will appear at #NeurIPS2025 as a ✨spotlight! + @MarzyehGhassemi, @leventsagun, @byron_c_wallace
English
If you're interested in the Ph.D. Program in Cognitive Science at the School of Informatics, METU the applications are now open to start in Spring 2026. To indicate your interest in working with me you can mention it in your cover letter.
ii.metu.edu.tr/important-date…
English
Duygu Ataman retuiteado
I am the 129th author🎉🎉🎉
We managed to include Azerbaijani, Kyrgyz, and Turkish examples, thanks to @_dataman_ and her team.
Multilingual Representation Workshop @ EMNLP 2025@mrl_workshop
Introducing Global PIQA, a new multilingual benchmark for 100+ languages. This benchmark is the outcome of this year’s MRL shared task, in collaboration with 300+ researchers from 65 countries. This dataset evaluates physical commonsense reasoning in culturally relevant contexts.
English
Duygu Ataman retuiteado
Excited to announce the call for papers for the Multilingual Representation Learning workshop #EMNLP2025 sigtyp.github.io/ws2025-mrl.html
with @_dataman_ @linguist_cat Jiayi Wang @fdschmidt @tylerachang @hila_gonen
and amazing speakers: Alice Oh, Kelly Marchisio, & Pontus Stenetorp
Catherine Arnett@linguist_cat
The call for papers is out for the 5th edition of the Workshop on Multilingual Representation Learning which will take place in Suzhou, China co-located with EMNLP 2025! See details below!
English
Excited to hold the first weekly meeting of my research group @MetuCogSci. Today our visiting researcher Kavsar Huseynova shared insights on how neural reasoning pathways can be traced in LLMs.
English
@phylo_GENETIC @LeonDerczynski But it doesn't apply to all categories
English
@phylo_GENETIC @LeonDerczynski As long as there's still a track left to submit traditional computational linguistics papers then technically that track could help not compete with more AI oriented papers
English
on ed hovy's framing of LLM heavy papers at #ACL2025NLP being "popcorn papers", which might seem fine enough while you're consuming them, but are not filling or nutritious, and just leave one hungry for some real knowledge
1. it's correct
English
@oflazer @sigturk Sigturk has 200 members. Did you ask all of them for help organizing? I wish you made it clear you didn't have time to organize in advance also the organizing committee and the members. The workshop benefits the community significantly and it will be sad to miss the opportunity.
English
Dear colleagues,
We're writing to share some important updates from ACL SIGTURK regarding our board members and our online presence.
Board Members
First we wanted to introduce our current board members. The current SIGTURK board consists of:
1/n
English
large scale fine-tuning
en.wikipedia.org/wiki/Fine-tune…
English
@inceppption If you're interested please send me a CV and a short statement on your research experience and interests and we can discuss a potential project
English
I still have open full-time or part-time research scholarships for Master's or PhD students who are interested in studying topics around efficient learning and optimization methods for language modeling and applications.
English
Duygu Ataman retuiteado
*I-Con: A Unifying Framework for Representation Learning*
by @Sa_9810 @mhamilton723 et al.
They show that many losses (contrastive, supervised, clustering, ...) can be derived from a single loss defined in terms of neighbors distributions.
arxiv.org/abs/2504.16929
English
Scholarships are open to students at other universities in Turkey and abroad but would require relocation during the time of the study.
English
Please get in touch if you are interested and looking for a funding opportunity.
English
@Anthony_Bonato A way to think, understand and express my thoughts
English
Duygu Ataman retuiteado
The submission deadline for the 5th Workshop on Multilingual Representation Learning is coming up! See details below!
English