#coling2025

Illustration of a young woman wearing an academic cap and lab coat, closely examining a document with a magnifying glass. A robotic parrot sits on her shoulder, suggesting a blend of science, research, and technology. The style is monochrome with clean, cartoon-like lines.

🚀 𝗟𝗮𝘁𝗲𝘀𝘁 𝗣𝗲𝗲𝗿 𝗥𝗲𝘃𝗶𝗲𝘄 𝗗𝗮𝘁𝗮𝘀𝗲𝘁 𝗥𝗲𝗹𝗲𝗮𝘀𝗲 𝗳𝗿𝗼𝗺 𝗔𝗥𝗥 𝟮𝟬𝟮𝟱!
tudatalib.ulb.tu-darmstadt.de/handle/tudat...

This 𝗻𝗲𝘄 𝗱𝗮𝘁𝗮𝘀𝗲𝘁 expands on previous releases, now including review data from #COLING2025 and #NAACL2025.

(1/🧵)

Why Does ChatGPT “Delve” So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Tom S Juzek, Zina B. Ward. Proceedings of the 31st International Conference on Computational Linguistics. 2025.

'Why Does ChatGPT “Delve” So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models' | Proceedings of the 31st International Conference on Computational Linguistics #COLING2025

🔗 aclanthology.org/2025.coling-...

Our pick of the week by @linaconti.bsky.social: "MuPe Life Stories Dataset: Spontaneous Speech in Brazilian Portuguese with a Case Study Evaluation on ASR Bias against Speakers Groups and Topic Modeling" by Evaldo Leal et al., #COLING2025

#speech #bias #brazilian #portuguese #NLProc

Let me advertise our COLING2025 paper:

Quality Beyond A Glance: Revealing Large Quality Differences Between Web-Crawled Parallel Corpora

We manually evaluate 5 of the largest parallel corpora for 11 low(ish)-resource languages.

The results are quite concerning.

#NLProc #COLING2025 #ACL2025 #NMT

ℹ️ #OraiNLP ko ikertaile Muitze Zulaika Abu Dhabin izan da berriki #euskara zko #LLM en alborapen sozialak ebaluatzeko lehen datu-multzoa aurkezten, #Coling2025 nazioarteko biltzarrean.

📈 Ikerketa horri buruz hitz egin du Zulaikak #EuskadiIrratia ko #Faktoria saioan ⤵️

📻 eitb.eus/N_eKDK5j/

🌐 Muitze Zulaika, researcher from #OraiNLP, showed at #COLING2025 a key step toward creating more #ethical #LLMs for low-resource languages

📝BasqBBQ: A QA Benchmark for Assessing Social Biases in LLMs for #Basque, a Low-Resource Language

💡 More info ⤵️
labur.eus/OL4BG

𝗠𝗮𝗶𝗮 𝗔𝗴𝗶𝗿𝗿𝗲 of the Speech and Natural Language Technologies team participated online at #COLING2025 presenting "Fine-Tuning Medium-Scale LLMs for Joint Intent Classification and Slot Filling: A Data-Efficient and Cost-Effective Solution for SMEs"

🔔 iDEM at #COLING2025

Our iDEM partners Nouran Khallaf, Serge Sharoff and Carlo Eugeni presented our project at the 31st International Conference on Computational Linguistics.

You can also read their paper here 👉 arxiv.org/abs/2501.01796

#science 🧪 #NLP #HorizonEU #disability #democracy #AI

#COLING2025 isn't over yet! I'm presenting my poster now on GatherTown! Come stop by and chat!

DefVerify: Do Hate Speech Models Reflect Their Dataset’s Definition? Urja Khurana, Eric Nalisnick, Antske Fokkens. Proceedings of the 31st International Conference on Computational Linguistics. 2025.

✨Looking forward to presenting our paper “DefVerify: Do Hate Speech Models Reflect Their Dataset’s Definition?” at #COLING2025! ✨

aclanthology.org/2025.coling-...

work done with Eric Nalisnick and Antske Fokkens

I hope to see you at our poster at the virtual session at 16.00 CET today! 🎤

It was great being at #COLING2025 in Abu Dhabi last week! There, I presented our work with @malvinanissim.bsky.social and @van-rijn.org on evaluating the confidence of LLMs as proxy for the difficulty of Multiple-Choice Questions.
You can check out our work here: aclanthology.org/2025.coling-...

🤔 Quite a provocative read from #COLING2025: "Is peer-reviewing worth the effort?"

TL;DR: #NLP A* venue ≠ Citations ≠ Quality. Could early citations (e.g., on ArXiv) + a nomination process fix peer-review scalability?

📎 Read more: aclanthology.org/2025.coling-...

Super honored that this paper received the best paper award at #COLING2025!

#COLING2025 best poster designs :)

#COLING2025 is done!

After the decoupling of LREC/COLING:
#LREC2026 will be "somewhere in the Mediterannean"
#COLING2027 will be in Macau

Check out the paper: "MOPO: Multi-Objective Prompt Optimization for Affective Text Generation" at COLING 2025. 🥳

aclanthology.org/2025.coling-...

📍Session 2, Posters - Jan 24 at 13:30-15:00 at Atrium.
Look for Yarik Menchaca for an interesting discussion!
#COLING2025 #NLProc #NLP #COLING

Iker de la Iglesiak medikuntzako argumentuen ebaluazio automatikoari buruzko posterra aurkeztu du #COLING2025 konferentzian

GitHub - Tireswind/ADTIST24 Contribute to Tireswind/ADTIST24 development by creating an account on GitHub.

Tomorrow at #COLING2025 Youri Peskine will present our paper "Automated Detection of Tropes In Short Texts" (13:30 in Session 13)

Paper: coling-2025-proceedings.s3.us-east-1.amazonaws.com/main/pdf/202...

GitHub for code and annotated data: github.com/Tireswind/AD...

We are in #COLING2025!

LENS poster and software demo at COLING2025

LENS poster and software demo at COLING2025

LENS paper photos... #COLING2025

LENS: Learning Entities from Narratives of Skin Cancer Daisy Monika Lal, Paul Rayson, Christopher Peter, Ignatius Ezeani, Mo El-Haj, Yafei Zhu, Yufeng Liu. Proceedings of the 31st International Conference on Computational Linguistics: System Demonstration...

I've just finished presenting with Daisy Lal our software demo paper on "LENS: Learning Entities from Narratives of Skin Cancer" #COLING2025 part of the 4D Picture (4dpicture.eu) project aclanthology.org/2025.coling-... Code & demo are available online, links are in the paper

Today, I'll be presenting my #COLING2025 paper "How to Leverage Digit Embeddings to Represent Numbers?", come and find me in room A at 2pm

aclanthology.org/2025.coling-...

Cross-lingual Text Classification Transfer: The Case of Ukrainian Daryna Dementieva, Valeriia Khylenko, Georg Groh. Proceedings of the 31st International Conference on Computational Linguistics. 2025.

I'm starting this morning at the low-resource languages 1 session #COLING2025 An interesting observation from @iamdddaryna.bsky.social in her paper aclanthology.org/2025.coling-... that Opus-MT better preserves the toxic lexicon compared to others where this is fine-tuned out

Robustness Evaluation of the German Extractive Question Answering Task Shalaka Satheesh, Katharina Beckh, Katrin Klug, Héctor Allende-Cid, Sebastian Houben, Teena Hassan. Proceedings of the 31st International Conference on Computational Linguistics. 2025.

Our COLING Paper "Robustness Evaluation of the German Extractive Question Answering Task" presentation is tomorrow Wed 14:00 LT at Capital Suite 7 #COLING2025
Want to learn more about multilingual evaluation? ➡️ drop by! 


📄Paper: aclanthology.org/2025.coling-...
💻Code: github.com/shalakasathe...

ModaFact: Multi-paradigm Evaluation for Joint Event Modality and Factuality Detection Marco Rovera, Serena Cristoforetti, Sara Tonelli. Proceedings of the 31st International Conference on Computational Linguistics. 2025.

If you are in Abu Dhabi and are interested in Event Factuality and Modality, feel free to drop by at the poster session on Friday morning (10:30-12)! Happy #COLING2025! #NLProc
📃Paper here: aclanthology.org/2025.coling-...

Why Does ChatGPT “Delve” So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models Tom S Juzek, Zina B. Ward. Proceedings of the 31st International Conference on Computational Linguistics. 2025.

An interesting paper from this morning's sessions at #COLING2025: "Why Does ChatGPT “Delve” So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models" aclanthology.org/2025.coling-...

I finished yesterday afternoon in the @loreslm.bsky.social workshop: low resource languages are a super hot topic in the LoResLM workshop and widely across the #COLING2025 conference

#COLING2025 is underway in Abu Dhabi, UAE, hosted by @mbzuai.bsky.social. Just opened by General Co-chairs Leo Wanner and Owen Rambow! All papers incl. Workshops now available at aclanthology.org. @lindatclariahcz.bsky.social

elmo says i am dino in front of a background of flames Alt: elmo says i am dino in front of a background of flames

just realized there are only 7 papers with "parsing" on their titles at the whole #COLING2025 conference...

If you are attending #COLING2025 find me at Poster Session 3 14.00-15.30 to tell you everything about efficient multi-lingual IR!

The final version of the paper is here

aclanthology.org/2025.coling-...