Cardiff NLP

This week, we had the pleasure of hosting @christinenlp.bsky.social , who presented her work on 'Modelling the Language of Extremist Groups.' Thank you for visiting us!

And our SemEval task won the best task award! 🥳
Co-led with Shamsuddeen Muhammad and Saif M. Mohammad. Thanks to all the team members!

Our ✨BRIGHTER✨ paper won the a best resource paper award at @aclmeeting.bsky.social #ACL2025!
Big thanks to all the team members!

Also presenting:
📄BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages
🔗 aclanthology.org/2025.acl-lon...
📍 Session 9: IP-Orals – Resources and Evaluation 2
🗓️ Tue, July 29 🕑 14:00–15:30📍 Hall B
2/

At #ACL2025 #ACL2025NLP In Vienna this week!
I’ll be presenting:
📄 Building Better: Avoiding Pitfalls in Developing Language Resources when Data is Scarce
🔗 aclanthology.org/2025.acl-lon...
📍 Panel 5: Multilinguality & Language Diversity
🗓️ Wed, July 30 🕘 09:00–10:30📍 Hall N.2
1/

Loved giving my second tutorial on steering vectors at #CardiffNLPWorkshop Lots of enthusiastic participants! @cardiffnlp.bsky.social

🚨 Check out the Cardiff NLP group and collaborators' accepted papers at #ACL2025NLP #ACL2025 (Main, Findings, Demo, Workshops) and #CoNLL2025! 🎉📄

See you in Vienna next week! We're looking forward to connecting and sharing ideas with the #NLP community! 🌍

Looking forward to seeing many of you at our next edition and do say hi if you’re attending #ACL2025 in Vienna! 3/3

We hope you also enjoyed the tutorial and the poster session! 2/3

Thank you to everyone who came along to our @cardiffnlp.bsky.social #NLP workshop, it was a pleasure to have you all!
A big thank you to our amazing speakers, and panelists!
1/3

Thank you for visiting us!

#CardiffNLPWorkshop off to a flying start with talks from Jennifer Foster and Marianna Apidianaki @cardiffnlp.bsky.social

4th Cardiff NLP Workshop Day 1 MONDAY, JULY 14 10:00–10:15 Welcome reception + Registration Abacws ground floor (registration) and room 0.34 (reception and coffee/pastries) 10:15–10:30 Opening session Cardiff NLP team, Lecture theatre 0.01 10:30–11:30 Jennifer Foster Worth the effort? Large Language Models for claim verification, syntactic analysis and taxonomy creation 11:30–12:30 Marianna Apidianaki Semantic and Perceptual Knowledge in Large Language Models' Embedding Space: Insights, Challenges and Perspectives Lunch break 12:30-13:30 13:30–14:30 Marzieh Fadaee Rethinking Evaluation for the Future of Language Models Coffee break 14:30-15:00 15:00–16:00 Tutorial (Dialz: A Python Toolkit for Steering Vectors) Where: 1.34/1.39 Windows lab Presented by Zara Siddique (Cardiff NLP) 16:00–17:30 Poster presentation + refreshments All participants. Where: Abacws main hall

4th Cardiff NLP Summer Workshop TUESDAY, JULY 15 Day 2 (Schedule) Late registration open 9:00 and during reception (Abacws ground floor) 9:15–9:30 Reception and late registration Abacws main hall 9:30–10:30 Christos Christodoulopoulos With great power... My journey in Responsible AI Coffee break 10:30-11:00 11:00–12:00 Alexander Shvets Challenges in Curating Data for Building a Multilingual LLM 12:00–13:00 Edoardo M. Ponti A blueprint for adaptive and tokenizer-free foundation models Lunch break 13:00-14:00 14:00–15:00 Interdisciplinary NLP Session Speakers: Dawn Knight: "Applying Corpus Linguistics and NLP in a Minoritised Language Context" Christian Arnold: "Research between NLP and Political Science: The Triggerpoint Project as a Use Case" Verity Bennett: "Multi-agency safeguarding, evaluation research and NLP" Coffee break 15:00-15:30 15:30–15:40 Sponsor talk: Short overview of the Digital Transformation Innovation Institute (DTII) and Hartree Centre Cardiff Hub Presented by Yulia Cherdantseva 15:40–16:30 Panel on "Interdisciplinarity and NLP" Panel members: Carla Pérez Almendros (Cardiff NLP) Christian Arnold (School of Government, University of Birmingham) Christos Christodoulopoulos (Information Commissioner's Office) Moderated by Steven Schockaert 16:30–16:40 Closing remarks Cardiff NLP team

The 4th Cardiff #NLProc Summer Workshop starts tomorrow! We'll have two full days of insightful talks, hands-on sessions, and networking.
📅 Check out the full schedule here: cardiffnlpworkshop.org/schedule

The Cardiff #NLP Workshop kicks off this Monday (14 July)!
Full schedule www.cardiffnlpworkshop.org/schedule
✨ Talks, a tutorial, poster session and networking opportunities, an interdisciplinary session, and a panel discussion✨
Confirmations were sent. Looking forward to welcoming you to Cardiff!

A Lyon pour suivre quelques cours de Taigi et parler de métaphores 😋

Research Associate at Cardiff University Explore an exciting academic career as a Research Associate. Don't miss out on other academic jobs. Click to apply and explore more opportunities.

I am looking for a postdoctoral research associate to work on (LLM-based and neurosymbolic) reasoning for story understanding, as part of the EPSRC-funded ReStoRe project. Details: www.jobs.ac.uk/job/DNS820/r... (deadline 21st July)
@cardiffnlp.bsky.social

Consider sending your work on multilinguality/low-resource/culturally grounded #NLP to our @meltworkshop.bsky.social at @colmweb.org‬ 👇🏻
🗓️ Deadline: 30 June
We’re also looking for reviewers, please fill out this form if you're interested: docs.google.com/forms/d/e/1F...

Hi #NLP BlueSky, I'm looking for 2 emergency reviewers for this ARR round (multilinguality/LLM evaluation). Please reach out if you can help. Thank you!

Don’t forget to register for our Cardiff #NLP Workshop **today**! 🗓️
Fill out the registration form here: forms.gle/EQDfwXv487tS...
✨Registration is free! ✨ We have:
✨ Amazing speakers and an interdisciplinary research session.✨
💻A Tutorial
📍A poster session
☕🍪Networking, coffee, and Welsh cakes.

🚨 Call for Submissions – MELT Workshop @colmweb.org 2025 🌍

We invite papers on regionally grounded, culturally aware language technologies.

🛠️ Two tracks:
— Workshop Track
— Conference Track

Details below ⬇️ #MeltWorkshop2025

🚨#ACL2025 position paper on key challenges in creating resources for mid- to low-resource lgges emphasising that data in #NLP is not merely a collection of tokens, but is rooted in cultural and social contexts.
Based on 81 responses from researchers working on >70lgges
📄 arxiv.org/abs/2410.12691 1/🧵

Don't forget to register for our Cardiff #NLP Hackathon, organised by @zarasiddique.bsky.social, before June 1st!
Register here: forms.gle/5k3joqckp6eW...

Pleased to say this has been accepted to ACL System Demos :)

Come to my hackathon! Last one was super fun I promise

Announcing... Cardiff NLP's second hackathon! Join us on the 10th and 11th of June for two days of code 💻, pizza 🍕and networking. Open to all! Register your interest here: forms.gle/dG6F2Pbuy4H7...

Multi-level Matching Network for Multimodal Entity Linking Multimodal entity linking (MEL) aims to link ambiguous mentions within multimodal contexts to corresponding entities in a multimodal knowledge base. Most existing approaches to MEL are based on repres...

#KDD2025
- Multi-level Matching Network for Multimodal Entity Linking arxiv.org/abs/2412.10440 Zhiwei Hu, Víctor Gutiérrez-Basulto, Ru Li, Jeff Z. Pan. 4/4

Building Better: Avoiding Pitfalls in Developing Language Resources when Data is Scarce Language is a symbolic capital that affects people's lives in many ways (Bourdieu, 1977, 1991). It is a powerful tool that accounts for identities, cultures, traditions, and societies in general. Henc...

#ACL2025 (Main)
- Building Better: Avoiding Pitfalls in Developing Language Resources when Data is Scarce arxiv.org/abs/2410.12691

- BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages arxiv.org/abs/2502.11926. (See also arxiv.org/abs/2503.07269)

3/

AUTALIC: A Dataset for Anti-AUTistic Ableist Language In Context As our understanding of autism and ableism continues to increase, so does our understanding of ableist language towards autistic people. Such language poses a significant challenge in NLP research due...

#ACL2025 (Main)

- AUTALIC: A Dataset for Anti-AUTistic Ableist Language In Context arxiv.org/abs/2410.16520

- Benchmarking Systematic Relational Reasoning with Large Language and Reasoning Models arxiv.org/abs/2503.23487
2/

Check out our group's accepted papers at #ACL2025 and #KDD2025. Preprints available for the following papers 👇 1/

🚨 NEW PAPER ALERT 🚨

Dialz: A Python Toolkit for Steering Vectors

ArXiv: arxiv.org/abs/2505.06262
Docs: cardiffnlp.github.io/dialz/
Repo: github.com/cardiffnlp/d...

A Python package to help you create, apply and visualise steering vectors for anything you want - from sycophancy to bias.