II Encontro Luso-Galego de Processamento de Linguagem Natural em Santiago de Compostela, Galiza #CISUC #NLProc #SantiagoDeCompostela
📢🚨We are hiring!
Come join our group as a PhD or postdoc on the newly founded Carlsberg project with Rob van der Goot!
Applications are open: candidate.hr-manager.net/ApplicationI...
More info about the project: www.carlsbergfondet.dk/en/what-we-h...
#NLProc @itu.dk
See you at #EACL2026 in Rabat 🕌!
#LLMs #AI #NLP #NLProc #MachineUnlearning #AIPrivacy #AISafety #ExplainableAI #ResponsibleAI @cs-tudarmstadt.bsky.social
And tomorrow Fri. 3/13—I will give a talk in the late afternoon panel called...
"Is agentic philology an oxymoron? Some thoughts on error, control, and disciplinary definition"
...covering some recent work on Latin post-OCR correction and its implications for philology #nlproc #digiclass
#TBT #NLProc 'Predicting News Headline Popularity' by Lamprinidis, Hardt, @dirkhovy.bsky.social (2018) shows neural networks perform similar to Logistic Regression in prediction.
Multimodal LLMs can read text in images, but why do they often perform worse than when the same text is given as tokens? Our work studies the modality gap of models perceiving text as pixels and shows how to close it.
📄 arxiv.org/abs/2603.09095
🧵👇 #NLProc #LLM #ComputerVision
Did you know...
...that the guide lists things to do in Rabat *other* than attending EACL ;-) 2026.eacl.org/participants...
(2 of 2)
#EACL2026 @eaclmeeting.bsky.social #research #conferences #NLProc #CL #NLP #language
This week in our reading group @taniseceron.bsky.social presented “Linear Representations of Political Perspective Emerge in LLMs”.
A study investigating how political biases are encoded in internal representations. 🧠
Paper: arxiv.org/abs/2503.02080
#NLProc
#NLProc #UKPLab #NLP #LLMs #AI
#MultiDocumentReasoning #ZeroShotLearning #Evaluation #OpenScience @cs-tudarmstadt.bsky.social
Call for Papers: LM Playschool (LMP 2026) – Co-located with EMNLP 2026!
Can #LLMs learn, adapt, and improve through situated, game-based interaction?
See lm-playschool.github.io
#GenAI #NLProc #HRI #ELLISforEurope #AI #ML
#UKPLab #NLP #NLProc #AI #PeerReview
#AIforScience #ScientificPublishing #NoveltyDetection #Evaluation #OpenScience @cs-tudarmstadt.bsky.social
CFP: If you're working on the evaluation of generative multimodal models, please consider submitting your work to the EvalMG workshop @ SIGIR 2026, Melbourne, Australia.
sigir2026.org/en-AU/pages/... #NLProc #SIGIR2026 @acmsigir.bsky.social
Think of the challenges for an NLP system — sorry, an AI — to understand what’s imperative / contractual, and what’s humor.
#linguistics #NLP #nlproc #AI
WOAH is coming back for its 10th edition at EMNLP 2026 in Budapest! 🎊
For this important anniversary, we invite authors to critically reflect on our achievements as a community and adjust the aim going forward.
Stay tuned, more updates coming soon!
#EMNLP2026 #WOAH2026 #NLProc
#UKPLab #NLP #NLProc #InformationRetrieval #DenseRetrieval #MultiHop #FactChecking #QuestionAnswering #RAG @cs-tudarmstadt.bsky.social
Join us on 8 June in #Sheffield to hear about our #PhD students’ #AI and #ML #speech and #NLProc research!
#Keynotes from @egrefen.bsky.social (Google DeepMind) & Prof Wenwu Wang (@uniofsurrey.bsky.social).
Find out more and #register (by 31 May) at slt-cdt.sheffield.ac.uk/annual-confe...
#MemoryModay #NLProc 'Comparing Bayesian Models of Annotation' by Paun et al. dives into corpus annotation, evaluating six models' predictiveness and accuracy. Essential for navigating annotators and item difficulties.
🚨#AmericasNLP26 shared task🚨
Do you know what‘s shown in this image?
Our new ST challenges participants to develop systems that generate culturally grounded captions for images depicting things from Indigenous cultures, written in the Indigenous languages themselves.
#NLProc
#TBT #NLProc 'Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting' by @dirkhovy.bsky.social and Christoph Purschke (2018) highlights how social class and background impact technology performance. #TechInclusion
New article on the evaluation of task-oriented chatbots: nejlt.ep.liu.se/article/view...
#NLProc #AI
Our annual #conference is on 8 June. Join us in #Sheffield to hear about our #PhD students' #AI and #ML #speech and #NLProc research!
Non-Sheffield PhD student? Present your #speech / #NLProc work! Submit an abstract by 24 Apr!
Check our website for info: slt-cdt.sheffield.ac.uk/annual-confe...
If anybody wants to be my direct colleague: we have an open vacancy for a full-stack research software engineer in our "Team Text" at the KNAW Humanities Cluster (Amsterdam): vacatures.knaw.nl/job/Amsterdam-Full-Stack...
Great […]
In the LLM era, author responses seem much longer, with more arguments and justification. I felt this in my own pool. Are meta-reviews drifting toward weighing extended defenses and vague complaints about reviewers instead of the technical core?
#ACL2026 #NLProc
ACL 2026 SRW Direct Submsision Deadline: March 18, 2026 (AoE) The image depicts a beautiful sunrise over San Diego.
📣 ACL 2026 SRW Direct Submissions are open!
🗓️ Deadline: March 18, 2026 (AoE)
Submit your work via OpenReview: openreview.net/group?id=acl...
We can’t wait to see your contributions—good luck! 💪✨
#ACL2026 #SRW #NLProc
#UKPLab #TUDarmstadt #NLP #NLProc #AIinEducation #AcademicWriting #Feedback #HigherEducation #LLMentor #CSDeptDarmstadt #hessianAI
📣 The 11th Workshop on Natural User-generated Text #W-NUT will be held at #EMNLP2026!
We welcome original research on noisy data, informal texts, and natural variation in language use 🗣️ and host the MultiLexNorm2 task 📊
More info at:
🌐 noisy-text.github.io/2026/
@emnlpmeeting.bsky.social #NLProc
Great wrap-up for #EVALITA2026! 🔥
Glad to have helped organize this edition and to see many interesting discussions!
Great response to our task Cruciverb-IT (with Ciaccio C., @gsarti.com, Dell’Orletta F., @malvinanissim.bsky.social)!
Thanks to all co-organizers and @ailc-nlp.bsky.social! #NLProc
Here's another model for today's meeting...
Ancient Greek LatinCy lg model, same workflow/infrastructure at the Latin models, obv. different texts/data!
Experimental, beta—but on HF now: huggingface.co/latincy/grc_...
#digiclass #nlproc
Good news! #NLProc methods cannot detect deception! @aswathyve.bsky.social's paper got accepted to the Computational Linguistics Journal.
"What if Deception Cannot be Detected? A Cross-Linguistic Study on the Limits of Deception Detection from Text"
Preprint arxiv.org/abs/2505.13147
Still working on that #NLProc paper? Time to submit! We welcome work on foundational research, #Swiss-centric language resources, and real-world NLP applications submitted via #OpenReview:
openreview.net/group?id=Swi...
(2/3)