NLPnorth retweeted
📢 #NLProc I'm hiring! 2x PhD students (apply by Nov 22) & postdoc (Nov 15). These positions are part of a large project on the problem of attribution for LLM outputs to the original data sources, on which LLMs were trained.
Job links on my website (in the bio)
/1
NLPnorth retweeted
I'm in Bangkok for #ACL2024NLP 🇹🇭 Looking forward to present our work "Dissecting Biases in Relation Extraction: A Cross-dataset analysis on People's Gender and Origin" @genderbiasnlp
Joint work w/ @marcostranisci @PereLluisHC @RNavigli
📄aclanthology.org/2024.gebnlp…
#NLProc
1/2
NLPnorth retweeted
I'm in Mexico City for #NAACL2024 🇲🇽 I'll present a poster at @_starsem on Friday morning where we introduce a tool for quantitative analysis of RE systems. Stop by if you're interested!
#NLProc @NLPnorth @MaiNLPlab
Replying to @CisLmu
📝What’s wrong with your model? A Quantitative Analysis of Relation Classification
🔎We provide a tool for quantitative analysis of RC models
👥@EliBassignana @robvanderg @barbara_plank
🔗github.com/mainlp/RC-analysi…
📁*SEM - Long
NLPnorth retweeted
Excited to work with @SashaMTL on this! A new position paper discussing what we even mean by "LLM", and some of the common claims/assumptions about them:
- LLMs are robust
- LLMs are SOTA
- Scale is all you need
- LLMs exhibit emergent properties
New position paper just dropped! 💣
In it, @annargrs take a critical look at LLMs, from their definition to their functionality and influence on the field of NLP.
arxiv.org/abs/2308.07120
A brief thread of our arguments 🧵:
NLPnorth retweeted
Obtaining calibrated confidence scores from #LLMs is hard, especially for black-box models. So, can we maybe predict them directly from the generated text?🤔Internship work at @parameterlab with @framart1 @oodgnas @hwaran_lee @coallaoh! arxiv.org/abs/2403.05973 🧵[1/6]
NLPnorth retweeted
📢We are excited to announce our paper "
Deep Learning-based Computational Job Market Analysis: A Survey on Skill Extraction and Classification from Job Postings" has been accepted to #EACL2024 at the @nlp4hr workshop.
In cooperation with @NLPnorth and @MaiNLPlab.
NLPnorth retweeted
Interested in how to apply #ConformalPrediction to #NLG? Check out our work on "Non-Exchangeable Conformal Language Generation with Nearest Neighbors" with @chryssaZrv @andre_t_martins accepted to #EACL2024 Findings! [1/4] 🧵 browse.arxiv.org/abs/2402.00…
NLPnorth retweeted
Check out our work on non-exchangeable conformal risk control and hopefully see you in Vienna 🙂
I'm excited to share that our paper "Non-Exchangeable Conformal Risk Control" (with @chryssaZrv @dnnslmr @andre_t_martins) has been accepted at #ICLR2024. Check out the updated version of the paper: arxiv.org/abs/2310.01262. See you in Vienna!
NLPnorth retweeted
Rob from ITU is visiting @MaiNLPlab @CisLmu, great to have him in Munich
NLPnorth retweeted
Celebrating tomorrow’s research leaders: 18 excellent young researchers receive a Villum Young Investigator grant to build their first research group. @VILLUMFONDEN
NLPnorth retweeted
📢 #NLProc job alert: I'm looking for a #compling postdoc to work on an ambitious generalization benchmark, in collaboration with @tallinzen. Could start as early as April. If you'd like to spend a year in beautiful Copenhagen 🇩🇰 - please reach out! ([email protected])
RT appreciated🙏
NLPnorth retweeted
📣Call for emergency reviewers📣
We got more submissions than expected and are looking for emergency reviewers for the EACL SRW.
If you're available and interested, please send your Openreview ID to:
[email protected]
🙏
#NLProc
NLPnorth retweeted
Super excited to share my @AmazonScience internship work about bootstrapping task-oriented dialogue data for #LLMs through 𝘴𝘦𝘭𝘧-𝘵𝘢𝘭𝘬! 💬🗨️ Work together with @elmanmansimov, @linkaixi, Justin Sun, Xibin Gao & Yi Zhang. #nlproc arxiv.org/pdf/2401.05033.pdf [1/7] 🧵
NLPnorth retweeted
Introducing... the Subspace Chronicles (ft. @robvanderg, @barbara_plank, @iatitov)—a riveting tale of linguistic information emerging, shifting and disentangling across LM training! Coming to an #EMNLP2023 near you! 📜⏳
📑personads.me/x/emnlp-2023-pa…
📽personads.me/x/emnlp-2023-vi…
NLPnorth retweeted
🙏🥳 Super grateful and honoured to receive this @VILLUMFONDEN grant which will finance my three year postdoc at @ITUkbh including a two year visit at @MilaNLProc working with @dirk_hovy
Looking forward to starting this project 🙌
Meet our excellent Villum International Postdocs 2023: @EliBassignana, @HENSE03, @monicasandgaard, @maria_scheel_, Mengting Li, Mahak Pancholi, Mie Thorborg Pedersen & Ersilia Guarini. tinyurl.com/3eycmvta #science #womeninscience
NLPnorth retweeted
You work in #NLProc and are interested in submitting your work on uncertainty or related topics? Consider submitting to the First Workshop on Uncertainty-Aware Natural Language Processing, co-located with #EACL2024 in Malta! Check our website and CfP here: uncertainlp.github.io/
NLPnorth retweeted
Interested in uncertainty in NLP and NLG systems?
We are organising the first workshop on uncertainty-aware NLP, co-located with #EACL2024 in Malta!
Consider submitting and/or attending!
More info (like awesome speakers and a broad range of topics) at uncertainlp.github.io/.
NLPnorth retweeted
Off to Copenhagen now, looking forward to our workshop organized by our amazing @NLPnorth PhD students Elisa, Max, Mike nlpnorth.github.io/content/m…
NLPnorth retweeted
This morning I had the honor to give the opening keynote @ #CLEF2023 @clef_initiative speaking about "Human-centric Natural Language Processing" - Work by @MaiNLPlab members & collaborators. Thanks to the organizer for the kind invitation #NLProc #Thessaloniki @MaiNLPlab @CisLmu
#clef2023 @barbara_plank keynote on human-centric NLP and the shift from models to data, evaluation and people with a strong message “NLP that is not human-centric could be exclusive and even harmful” @clef_initiative
NLPnorth retweeted
Excited to announce the second result of my collaboration with @TurkuNLP "Silver Syntax Pre-training for Cross-Domain Relation Extraction" w/ Filip Ginter, Sampo Pyysalo, @robvanderg, @barbara_plank
Accepted in Findings of #ACL2023 #ACL2023NLP 🇨🇦
📄arxiv.org/pdf/2305.11016.pdf
🧵1/3
Replying to @CisLmu
📝Silver Syntax Pre-training for Cross-Domain Relation Extraction
👥@EliBassignana, Filip Ginter, Sampo Pyysalo, @robvanderg, @barbara_plank
🔗arxiv.org/abs/2305.11016
📁Findings - Short































