🎉Very happy that this paper will appear at TACL. Time and time again, the topic pops up in my own and others works, and while teaching.

'Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practice'

#nlproc #machinelearning

arxiv.org/abs/2404.16958…

Thanks a lot for this post, I feel honored!! 🙏 ❤️ DH is a passion that comes up in my work again and again. Nowadays mostly triggered by great young researchers, who are passionate of DH. It's great to work with them, and to see how much NLP can bring DH further! #womoninDH

There'll also be a super interesting poster by Moritz Plenz from Heidelberg University NLP Group !

Creating Commonsense Reasoning Graphs for linking texts, making explicit the implicit links between texts.

How? Using good ol' graph algos and advanced neural text embeddings. #EACL2024 #nlproc

While I couldn’t join #EACL2024 , Heidelberg University NLP Group was represented, i.a. by Frederick Riemenschneider Frederick Riemenschneider, who won the SIGTYP Shared Task, jointly with Kevin Krahn. Their character-aware hierarchical LM perfectly addresses low-resource Historical Languages. Well done, Frederick 🥳 👏

Two years have passed since Russia initiated its full-scale war.

Each day Ukrainians show the world what bravery really means.

We stand with Ukraine, as you stand for the security of all of Europe.

I believe in Ukraine’s victory and that Russia can be defeated.

#SlavaUkraini

“We have made many mistakes, from just before Russia's invasion and throughout. The biggest mistake was holding back on types of military assistance out of fear,” says Kurt Volker in the interview with the Kyiv Independent.
kyivindependent.com/volker-a-lot-o…

🇺🇦

📢Thrilled to share that our work 'ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models' is accepted to #ICLR2024 ! ICLR 2024 #NLPro

- Paper: arxiv.org/abs/2311.07022
- Site: cyberiada.github.io/ViLMA
- Code: github.com/ilkerkesen/ViL…

Proud to see this collaborative work over many sites now coming out at #ICLR24 . 🥳

Pre-trained S3BERT multi-feature sentence embeddings are available at Hugging Face , happy to see that!

#nlproc #machinelearning

huggingface.co/brjezierski/S3…

Prompting LLMs as explainable metrics:

🏆Congrats to the winners of the shared task! Other approaches are also very interesting, lots of diversity and creativity and interesting insights.

#nlproc #machinelearning

I’m so excited that my upcoming AI science memoir book “The Worlds I See” is an Editor’s Pick on Amazon! 🤩 It’s coming out in 10 days on Nov 7, pre-order here: a.co/d/96QLfoE

Efficient and robust evaluation of factual consistency in text generation.

Models from our ACL 2023 paper are now available on Hugging Face

huggingface.co/juliussteen/De… #nlproc #machinelearning

I am building my future team at GESIS! If you want to work on NLP and Computational Social Science, in a very cool institute and in a great city, have a look at these calls (1 postdoc, 1 phd student) and get in touch for more info!

Have you ever wondered where the limits of NLP lie? Maybe it is worth doing a PostDoc on natural language _mis_understandings? If you are interested, check out the open position in my independent research group (IMS at University of Stuttgart): ims.uni-stuttgart.de/en/institute/n…

Thank you Melinda French Gates ! I’m grateful for the opportunity to work with you and #MomentofLiftBooks on this book. It’s a story of #AI , but at its heart it’s a human story that I hope to find resonance among many readers, especially young people around the world. 😍

Impressions from the ACL 2023: Check out the highlights and interviews with presenters by AI Coffee Break with Letitia! #ACL2023NLP #nlproc