🎤 Dr. Valentina Pyatkin is a postdoctoral researcher at the Allen Institute for AI, contributing to OLMo and working on post-training for LLMs, and part-time affiliated with the ETH AI Center as part of the Swiss AI Initiative. @valentinapy.bsky.social
3/3
🎤 Prof. Dr. Alexandra Birch is Professor and Chair of Multilingual NLP at the University of Edinburgh and co-founder & Chief Scientist of Aveni.ai. Her research spans multilingual and multimodal NLP, ethics, and explainability, and she has led major EU projects including EuroLLM and GoURMET.
2/3
🗓️ SwissText 2026 keynote speakers announced & registration open!
We are delighted to welcome Prof. Dr. Alexandra Birch and Dr. Valentina Pyatkin as our keynote speakers.
📋 Register here: ema.uzh.ch/RHK4W
Early-bird rates available throughout April, with additional student discounts.
#NLProc
1/3
🔵 (Findings:) Elias Schuhmacher, Andrianos Michail, @nlopitz.bsky.social, @ricosennrich.bsky.social, @simon-clematide.bsky.social. Information Representation Fairness in Long-Document Embeddings: The Peculiar Interaction of Positional and Language Bias. arxiv.org/abs/2601.16934
7/7
🔵 Apertus: Democratizing Open and Compliant LLMs for Global Language Environments. arxiv.org/abs/2509.14233
6/7
🔵 @negarforoutan.bsky.social, Clara Meister, Debjit Paul, @joelniklaus.bsky.social, @sinaahmadi.bsky.social, Antoine Bosselut, @ricosennrich.bsky.social . Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization. arxiv.org/abs/2508.04796
5/7
🔵 Kevin Du, Clara Kümpel, @michellewastl.bsky.social, Alex Warstadt. It’s Not What You Say, It’s How You Say It: Evaluating LLM Responses to Expressions of Belief.
4/7
🔵 @zifanjiang.bsky.social, Youngjoon Jang, Liliane Momeni, Gül Varol, Sarah Ebling, Andrew Zisserman. Segment, Embed, and Align: A Universal Recipe for Aligning Subtitles to Signing. arxiv.org/abs/2512.08094
3/7
🔵 @michellewastl.bsky.social, @vamvas.bsky.social, @ricosennrich.bsky.social. SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents. arxiv.org/abs/2512.07538
2/7
🔵 Michelle Wastl, Jannis Vamvas, Rico Sennrich. SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents. 🔵 Zifan Jiang, Youngjoon Jang, Liliane Momeni, Gül Varol, Sarah Ebling, Andrew Zisserman. Segment, Embed, and Align: A Universal Recipe for Aligning Subtitles to Signing. 🔵 Kevin Du, Clara Kümpel, Michelle Wastl, Alex Warstadt. It’s Not What You Say, It’s How You Say It: Evaluating LLM Responses to Expressions of Belief. 🔵 Negar Foroutan, Clara Meister, Debjit Paul, Joel Niklaus, Sina Ahmadi, Antoine Bosselut, Rico Sennrich. Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization. 🔵 Apertus: Democratizing Open and Compliant LLMs for Global Language Environments. https://lnkd.in/eFTh-5m7 🔵 (Findings:) Elias Schuhmacher, Andrianos Michail, Juri Opitz, Rico Sennrich, Simon Clematide. Information Representation Fairness in Long-Document Embeddings: The Peculiar Interaction of Positional and Language Bias.
Looking forward to the ACL 2026 conference in San Diego, California!
Several accepted papers have involvement from our department:
1/7
My lab is recruiting one PhD student and one post-doctoral researcher for a start as soon as this Summer! Apply by April 1 / March 31 to be among first candidates considered.
jobs.uzh.ch/job-vacancie...
jobs.uzh.ch/job-vacancie...
📣 SwissText 2026 submission deadline has been extended until 24 March 2026 (AoE)!
Submit your work here: openreview.net/group?id=Swi...
Available tracks:
🔹 Scientific Track (archival research)
🔹 Corpus Track (focus on datasets)
🔹 Applied Track (real-world NLP applications)
🔹 Demonstration Track (live system demos)
Less than 3 weeks left – don't miss your chance to present in Zurich!
(3/3)
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)
📣 SwissText 2026 – 2nd Call for Papers!
🎯 Special theme: #ReproducibleNLP
📅 Deadline approaching: 17 March 2026
📍 Zurich, Switzerland, 10 June 2026
www.swisstext.org/call-for-pap...
(1/3)
Congratulations to @ricosennrich.bsky.social on his dual Professorship at our department and at the Department of Informatics.
www.ifi.uzh.ch/en/news/rico...
All submissions are handled via #OpenReview
openreview.net/group?id=Swi...
(4/4)
We welcome submissions across multiple tracks, including:
🔹 Scientific Track (archival research)
🔹 Corpus Track (focus on datasets)
🔹 Applied Track (real-world NLP applications)
🔹 Demonstration Track (live system demos)
(3/4)
Whether you’re advancing foundational #NLProc research, releasing new Swiss-centric #language resources, or showcasing cutting-edge NLP applications, we’d love to see your work!
(2/4)
📣 SwissText 2026 – Call for Papers is open!
🎯 Special theme: #ReproducibleNLP
📅 Submission deadline: 17 March 2026
📍 Zurich, Switzerland · 10 June 2026
www.swisstext.org/call-for-pap...
(1/4)
📣 We’re pleased to announce that our department will co-organize the 11th edition of the SwissText conference!
#SwissText2026 will take place on 10 June 2026, hosted at the University of Zurich (Campus Oerlikon). Save the date!
www.swisstext.org/current/
#NLProc #UZHai #CompLing
UZH Postdoc Team Award: When Spirituality Meets AI Group photo of the winning team consisting of Patrick Montjouridès, Anastassia Shaitarova, Fabian Winiger and Yingqiang Gao.
Congratulations to @shaitarova.bsky.social and Yingqiang Gao from our department, and to their collegues Fabian Winiger (Department of Theology) and Patrick Montjouridès (Institute of Education) for winning the UZH Postdoc Team Award!
www.news.uzh.ch/en/articles/...
Best Talk Award CPL 2025
Congratulations to our PhD student @cuiding.bsky.social for winning the Best Talk Award in the Computational Psycholinguistics Meeting 2025 (CPL 2025) lnkd.in/euTX89gi!
Take a look at how we challenge state-of-the-art NLP systems to recognize token-level semantic differences across languages with our new SwissGov-RSD dataset! @vamvas.bsky.social @ricosennrich.bsky.social
Paper: arxiv.org/pdf/2512.075...
Dataset: huggingface.co/datasets/Zur...
#NLProc
Iuliia Thorbecke wearing her Docotor's hat that was decorated by other PhD students of our department
Congratulations to Iuliia Thorbecke (Nigmatulina), who just passed the viva of her PhD on using contextual information to improve automatic speech recognition, for example using radar flight information to better transcribe air traffic communication.
Congratulations to Ann-Sophie Gnehm, who just passed the viva of her PhD on "Bridging the Gap between Job Ad Texts and Labor Market Ontologies with Adaptation and Contextualization Techniques". With many thanks to the external examiners @dirkhovy.bsky.social and Einat Minkov.
UZH group picture at #EMNLP2025!
If you're here, catch us for a chat!
🎉 Terminology Shared Task @WMT25: Paper Out 🎉
Highlights:
- sentence translation seems solvable, document translation is still challenging
- better systems benefit more from proper terminologies
- term-based metrics correlate poorly with general translation quality
www2.statmt.org/wmt25/pdf/20...
Upcoming panel discussion on Nov 12 moderated by our @tevuko.bsky.social: What Does and What Should AI Know?
More info and registration link: www.ema.uzh.ch/de/register/...
📢 Announcing the First Workshop on Multilingual and Multicultural Evaluation (MME) at #EACL2026 🇲🇦
MME focuses on resources, metrics & methodologies for evaluating multilingual systems! multilingual-multicultural-evaluation.github.io
📅 Workshop Mar 24–29, 2026
🗓️ Submit by Dec 19, 2025