Lightnews — Scholar-powered news

Reposted by Barbara Plank

Verena Blaschke @verenablaschke.bsky.social · Aug 7

Check out the...
- talk on Mon Aug 18, 15:50–16:10
- preprint: arxiv.org/abs/2506.02894
- suppl. material: github.com/mainlp/betth...

Joint work w/ Miriam Winkler & @barbaraplank.bsky.social from @mainlp.bsky.social, and Constantin Förster & Gabriele Wenger-Glemser from Bayerischer Rundfunk!

A Multi-Dialectal Dataset for German Dialect ASR and Dialect-to-Standard Speech Translation

Although Germany has a diverse landscape of dialects, they are underrepresented in current automatic speech recognition (ASR) research. To enable studies of how robust models are towards dialectal var...

arxiv.org

1 5

Reposted by Barbara Plank

Verena Blaschke @verenablaschke.bsky.social · Aug 7

At #Interspeech2025 I'm going to present Betthupferl, a dataset for German dialect ASR & dialect-to-standard speech translation! We analyze differences between dialectal & Standard German transcriptions, benchmark ASR models, and examine shortcomings of current ASR models & evaluation metrics.

Piper title ("A multi-dialectal dataset for German dialect ASR and dialect-to-standard speech translation") and a map of the German state Bavaria showing where the Franconian, Bavarian, and Alemannic dialect groups are spoken

1 4 16

Barbara Plank @barbaraplank.bsky.social · Jul 30

So well-deserved, and such a great, supportive talk, especially kudos for including her students in the Lifetime Achievement Award! Thank you, Kathy ☀️

ACL @aclmeeting.bsky.social · Jul 30

🕊️ Lifetime Achievement Award at #ACL2025NLP

A standing ovation for Prof. Kathy McKeown, recipient of the ACL 2025 Lifetime Achievement Award! 🌟

1 11

Reposted by Barbara Plank

ACL @aclmeeting.bsky.social · Jul 28

This year ACL inaugurates the ✨🎓ACL Computational Linguistics Doctoral Dissertation Award! 🎓✨
Instrumental for launching this inaugural prize is the Computational Linguistics Journal @CompLingJournal, with support of the ACL Exec.

#CLJournal #ComputationalLinguistics
#ACL2025NLP @CompLingJournal

1 3 9

Reposted by Barbara Plank

ACL @aclmeeting.bsky.social · Jul 29

1/3
📣 Social event at Day2 at #ACL2025NLP 🇦🇹

Get ready to experience the vibrant culture of Vienna at the ACL 2025 Social Event this Tuesday night at the ACV! 🎉

We've got an unforgettable evening planned!

Willkommen | TU Orchester, Wien

bit.ly

1 1 3

Reposted by Barbara Plank

ACL @aclmeeting.bsky.social · Jul 28

Sewon Min 🏆 presenting the essence of her thesis: Rethinking Data Use in Large Language Models -- It won the first ACL Computational Linguistics Doctoral Dissertation Award 🎓✨
#ACL2025NLP #CLJournal @complingjournal.bsky.social

2 15

Reposted by Barbara Plank

ACL @aclmeeting.bsky.social · Jul 27

Get ready, ACL 2025 attendees! 🎉 The Opening Ceremony kicks off Monday, July 28 at 9 AM CEST in Hall A of the Austria Center Vienna. Don't miss it! 📍 #ACL2025NLP #Vienna

1 14

Barbara Plank @barbaraplank.bsky.social · Jul 4

Thanks for the invitation to the Freiburg Institute for Advanced Studies (FRIAS) to give this year's Hermann-Paul-Center Lecture lnkd.in/d_wUeDfY

I enjoyed the visit, the great audience, and the stay in this lovely city.
Thank you
#blackforest #freiburg #breisgau

2 10

Barbara Plank @barbaraplank.bsky.social · Jun 20

Thanks again to the ACL 2024 chairs for this invitation! (Andre Martins, Vivek Srikumar, Lun-Wei Ku, Claire Gardent)

Special thanks to the European Research Council (ERC) and also Munich Center for Machine Learning for research funding and support

@erc.europa.eu @munichcenterml.bsky.social

5

Barbara Plank @barbaraplank.bsky.social · Jun 20

My ACL 2024 keynote talk on "Are LLMs Narrowing Our Horizon? Let’s Embrace Variation in NLP!" is online now:

underline.io/events/466/s...

2024.aclweb.org/program/keyn...

It was a huge honor to me to give last year's flagship-in-NLP-conference keynote in Bangkok 🇹🇭

Watch lectures from the best researchers.

On-demand video platform giving you access to lectures from conferences worldwide.

underline.io

1 3 19

Barbara Plank @barbaraplank.bsky.social · Jun 4

Do you speak Bavarian? Then please consider helping in a thesis research project👇

Verena Blaschke @verenablaschke.bsky.social · Jun 4

Dei Boarisch heard ned bei "Servus" und "Pfiade" auf? Dann suach ma genau Di!
Wir suachan Bairischsprecher:innen, de a kurze Umfrage über KI-generierds Boarisch für a Masterarbeit beantwortn mechadn.
Mid jeder Teilnahme bring ma den boarischn Dialekt a Stickal weida in de digitale Weyd!

Verena Blaschke @verenablaschke.bsky.social · May 30

Bavarian dialect speakers needed! Our MSc student Miriam wants to find out 1. how good/bad LLM-generated "Bavarian" is, and 2. whether dialect speakers agree with each other on this. The survey takes <5 min: survey.ifkw.lmu.de/dialquali25/ Thank you for sharing/participating!

3 3

Barbara Plank @barbaraplank.bsky.social · May 28

MaiNLP/CIS participates in #stadradeln 🚴☀️

Florian Eichin @florian-eichin.com · May 28

Proposing "kilometers cycled in 2 weeks" as a new success metric for research groups 🚴‍♀️📊🥇
@mainlp.bsky.social #stadtradeln

2

Barbara Plank @barbaraplank.bsky.social · May 20

Thanks to everyone who worked on this update!

Barbara Plank @barbaraplank.bsky.social · May 20

-- These recommendations were further clarified in March 2025, and now read as follows:
www.aclweb.org/adminwiki/in...

ACL Conference Awards Policy - Admin Wiki

www.aclweb.org

1

Barbara Plank @barbaraplank.bsky.social · May 20

Just submitted your EMNLP paper? Congrats!

An update on paper awards: the ACL award policy has been updated - in future the non-publicized awards won't have that info any longer in its title. Read more below:

🏆

ACL Conference Awards Policy - Admin Wiki

www.aclweb.org

1 2

Barbara Plank @barbaraplank.bsky.social · May 16

Are you working with LLMs and survey data or generally care about high-quality data and reliable evaluation? Then this might be for you!

Very excited to share the news about our upcoming COLM 2025 workshop #NLPOR

Thanks for helping spread the word ☺️

Janet Liu @janetlauyeung.bsky.social · May 16

🛎️ Excited to announce the 1st Workshop on Bridging NLP and Public Opinion Research at COLM 2025, Oct 10th in Montreal 🇨🇦

As LLMs reshape public discourse and research, collaboration between NLP and Public Opinion Research (POR) is more vital than ever #NLPOR Submit by June 23📄

🔗 tinyurl.com/nlpor25

Welcome to the First Workshop on Bridging NLP and Public Opinion Research, co-located with COLM 2025, October 10, 2025, Montreal, Canada.

3 13

Barbara Plank @barbaraplank.bsky.social · May 14

LeWiDi: Shared task on Learning With Disagreement
Website: le-wi-di.github.io

We'd like to invite researchers in disagreement & variation to participate in the third edition of the LeWidi shared tasks held in conjunction with the NLPerspectives workshop at EMNLP 2025

nlperspectives.di.unito.it

LeWiDi 2025 - 3rd edition

This is the page of the Learning With Disagreements tasks

le-wi-di.github.io

3 11

Reposted by Barbara Plank

Verena Blaschke @verenablaschke.bsky.social · Apr 29

On my way to #NAACL2025 where I'll give a keynote at the noisy text workshop (WNUT), presenting some of the challenges & methods for dialect NLP + also discussing dialect speakers' perspectives!

🗨️ Beyond “noisy” text: How (and why) to process dialect data
🗓️ Saturday, May 3, 9:30–10:30

1 7 27

Reposted by Barbara Plank

MaiNLP lab, LMU Munich @mainlp.bsky.social · Apr 24

Reunion in Singapore!🇸🇬 @barbaraplank.bsky.social, @xinpeng.bsky.social, who's currently on a research stay at NYU, and Chengzhi are presenting their work at @iclr-conf.bsky.social

2 2 19

Barbara Plank @barbaraplank.bsky.social · Apr 23

💬 Find us today at Poster Session 1, happening this morning right after the keynote talk (poster #531)
@xinpeng.bsky.social

Barbara Plank @barbaraplank.bsky.social · Apr 15

Upcoming ICLR 2025 paper: ✂️ Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation

We propose a surgical & flexible approach to mitigate false refusal in LLMs with minimal effect on performance and inference cost

led by @xinpeng.bsky.social (1/2)

1 4

Barbara Plank @barbaraplank.bsky.social · Apr 23

😍 MaiNLP 3rd anniversary

MaiNLP lab, LMU Munich @mainlp.bsky.social · Apr 23

Party time! 🛎️🎉 We had a cozy barbecue by the Isar river to celebrate MaiNLP’s 3rd anniversary — here are some impressions! 🎂

a barbecue with grill cheese and skewers

the Isar river with swans and ducks on it

5

Barbara Plank @barbaraplank.bsky.social · Apr 15

More info:
verenablaschke.github.io
mainlp.github.io - @mainlp.bsky.social
@munichcenterml.bsky.social

Barbara Plank @barbaraplank.bsky.social · Apr 15

Are you attending NAACL 2025 and are you interested in low-resource languages and dialects?

Then don't miss our very own @verenablaschke.bsky.social's keynote talk at the WNUT 2025 workshop on May 3rd:

Beyond “noisy” text: How (and why) to process dialect data

🌐 ☀️
noisy-text.github.io/2025/

1 5 17

Barbara Plank @barbaraplank.bsky.social · Apr 15

Paper: arxiv.org/abs/2410.03415
Code: github.com/mainlp/False...

Joint work of @mainlp.bsky.social @xinpeng.bsky.social Chengzhi Hu with @paul-rottger.bsky.social

(2/2)

Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation

Training a language model to be both helpful and harmless requires careful calibration of refusal behaviours: Models should refuse to follow malicious instructions or give harmful advice (e.g."how do ...

arxiv.org

1

Barbara Plank @barbaraplank.bsky.social · Apr 15

Upcoming ICLR 2025 paper: ✂️ Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation

We propose a surgical & flexible approach to mitigate false refusal in LLMs with minimal effect on performance and inference cost

led by @xinpeng.bsky.social (1/2)

1 2 10