Janet Liu

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

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.

Unsure which presentations to attend at #ACL2025? 🛎️🗣️

🕺🏼swing by our poster in Hall 4/5 on Wednesday, July 30 at 11:00 to chat with @florian-eichin.com and I to find out the answers to these questions

🛎️ bonus: to see the full poster 🫣🧩

#ACL2025 #NLProc

Some recommendations for #ACL2025 👇
(join me and @janetlauyeung.bsky.social to talk about discourse generalization and probing!)

Headed to ACL? MaiNLP & our most recent work will be there too👥📄
Come see what we’ve been working on!

💡 more findings, error analysis, and in-depth discussion are in our paper:

📄 arxiv.org/abs/2503.10515
🤖 github.com/mainlp/disco...

meet and chat with us at our poster in Vienna 🇦🇹 at #ACL2025NLP

🕰️ 11:00-12:30, Wednesday, July 30
📍 Hall 4/5 Session 12: IP-Posters

Layer-wise probe performance by languages. Mean accuracy over five runs.

🔍 finding 3: discourse representations are best aligned across languages in the intermediate layers

Mean accuracy over five runs of the Aya-23-35B-probe trained and tested on various partitions of DISRPT.

🌍 finding 2: our probes generalize across languages and language families

Mean accuracy over five runs of the probing classifiers trained on the entire DISRPT and full attention representations. The reference system DisCoDisCo achieved a mean accuracy of 47.9% (the red dashed line).

📌 finding 1: model size alone does not lead to discourse probing success; instead, multilingual training, dataset composition, and language-specific factors play significant roles

🧪 for 23 SOTA LLMs, we use a probing approach to test whether their representations encode information relevant to discourse relation classification on DISRPT 2023, which covers 13 languages, four frameworks, 26 datasets, and various genres, domains, and modalities

Examples of the core discourse relation CONDITION (Bunt and Prasad, 2016) annotated in different frameworks and languages using different labels.

the proposed unified label set (see definitions and examples in the appendix of the paper)

❓problem: discourse relations are central to NLU, but current work is primarily fragmented across frameworks & languages

🔧 solution: we proposed a unified label set of 17 relations across 4 discourse frameworks. This lets us compare model behavior across corpora, languages, and annotation schemes

to appear at ACL2025

🦙 how well do LLMs encode discourse knowledge? does that generalize across languages?

🛎️ in our #ACL2025 paper, we uncover fascinating trends about multilingual discourse representations!

joint work w/ @florian-eichin.com @barbaraplank.bsky.social @mhedderich.bsky.social

📄 arxiv.org/abs/2503.10515

I'm looking for a reviewer for a paper on measuring syntactic productivity (lots of maths!) due a week from now. Please shoot me an email if you could review!

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!

@munichcenterml.bsky.social
@slds-lmu.bsky.social
@munichcenterml.bsky.social
@berd-nfdi.bsky.social

my amazing co-organizers: @assenmacher.bsky.social Jacob Beck, @barbaraplank.bsky.social , @stephnie.bsky.social, Frauke Kreuter, Gina Walejko

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

🛎️ 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

BlackboxNLP, the leading workshop on interpretability and analysis of language models, will be co-located with EMNLP 2025 in Suzhou this November! 📆

This edition will feature a new shared task on circuits/causal variable localization in LMs, details here: blackboxnlp.github.io/2025/task

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

Logo for MIB: A Mechanistic Interpretability Benchmark

Lots of progress in mech interp (MI) lately! But how can we measure when new mech interp methods yield real improvements over prior work?

We propose 😎 𝗠𝗜𝗕: a 𝗠echanistic 𝗜nterpretability 𝗕enchmark!

The hand-drawn sign from three years ago.

🎉MaiNLP is turning 3 today!🎂🥳 We’ve grown a lot since @barbaraplank.bsky.social started this group with nothing but three aspiring researches and a hand-drawn sign on the door. Huge thanks to all the amazing people who have joined or visited us since. Here’s to many more years of exciting research!🚀

🎯

this 🎯🎯

Welcome back, astronauts! A LOT has changed since you left... #DailyShow #NASA #Trump #DesiLydic TikTok video by The Daily Show

www.tiktok.com/@thedailysho...

All the ACL chapters are here now: @aaclmeeting.bsky.social @emnlpmeeting.bsky.social @eaclmeeting.bsky.social @naaclmeeting.bsky.social #NLProc

“Seeing the Big through the Small”: Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations? Beiduo Chen, Xinpeng Wang, Siyao Peng, Robert Litschko, Anna Korhonen, Barbara Plank. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

Beiduo Chen from @MaiNLPlab: ⁉️Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?

📍poster session 6, Nov 13 (Wed) 10:30-12:00
📜 aclanthology.org/2024.finding...

Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models Philipp Mondorf, Barbara Plank. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Philipp Mondorf from @MaiNLPlab: 🧝🏻Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models

📍poster session 6, Nov 13 (Wed) 10:30-12:00
📜 aclanthology.org/2024.emnlp-m...

2⃣ eRST: A Signaled Graph Theory of Discourse Relations and Organization (CL journal)

📍oral session 6, Nov 13 (Wed) 10:30-12:00
📜 direct.mit.edu/coli/article...

GDTB: Genre Diverse Data for English Shallow Discourse Parsing across Modalities, Text Types, and Domains Yang Janet Liu, Tatsuya Aoyama, Wesley Scivetti, Yilun Zhu, Shabnam Behzad, Lauren Elizabeth Levine, Jessica Lin, Devika Tiwari, Amir Zeldes. Proceedings of the 2024 Conference on Empirical Methods in...

1⃣ GDTB: Genre Diverse Data for English Shallow Discourse Parsing across Modalities, Text Types, and Domains

📍poster session 3, Nov 12 (Tue) 14:00-15:30
📜 aclanthology.org/2024.emnlp-m...
🖥️github.com/gucorpling/gum…

🌴 in Miami for #EMNLP2024 this week 🌴

1st conference {of the year | with @MaiNLP | as a postdoc}:
> 2 papers to present, SPF 50 on standby
> with my new labmates (who are doing cool work🤩)
> reunite with @GUCompLing folks 🙌
> come say hi and catch up 🕺🏻

see 🧵