NLP @ Uni Vienna
@ViennaNLP
Followers
159
Following
7
Media
12
Statuses
44
Digital Philology group led by Prof. Ben Roth Data Mining and Machine Learning research group @csunivie @univienna #nlpunivie #NLProc
Vienna, Austria
Joined February 2022
PhD (funded) in Explainable NLP, supervised by Benjamin Roth, Univ. of Vienna. Possible topics: * Personalized explanations for LLMs and AI agents * Training data-based explanations * Evaluation and usability of explainable AI Apply until 24 June 2025:
jobs.univie.ac.at
University assistant predoctoral
0
0
0
[4/4] Als Mitglied der Wiener Forschungscommunity werde ich daran mitwirken. Denn ich lebe und forsche gerne in Wien! Benjamin Roth, Professur für Digitale Textwissenschaften #IchForscheGernInWien #TopForschungWien #Wien
0
0
0
[3/4] Hier in Wien wurden die Bedingungen für Wissenschaft und Forschung in den letzten Jahren immer besser. Ich bin überzeugt davon, dass das auch so bleibt und dass die entsprechenden Anstrengungen und Unterstützungen in Zukunft noch stärker ausfallen werden.
1
0
0
[2/4] Unser Anspruch ist State-of-the-Art Forschung zu Sprachmodellen und statistischer Sprachverarbeitung. Für die Forschung sind die Zeiten in vielen Ländern schwieriger und finsterer geworden.
1
0
0
[1/4] Nach Massachusetts und München bin ich 2020 in Wien angekommen und konnte dort dank des WWTF die Vienna Research Group "Knowledge-Infused Deep Learning for Natural Language Processing" aufbauen.
1
0
0
0
4
12
Check out this EMNLP 2024 paper from @MaiNLPlab and our lab, and chat with @anasedova in Miami! 🌴
🚨How well can LLMs perform under lexical ambiguity? Excited to present our #EMNLP2024 paper, where we analyze large language models' performance and self-consistency when prompted with ambiguous entities. A joint work with the awesome @MaiNLPlab! (1/5)🧵
0
0
2
Will art soon be automated?🖼️🤖 A discussion between the philosopher Violetta Waibel and our group lead Ben Roth at the University of Vienna (available only in German) https://t.co/l6Y1mSvI04
rudolphina.univie.ac.at
Auf KI basierende Bild- und Textgeneratoren produzieren digitale Werke von verblüffender Qualität, die manche Menschen beunruhigen: Wird Kunst bald automatisiert? Rudolphina sucht mit der Philosophin...
0
0
4
- Weak supervision of natural language processing models, - Multimodal and multilingual deep learning.
1
0
1
Possible research topics are: - Analysis, explainability and interpretability of large language models, - Linguistic capabilities of large language models, - Extraction of structured information from text, linking knowledge graphs and language,
1
0
1
The research group Data Mining and Machine Learning at the University of Vienna is looking for a Postdoctoral Researcher in Natural Language Processing. For more details see: https://t.co/JLX27tHiiH
jobs.univie.ac.at
Postdoctoral Researcher in Natural Language Processing
1
12
18
1 extended abstract for the BabyLM challenge: "CogMemLM: Human-Like Memory Mechanisms Improve Performance and Cognitive Plausibility of LLMs" @LukasThoma7 @ivonne_weyers @stefan_it_ Erion Çano, Jutta L. Mueller & Ben Roth
0
1
3
1 TACL publication: “Cross-functional Analysis of Generalization in Behavioral Learning” @pedrohluzaraujo & Ben Roth https://t.co/14vStTxJY4
1
1
4
“Seeing through the mess: evolutionary dynamics of lexical polysemy” Andreas Baumann, @andst_link & Ben Roth
1
0
4
2 main conference papers: “ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision" @anasedova & Ben Roth https://t.co/lsNDdqkLYD
1
0
2
We will be at @emnlpmeeting with 4 papers! Congratulations to everybody involved! 🎉 #EMNLP2023
1
0
7
When looking forward to #EMNLP2023 today with everyone, I also have something to share about past events 😊 two weeks ago, I had a fantastic time at #ECMLPKDD 2023 conference presenting our recent work on gradient-based outlier removal as both an oral presentation and a poster!
0
2
10
Last week, Ben and @andst_link, @anasedova and @vassilikiKou had an invited tutorial about weak supervision at @Aalborg_uni in Copenhagen 🇩🇰 Big thanks to @johannesbjerva for the invitation!
0
4
9
Super happy to share that we won the Theme Paper Award at #ACL2023NLP! 🥳 Especially congrats to the project lead, the brain and muscles of the operation, @cs_dawei, for his determination and hard work! Unbelievable 😀
Theme Paper Award: 📢S2: Theme: Reality Check (Oral) 📌Weaker Than You Think: A Critical Look at Weakly Supervised Learning 🔎 Thoroughly analysis of diverse NLP datasets/tasks to ascertain when and why weakly supervised approaches work 🔗 https://t.co/GemBhp3JZ8 🧵(4/4)
1
2
26
🚀Our paper "ACTC: Active Threshold Calibration for Cold-Start Knowledge Graph Completion" will be at today’s #ACL2023nlp poster session, 11:00-12:30, Frontenac Ballroom and Queen’s Quay!
1
1
4