🚀 MALLM: a plug-and-play framework for multi-agent debate.
✅ Accepted as #EMNLP2025 Demo
🔧 144+ configurations out of the box
🔎 Find the best multi-agent setup for your research
📄 Preprint: https://t.co/DrPFdYoUZ6
🧪 Demo: https://t.co/g3Qru5uDLj
A very engaging poster session at #EMNLP2024 this morning! The room was packed!
Find the full paper that @jpwahle and @ruasterry presented here:
📄 https://t.co/DqnzdxBn3c
It's not just what you say but how you say it. Paraphrase types can potentially improve models' task performance without further training. If you are @EMNLP, stop by to check out our poster.
Are you interested in LLM sensitivity, model robustness, and paraphrases?
Stop by at our #EMNLP paper today, Wednesday at 10:30 in the Jasmine hall!
Paper Title: Paraphrase Types Elicit Prompt Engineering Capabilities
Session 06, Interpretability and Analysis of Models for NLP 3
🔗 Read the full paper: https://t.co/fyKqK4vT3p
📑 Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges
Explore recent advances in text generation since 2017, focusing on five core sub-tasks and highlighting key research gaps.
🔗 Read the paper: https://t.co/97IMuVnS7O
🧵 1/8
A great way to provide, in an incredibly easy way, all citation information about your paper independently where you upload it. Great work by @lbkaesberg and the authors.
🚀 Introducing CiteAssist: A System for Automated Preprint Citation and BibTeX Generation! 📄✨
📅 Published Date: 03.07.2024
🔗 Try it now: https://t.co/n0Zsttxzbo
🔗 Read the paper: https://t.co/wC2RFOQXbp
📚 Accepted at SDProc @ ACL2024
🧵 (1/9)
Wir suchen eine Assistenz für unser Team an der @uniGoettingen und @subugoe! Wir bieten ein modernes Arbeitsumfeld mit viel Gestaltungsspielraum, flache Hierarchien und eine unbefristete Anstellung im öffentlichen Dienst. Jetzt bis 28.4. bewerben: https://t.co/Fd7GgYv9SQ
The Influence Between NLP and Other Fields
This paper aims to quantify the degree of influence between 23 fields of study and NLP.
The cross-field engagement of NLP has declined from 0.58 in 1980 to 0.31 in 2022.
What does this mean? It means that NLP papers are drawing proportionally less from other fields over time and engaging less with outside literature.
The study also finds that NLP citations are dominated by CS which accounts for over 80% of citations with emphasis on AI, ML, and information retrieval.
Overall, NLP is growing more insular -- higher growth of intra-field citation and a decline in multidisciplinary works.
Quote from the paper: "Contributions from non-CS fields like linguistics and sociology have diminished over time."
Quote from the blog: "We see that linguistics, mathematics, psychology, and sociology are the most cited non-CS fields by NLP. They are also the non-CS fields that cite NLP the most, albeit the order for mathematics and psychology is swapped."
Lots of other great insights in the paper. The authors also wrote a nice blog post on it. Check it out below.
We are excited about the kick-off of our Programming for Data Scientists: Python course with 130+ participants @uniGoettingen and @subugoe. It's still possible to join this and all our other courses (all materials also online). Check out https://t.co/PSuLhyuOpv for details.
I want to take the opportunity to thank some wonderful people for the exciting collaborations of the past couple months: @ruasterry@SaifMMohammad@BelaGipp, and Mohamed Abdalla!
EMNLP papers below 👇🏻
Great talk with @MeuschkeN from @GippLab . Many examples of how we can use current technology to improve our teaching practices. The takeaways and exercises from @alxecker also brought together a fruitful discussion. @uniGoettingen#AI#NLP
Spannender Austausch über #KI in der #Hochschullehre heute an der @uniGoettingen. Es hat mir viel Spaß gemacht, einen Input-Vortrag zu den Potenzialen von KI halten zu dürfen. Vielen Dank an alle Teilnehmer für die inspirierende Diskussion. Folien: https://t.co/KF063wH5WF
Thanks to the outstanding audience of this session and the brilliant questions.
If you want to catch up just stop me anywhere you see me at the conference or shoot me an email!
Many of the coauthors are at ACL too @ruasterry@SaifMMohammad @KarnFort1 @fanny_dcl@AlmostAisling
📢 Oral Pres in Session 1: Ethics & NLP.
📌 The Elephant in the Room: Analyzing the Presence of Big Tech in NLP Research
🔍 Quantify and characterize the growing industry presence in the NLP community - highlighting the need for transparency. 🌐
🔗https://t.co/oiVVKWewXE
I‘m looking forward to present our work at #ACL2023NLP on the role of Big Tech in #NLProc research.
Join the talk tomorrow on Monday, July 10th at 11:45 Pier 2&3!
I‘m looking forward to present our work at #ACL2023NLP on the role of Big Tech in #NLProc research.
Join the talk tomorrow on Monday, July 10th at 11:45 Pier 2&3!
What’s in the News? Towards Identification of Bias by Commission, Omission, and Source Selection (COSS) - A. Zhukova, T. L. Ruas, F. Hamborg, K. Donnay, and B. Gipp (https://t.co/zpmDoG9UIz)
TEIMMA: The First Content Reuse Annotator for Text, Images, and Math - A. Satpute, A. Greiner-Petter, M. Schubotz, N. Meuschke, A. Aizawa, O. Teschke, and B. Gipp (https://t.co/QzeilSSmjA)