CoRNLP
Computational Rhetoric and Natural Language Processing
We develop computational linguistic models for discourse and argumentation and conduct research on assessing the linguistic capabilities of LLMs.
____________________________________________________________
Our latest activities:
06/25: Textbook chapter forthcoming
Nette will be featured with a chapter on 'Argumentation & Natural Language Processing' in the new Routledge Handbook of Argumentation Theory, edited by Scott Aikin, John Casey and Katharina Stevens, forthcoming spring 2026.
06/25: Talk at the "Bridging the Gap in Political Communication Online through Technology?" Workshop, Bielefeld
Zlata and Artur present the DeLab moderation bot for online deliberation in the panel on 'Automated Interventions into Social Media Discourses'.
06/25: Talk at RIS Zagreb
Presenting our work on 'Rhetorical effects of LLM-generated impersonations', co-authered by Steffen Herbold, Alexander Trautsch, Zlata Kikteva and Annette Hautli-Janisz at RIS 2025.
06/25: Invited talk at the Annual Meeting of the Marianne-Plehn-Program
Nette is delighted to be invited to yet another venue co-organized by the Studienstiftung des Deutschen Volkes, this time in Herrsching am Ammersee. The title of her talk is “GenAI 2: humans 0 — From writing essays to mimicking politicians — GPT outperforms humans” - looking forward!
06/25: Talk in Ringvorlesung
The Ringvorlesung 'Künstliche Intelligenz - zwischen Hype und Realität' on 5 June features two talks on argumentation: Henning Wachsmuth (Leibniz University Hannover) on 'Fantastic LLMs and How to Tame Them' and Nette on 'Can LLMs really argue well?'.
05/25: Three papers accepted to ArgMin @ ACL2025
A set of papers with a range of authors got accepted to the 2025 edition of the Argument Mining workshop. '"The Facts Speak for Themselves": Fallacy Classification with GPT' (Erisa Bytyqi and Nette), 'DEBARGVIS: An Interactive Visualisation Tool for Exploring
Argumentative Dynamics in Debate' (Martin Gruber, Zlata Kikteva, Ignaz Rutter, Annette Hautli-Janisz) and 'Toward Reasonable Parrots: Why Large Language Models Should Argue with Us by Design', a position paper led by Elena Musi, with a list of authors, including Nette, see here.
05/25: Main paper at ACL2025
The paper 'Mining Complex Patterns of Argumentative Reasoning in Natural Language Dialogue' that Zlata co-authored has been accepted to main ACL! The work was led by Ramon Ruiz-Dolz in collaboration with John Lawrence, both from the University of Dundee.
04/25: Paper at LaTeCH-CLfL 2025
Coming out of the Konstanz EXC project, Steffen Frenzel and Nette have a paper at LaTeCH-CLfL 2025 (NAACL 2025 workshop) on 'Identifying Small Talk in Natural Conversations'.
04/25: Invited talk at PhiLang
Nette is giving a plenary talk at PhiLang 2025 with the title "What Do LLMs Know About Language?"
04/25: Invited talk in Tübingen
Nette is invited to give a talk at the Institutskolloquium of the Seminar für Allgemeine Rhetorik, Universität Tübingen, with the title "Die Fakten sprechen für sich: Argumentative und rhetorische Fähigkeiten von LLMs".
04/25: New paper, on Urdu/Hindi lexical semantics, for a change
Going back to Nette's roots, the first paper on Urdu/Hindi after 10 years has come out, in Dick Crouch's Festschrift 'Semantics at the Crossroads', entitled "Revisting the Light Verb Jungle: How Good is GPT at Hacking Away?", with co-authors Erisa Bytyqi, Pranshu Gupta and Miriam Butt. Congratulations Dick!
04/25: DeLab @ Schloss Herrenhausen
Zlata and Artur present the latest developments in the DeLab project at the Final Symposium "AI and the society of the future", organized by the VolkswagenStiftung.
03/25: Nette @ Lorentz Center, Leiden, NL
Nette is invited to join the seminar on 'Hybrid Argumentation and Responsible AI' in Leiden, Netherlands, for a week of brainstorming on how to set up HA systems.
03/25: DGfS-CL activities at DGfS 2025 coming up!
The CL tutorial this year will be held by Dominik Schlechtweg, IMS, Uni Stuttgart, on Lexical Semantic Change Detection - the poster session is spread across two days!
02/25: Nette at NOVA Institute in Lisbon
Happy to join the Workshop on the Concept of 'Argument' and talk about 'Argumentation & NLP'!
02/25: Artur Romazanov joins CoRNLP
Artur joins CoRNLP for DeLab and will wrap up the bot - welcome Artur!
12/24: COLING2025 paper
The paper "Looking at the Unseen: Effective Sampling of Non-Related Propositions for Argument Mining" by Ramon Ruiz-Dolz, Debela Gemechu, Zlata Kikteva and Chris Reed accepted at COLING 2025 - way to go!
10/24: Two papers accepted @ EMNLP2024 workshops
Wassiliki and Ingrid Espinoza were successful with "So, are you a different person today? - Analyzing Bias in Questions during Parole Hearings", which has been accepted to the ICon2024 workshop (Social Influence in Conversations) and ''Automated Anonymization of Parole Hearing Transcripts'' (Abed El Rahman Itani, Wassiliki and Nette) was accepted to the NLLP (Natural Legal Language Processing) workshop.
09/24: Computational Linguistics Fall School 2024
Two weeks of intense CL input for 35 international students - it's a great crowd!
09/24: Zlata @ SIGDial in Kyoto
Zlata presents our paper 'Question Type Prediction in Natural Debate' at SIGDial 2024!
08/24: Nette teaching 'NLP: From Language to Information'
Eight days of teaching the most interdisciplinary group I ever had at the Sommerakademie of the Max Weber-Program (Studienstiftung des deutschen Volkes) in Ljubljana!
07/24: ECAI workshop paper accepted
A new strand of research coming out of CoRNLP, namely on ithe automatic identification of misinformation, with collaborators Bruna Paz Schmid and Steve Oswald (Université de Fribourg, Switzerland) and accepted at the ECAI 2024 workshop on 'Countering Disinformation with Artificial Intelligence'.
07/24: SIGDIAL paper accepted
Looking forward to presenting our paper 'Question Type Prediction in Natural Debate' at SIGDIAL in Kyoto in September. Authors are Zlata Kikteva, Alex Trautsch, Steffen Herbold and Nette Hautli-Janisz.
07/24: New work on LLM capabilities!
We're happy to announce our latest piece on assessing the capabilities of LLMs, this time on how good LLMs can impersonate politicians and other figures. Authors are Steffen Herbold, Alexander Trautsch, Zlata Kikteva and Nette Hautli-Janisz.
06/24: PIZ Fachbeirat (Bayerisches Staatsministerium für Unterricht und Kultus)
From September 2024 onwards, Nette will be member of the "Profilschule für Informatik und Zukunftstechnologien" (PIZ) Fachbeirat which promotes computer science and technology in Bavarian secondary schools - way to go!
06/24: Nette gives keynote at ARGAGE 2024
Looking forward to giving one of the keynotes at ARGAGE 2024 in Fribourg, CH, plus a presentation with Thierry Hermann, Université de Neuchâtel.
05/24: Nette @ OSSA2024 in Windsor, CA
Excited to talk about a paper by Erisa Bytyqi and me on 'The Facts Speak For Themselves': Fallacy Detection with GPT at OSSA 2024 in Canada. Also commenting on Oxana Pimenova's paper on argument continuity.
05/24: Nette invited to Liverpool Symposium
I'm very happy to give a talk on 'GAI 1 – humans 0: Assessing the structure of automatically generated persuasive essays' at the “GenAI, Language, and Society” symposium organised by Rudi Palmieri and Elena Musi at the University of Liverpool.
05/24: Program out for DELITE at LREC-Coling 2024!
Looking forward to an exciting mix of papers on current work on deliberation technology in Torino at DELITE2024!
05/24: Nette invited to INDIGO Digital Tag
Happy to meet up with industry representatives to talk about 'Large Language Models & natural language' at the INDIGO Digital Tag 2024.
05/24: Nette in ZEIT Sprachen
Happy to contribute to an article in ZEIT Sprachen on assessing the capabilities of Large Language Models.
See here for more updates on conference trips, accepted papers etc.
____________________________________________________________________________________________________________________________