Independent Research Group

Trustworthy
Human Language Technologies

Dr. Ivan Habernal
Group leader

Welcome to my official research website!

Group

TrustHLT Group

Trustworthy Human Language Technologies (TrustHLT) is an Independent Research Group hosted at the Department of Computer Science at the Technical University of Darmstadt, Germany, appointed in January 2021.

Dr. Ivan Habernal

Head of the group

My current research areas include legal argument mining, privacy-preserving NLP, and explainable and trustworthy models. My research track spans argument mining and computational argumentation, crowdsourcing, large-scale corpora, serious games, sentiment and sarcasm on social media, and semantic web.

Download my academic CV

Doctoral candidates

Lena Held, MSc.

Ph.D. student

Lena is currently exploring the research area of computational argumentation in the legal domain.

Timour Igamberdiev, M.A.

Ph.D. student

Timour's current research areas include privacy-preserving NLP, differential privacy in graph neural networks, and privacy-preserving semantic representations of language.

Sebastian Ochs, MSc.

Ph.D. student

Sebastian' research areas include privacy-preserving NLP with a focus on text rewriting with provable guarantees.

Master and Bachelor students

Martin Kerscher

Master student

Martin's thesis compares privacy-preserving inference methods, applying them to NLP tasks and developing software to connect PyTorch with techniques like homomorphic encryption and garbled circuits.

Marius Büttner

Master student

Marius investigates question answering in the German legal domain. His thesis explores how well existing models can support laymen to receive a first legal aid, based on a created dataset of questions in lay language to answers in legalese.

Alumni

Christopher Weiss

2023, Master thesis

Chris's thesis focused on finding best practices on how to optimally adapt the concept of differential privacy in NLP environments while putting the needs of the end-users first and considering perceptional biases to make differential privacy more accessible.

Lijie Hu

2022, Research internship

Lijie is a second-year PhD student in Computer Science at King Abdullah University of Science and Technology. Her research interests cover machine learning algorithm on Explainable AI (XAI), Differential Privacy, and Differential Private Natural Language Models. She is also interested in Machine Unlearning, and other security issues in data field.

Sudarshan Sivakumar

2022, Research internship Sudarshan is an undergraduate student in Computer Science from India. His primary research interest is in creating language processing tools that are socially and ethically responsible. He is working on a research project related to differentially private synthetic data generation.

Nina Mouhammad

2022, Master thesis

Nina wrote her thesis on privacy-preserving techniques for crowdsourcing sensitive text data.

Johanna Frenz

2022, Bachelor thesis

Johanna studied computer science at TU Darmstadt. In her bachelor thesis, she compiled an easily accessible legal benchmark dataset to enable evaluating models on a variety of legal NLP tasks.

Lars Wolf

2022, Master thesis

Lars, student of information systems technologies, cooperated with political scientists to identify indoctrination in German history textbooks through entity emotion analysis.

Ying Yin

2022, Master thesis

Ying explored privacy-preserving transformer models in the legal domain. Her thesis combined large-scale pre-training with differential privacy and evaluates the trade-off between privacy-preserving capability and downstream performance.

Sarah Lettmann

2021, Master thesis

Sarah explored ethical argumentation in scientific literature. Her thesis focused on controversial technologies and automatic mining of absent, shifting, and evolving ethical arguments.

Manuel Senge

2021, Bachelor thesis

Manuel was a bachelor's student at the TU Darmstadt focusing on machine learning. He wrote his thesis on the effectiveness and impact on accuracy using differential privacy in NLP.

Lena Held

2021, Master thesis

Lena studied computer science at TU Darmstadt. In her thesis she dealt with differentially private language representation learning.

Daniel Faber

2021, Master thesis

Daniel explored legal argument mining in court decisions with focus on ECHR decisions and their art of argumentation in regard to their importance level.

Fabian Kaiser, M.Sc.

2020-2021, TU Darmstadt research Scholarship

Fabian's research area included legal argument mining, expert annotations, and low-resource and few-shot transfer learning for annotation recommendations.

Positions

Open positions

TrustHLT has currently the following open positions

March 2023

Student Research Assistants (Project PrivaLingo)

We're looking for several student research assistants (HiWi) for a research project related to privacy-preserving natural language processing and neural machine translation. Read the full job posting (PDF).

News

News

May 10, 2023

Two papers accepted to ACL Findings

TrustHLT has two papers on privacy-preserving NLP accepted to the Findings of the Association for Computational Linguistics: ACL 2023, co-authored by Timour Igamberdiev, Cleo Matzken, and Steffen Eger.

May 6, 2023

Tutorial on Private NLP at EACL

We held a tutorial on Privacy-Preserving Natural Language Processing at the The 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023) in Dubrovin, Croatia. The slides are available at GitHub.

March 15, 2023

Invited talk at Aalto University

It was my pleasure to give an invited talk about Privacy-Preserving Natural Language Processing at the Aalto University in Helsinki. The video recording should soon become available.

March 1, 2023

Tutorial accepted at EACL

The 17th Conference of the European Chapter of the Association for Computational Linguistics will host our tutorial on Privacy-Preserving Natural Langauge Processing in Dubrovnik, in May 2023.

October 7, 2022

Paper accepted at EMNLP

Our new paper "One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks" by Manuel Senge, Timour Igamberdiev, and myself will be presented at the 2022 Conference on Empirical Methods in Natural Language Processing in Abu Dhabi in December this year.

October 1, 2022

Interim Professorship at LMU

In this winter term, I'm holding a W2 interim professorship at the The Center for Information and Language Processing at the Ludwig-Maximilians-Universität München.

August 17, 2022

Paper accepted at COLING

Our new paper "DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting" by Timour Igamberdiev (TrustHLT), Thomas Arnold (UKP), and myself will be presented at the 29th International Conference on Computational Linguistics in Korea in October this year.

August 2, 2022

Member of hessian.AI

I'm now a member of hessian.AI — The Hessian Center for Artificial Intelligence. Its mission is to drive research excellence, education, practice and leadership in AI to foster economic growth and improve the human condition.

April 5, 2022

Paper accepted at LREC

Our paper on protecting privacy of models trained on graph data using differential privacy has been accepted at the International Conference on Language Resources and Evaluation (LREC) to be held in Marseille, France in June.

February 24, 2022

Paper accepted at ACL

Our paper analyzing trickiness of differentially-private text representation learning will be presented at the 60th Annual Meeting of the Association for Computational Linguistics, the world's top conference for natural language processing.

October 21, 2021

Invited lecture at University of Maine

I'm giving an invited lecture at the School of Computing and Information Science, University of Maine with a bit provoking title "If all you have is a hammer, everything looks like a nail: SGD-DP in privacy-preserving NLP" (download slides).

September 1, 2021

Paper accepted at EMNLP

Our paper on the pitfalls of differential privacy in NLP will be presented at the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), one of the world's leading conferences for natural language processing.

June 10, 2021

Guest lecture on "AI and Criminal Justice"

I'll be giving a guest lecture at the International Summer School on "AI and Criminal Justice" in Rome on July 12th. This summer school is a great opportunity to acquire an interdisciplinary and in-depth knowledge in the cutting-edge area of AI and criminal justice.

April 19, 2021

Hosting mentoring session at EACL

I'm happy to volunteer as a mentor for early career researchers at this year's Conference of the European Chapter of the Association for Computational Linguistics (EACL). One of the topics on the agenda is "How to survive grad school", I'm very much looking forward to some fresh perspectives!

March 17, 2021

Invited talk on privacy-preserving NLP

Thanks to Yang Gao for invited me over to Royal Holloway, University of London to give an invited talk on privacy-preserving NLP, a joint work with Timour Igamberdiev. Slides available here.

March 3, 2021

Area Chair for argument mining at EMNLP

Happy to join the Area Chairs for sentiment analysis and argument mining at this year's Conference on Empirical Methods in Natural Language Processing (EMNLP).

January 14, 2021

Serving as Area Chair for *SEM 2021

I'll be serving as Area Chair ("Semantics for NLP Applications") at the upcoming *SEM conference, which is co-located with ACL'21 in Thailand this year.

December 27, 2020

Standing reviewer of Computational Linguistics

I happily accepted an invitation to join the standing reviewer board of Computational Linguistics, the "longest-running publication devoted exclusively to the computational and mathematical properties of language".

May 21, 2020

Serving as Tutorial Chair for EACL 2021

Together with Isabelle Augenstein and tutorial chairs for NAACL, EMNLP, and ACL-IJCNLP, we are preparing the next year's selection of tutorials to be presented either virtually or in-person.

0 H-index
0 Citations
23 ACL-Anthology papers
6 Journals + book chapters

Publications

Selected publications

For the complete list, see my Google Scholar profile.

Igamberdiev, T., Habernal, I. (2023). DP-BART for Privatized Text Rewriting under Local Differential Privacy. arXiv.
Bongard, L., Held, L., Habernal, I. (2022). The Legal Argument Reasoning Task in Civil Procedure. Proceedings of the 2022 Natural Legal Language Processing workshop.
Ying, Y., Habernal, I. (2022). Privacy-Preserving Models for Legal Natural Language Processing. Proceedings of the 2022 Natural Legal Language Processing workshop.
Senge, M., Igamberdiev, T., Habernal, I. (2022). One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing.
Igamberdiev, T., Arnold, T., Habernal, I. (2022). DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting. Proceedings of the 29th International Conference on Computational Linguistics (COLING 2022), 2927–2933. Gyeongju, Republic of Korea, International Committee on Computational Linguistics.
Habernal, I., Faber, D., Recchia, N., Bretthauer, N., Gurevych, I., Spiecker genannt Döhmann, I., Burchard, C. (2022). Mining Legal Arguments in Court Decisions. arXiv preprint.
Igamberdiev, T., Habernal, I. (2022). Privacy-Preserving Graph Convolutional Networks for Text Classification. Proceedings of the 13th Language Resources and Evaluation Conference (LREC 2022), 338‑350. Marseille, France: European Language Resources Association.
Habernal, I. (2022). How reparametrization trick broke differentially-private text representation leaning. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), 771-777. Dublin, Ireland: Association for Computational Linguistics.
Habernal, I. (2021). When differential privacy meets NLP: The devil is in the detail. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 1522–1528. Punta Cana, Dominican Republic: Association for Computational Linguistics.
Glockner, M., Habernal, I., & Gurevych, I. (2020). Why do you think that? Exploring Faithful Sentence-Level Rationales Without Supervision. Findings of the Association for Computational Linguistics: EMNLP 2020, 1080–1095.
Habernal, I., Wachsmuth, H., Gurevych, I., & Stein, B. (2018). The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 1930–1940.
Habernal, I., Wachsmuth, H., Gurevych, I., & Stein, B. (2018). Before Name-calling: Dynamics and Triggers of Ad Hominem Fallacies in Web Argumentation. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 386–396.
Habernal, I., Wachsmuth, H., Gurevych, I., & Stein, B. (2018). SemEval-2018 Task 12: The Argument Reasoning Comprehension Task. Proceedings of The 12th International Workshop on Semantic Evaluation, 763–772.
Habernal, I., Pauli, P., & Gurevych, I. (2018). Adapting Serious Game for Fallacious Argumentation to German: Pitfalls, Insights, and Best Practices. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 3329–3335.
Daxenberger, J., Eger, S., Habernal, I., Stab, C., & Gurevych, I. (2017). What is the Essence of a Claim? Cross-Domain Claim Identification. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2045–2056.
Habernal, I., & Gurevych, I. (2017). Argumentation Mining in User-Generated Web Discourse. Computational Linguistics, 43(1), 125–179.
Habernal, I., & Gurevych, I. (2016). What makes a convincing argument? Empirical analysis and detecting attributes of convincingness in Web argumentation. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 1214–1223.
Habernal, I., & Gurevych, I. (2016). Which argument is more convincing? Analyzing and predicting convincingness of Web arguments using bidirectional LSTM. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 1589–1599.
Habernal, I., & Gurevych, I. (2015). Exploiting Debate Portals for Semi-Supervised Argumentation Mining in User-Generated Web Discourse. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2127–2137.

Projects

Research projects

ECALP

Empirical Computational Argumentation in Legal Proceedings

Funded by the DFG

In this interdisciplinary collaboration, we look into argumentation in the verdicts of the European Court of Human Rights. What makes a verdict of a high importance? Is it the facts? Is it the argumentation pattern? Is it the judges? Or is it something left between the lines?

We combine legal expertise with state-of-the-art NLP.

We collaborate with expert legal researchers Prof. Dr. Christoph Burchard from Geothe University Frankfurt.

logo logo
Prof. Dr. Christoph Burchard, LL.M. (NYU)
Prof. Dr. Christoph Burchard, LL.M. (NYU)
Goethe Universität Frankfurt am Main

Chair for German, European and International Criminal Law and Procedure, Comparative Law and Legal Theory

PrivaLingo

Truly Privacy-Preserving Machine Translation

Funded by the HMdIS

What does is mean for machine translation models to protect privacy? What personal information do neural machine translation systems leak? Can we protect users during inference?

In this research project supported by the Hessisches Ministerium des Innern und für Sport we tackle privacy-preserving natural language processing in the context of machine translation, including differential privacy and cryptographical tools.

logo
ATHENE SenPai Text

Protecting Privacy and Sensitive Information in Texts

Funded by ATHENE

The goal of this project is to explore Natural Language Processing methods that can dynamically identify and obfuscate sensitive information in texts, with a focus on implicit attributes, for example, their ethnic background, income range, or personality traits. These methods will help to preserve the privacy of all individuals - both authors and other persons mentioned in the text. Further, we go beyond specific text sources, like social media, and aim to develop robust and highly adaptable methods that can generalize across domains and registers.

We collaborate with the UKP Lab led by Prof. Dr. Iryna Gurevych.

logo
Prof. Dr. Iryna Gurevych
Prof. Dr. Iryna Gurevych
Technische Universität Darmstadt

Director of the Ubiquitous Knowledge Processing (UKP) Lab

Teaching

Teaching

Summer Term 2023

Deep Learning for Natural Language Processing

Slides are freely available at GitHub under open licences.

Recorded lectures are in a YouTube playlist.

Anonymous feedback from students
  • "The content quality, language quality and the concept (usage of discord, github and YouTube) is outstanding."
  • "Very well executed online lectures in both quality of content but also of production. [...] The lecture is very well structured."
  • "Ivan Habernal hat eine ausgezeichnete Art, Vorlesungen zu halten: motivierend und wohlwollend; selbst Kompliziertes wirkt einfach(er) - vielen Dank!"
  • "Einfach erklärt, ermutigend, wenn es kompliziert wird und man weiß, dass man immer fragen kann. Es kommen hilfreiche Antworten und die VL sind didaktisch einfach richtig gut."
  • "The quality of the recorded lectures are very high, everything is explained very clearly and makes me want to investigate this topic further."

Contact

Contact

Send me an e-mail

Address

Trustworthy Human Language Technologies,
Department of Computer Science, S202-A309
Technical University of Darmstadt,
Hochschulstraße 10, 64289 Darmstadt

Email Address

ivan (dot) habernal (at) tu-darmstadt.de

Twitter

Follow me on Twitter

LinkedIn

Follow me on LinkedIn