Portrait of Daniel Braun

Prof. Dr. Daniel Braun

Professor of Computer Science

Natural Language Processing Group
Department of Mathematics and Computer Science
University of Marburg

daniel.braun@uni-marburg.de

Philipps-Universität Marburg
Hans-Meerwein-Strasse 6
35043 Marburg
Germany

About me

I am a Professor of Computer Science and head of the Natural Language Processing Group at the University of Marburg. My research is focused on the application of Artificial Intelligence (AI), Natural Language Processing (NLP), and Natural Language Generation (NLG) in knowledge-intensive processes and societally relevant contexts, e.g. in the legal domain. I hold a PhD in Informatics from the Technical University of Munich, where I worked as a research associate at the chair of Software Engineering for Business Information Systems.

YouTube Video Vorschaubild Die größte Lüge im Internet - Daniel Braun KlarText-Preisträger 2022

Research

Research Interests

Areas of interest include:

Current Projects

AGB-Check logo Rule-based German NLG 4 Health (SimpleNLG-DE 4 Health)

AGB-Check logo License-Aware Web Crawling for Open Search AI (LAW4OSAI)

More information
EasyGrader

AI-supported assessment of open question in higher education.

More information

Past Projects

AGB-Check logo AI-Supported Legal Review of Terms and Conditions to Strengthen Consumer Protection (AGB-Check)

More information
TSaaS logo Technology Scouting as a Service (TSaaS)

More information
VSS logo Vertical Social Software (VSS)

More information
A-SUM logo Meta Model based Natural Language Generation for Automatic Abstractive Text Summarization (A-SUM)

More information
SaToS logo Software Aided Analysis of Terms of Services (SaToS)

More information

Tools and Resources

AGB-DE A corpus and models for the automated legal assessment of clauses in German consumer contracts
(ISLRN 097-156-615-475-5)
Lowest Common Ancestor Extractor Open source A python library for the structured extraction of content from German and English Terms and Conditions
SimpleNLG-DE Open source Java library for surface realisation in German
MucLex

A German lexicon for surface realisation based on Wiktionary
(ISLRN 206-939-257-359-6)

NLU-Evaluation-Corpora English corpora for evaluating NLU services
(ISLRN 165-571-578-116-6)
NLU-Evaluation-Scripts Python scripts for the automatic evaluation of NLU services

Invited Talks

Publications

2024

Jin Xu, Mariët Theune, and Daniel Braun. 2024.

Leveraging Annotator Disagreement for Text Classification.

In Proceedings of the 7th International Conference on Natural Language and Speech Processing (ICNLSP 2024), pages 1--10, Trento. Association for Computational Linguistics. doi: 10.48550/arXiv.2409.17577.

Vitalii Fishchuk and Daniel Braun. 2024.

Robustness of generative AI detection: adversarial attacks on black-box neural text detectors.

In International Journal of Speech Technology. Springer. doi: 10.1007/s10772-024-10144-2.

Daniel Braun. 2024.

Daten und Datenkennzeichnung im Kontext der KI‑VO.

In Künstliche Intelligenz und Recht, pages 43--46, München. C.H. Beck.

Daniel Braun. 2024.

KI-gestützte Klauselkontrolle in allgemeinen Geschäftsbedingungen: Wie künstliche Intelligenz dabei helfen kann, den Verbraucherschutz beim Onlineshopping zu stärken.

In Professionalisierung im Verbraucherschutz. Jahrbuch Konsum & Verbraucherwissenschaften 2023/2024, pages 87--100, Düsseldorf. Verbraucherzentrale.

Daniel Braun. 2024.

Why "Artificial Intelligence" Should Not Be Regulated.

In Digit. Gov.: Res. Pract., New York, NY, USA. Association for Computing Machinery. doi: 10.1145/3696010.

Daniel Braun and Florian Matthes. 2024.

AGB-DE: A Corpus for the Automated Legal Assessment of Clauses in German Consumer Contracts.

In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10389--10405, Bangkok, Thailand. Association for Computational Linguistics. doi: 10.18653/v1/2024.acl-long.559.

Daniel Braun. 2024.

Teaching Natural Language Processing in Law School.

In Proceedings of the Sixth Workshop on Teaching NLP, pages 85--90, Bangkok, Thailand. Association for Computational Linguistics.

Leixin Zhang and Daniel Braun. 2024.

Twente-BMS-NLP at PerspectiveArg 2024: Combining Bi-Encoder and Cross-Encoder for Argument Retrieval.

In Proceedings of the 11th Workshop on Argument Mining (ArgMining 2024), pages 164--168, Bangkok, Thailand. Association for Computational Linguistics. doi: 10.18653/v1/2024.argmining-1.17.

Zhenqi Zhao, Mariët Theune, Sumit Srivastava, and Daniel Braun. 2024.

Exploring Lexical Alignment in a Price Bargain Chatbot.

In ACM Conversational User Interfaces 2024, New York, NY, USA. Association for Computing Machinery. CUI '24. doi: 10.1145/3640794.3665576.

2023

Vitalii Fishchuk and Daniel Braun. 2023.

Efficient Black-Box Adversarial Attacks on Neural Text Detectors.

In Proceedings of the 6th International Conference on Natural Language and Speech Processing (ICNLSP 2023), pages 78--83, Online. Association for Computational Linguistics. doi: 10.48550/arXiv.2311.01873.

Daniel Braun. 2023.

I Beg to Differ: How Disagreement is Handled in the Annotation of Legal Machine Learning Data Sets.

In Artificial Intelligence and Law. Springer. doi: 10.1007/s10506-023-09369-4.

Daniel Braun, Patricia Rogetzer, Eva Stoica, and Henry Kurzhals. 2023.

Students' Perspective on AI-Supported Assessment of Open-Ended Questions in Higher Education.

In Proceedings of the 15th International Conference on Computer Supported Education - Volume 2: CSEDU, pages 73-79. SciTePress. doi: 10.5220/0011648900003470.

Phillip Schneider, Anum Afzal, Juraj Vladika, Daniel Braun, and Florian Matthes. 2023.

Investigating Conversational Search Behavior for Domain Exploration.

In Advances in Information Retrieval, pages 608--616, Cham. Springer Nature Switzerland. doi: 10.1007/978-3-031-28238-6_52.

Anum Afzal, Juraj Vladika, Daniel Braun, and Florian Matthes. 2023.

Challenges in Domain-Specific Abstractive Summarization and How to Overcome Them.

In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, pages 682-689. SciTePress. doi: 10.5220/0011744500003393.

Tim Schopf, Daniel Braun, and Florian Matthes. 2023.

Semantic Label Representations with Lbl2Vec: A Similarity-Based Approach for Unsupervised Text Classification.

In Web Information Systems and Technologies, pages 59--73, Cham. Springer International Publishing. doi: 10.1007/978-3-031-24197-0_4.

2022

Tim Schopf, Daniel Braun, and Florian Matthes. 2022.

Evaluating Unsupervised Text Classification: Zero-Shot and Similarity-Based Approaches.

In Proceedings of the 2022 6th International Conference on Natural Language Processing and Information Retrieval, pages 6–15, New York, NY, USA. Association for Computing Machinery. NLPIR '22. doi: 10.1145/3582768.3582795.

Daniel Braun. 2022.

Tracking Semantic Shifts in German Court Decisions with Diachronic Word Embeddings.

In Proceedings of the Natural Legal Language Processing Workshop 2022, pages 218--227, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics. doi: 10.18653/v1/2022.nllp-1.19.

Daniel Braun and Florian Matthes. 2022.

Clause Topic Classification in German and English Standard Form Contracts.

In Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5), pages 199--209, Dublin, Ireland. Association for Computational Linguistics. doi: 10.18653/v1/2022.ecnlp-1.23.

Tobias Schamel, Daniel Braun, and Florian Matthes. 2022.

Structured Extraction of Terms and Conditions from German and English Online Shops.

In Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5), pages 181--190, Dublin, Ireland. Association for Computational Linguistics. doi: 10.18653/v1/2022.ecnlp-1.21.

2021

Daniel Braun, Oleksandra Klymenko, Tim Schopf, Yusuf Kaan Akan, and Florian Matthes. 2021.

The Language of Engineering: Training a Domain-Specific Word Embedding Model for Engineering.

In 2021 3rd International Conference on Management Science and Industrial Engineering, pages 8–12, New York, NY, USA. Association for Computing Machinery. MSIE 2021. doi: 10.1145/3460824.3460826.

Daniel Braun. 2021.

Automated Semantic Analysis, Legal Assessment, and Summarization of Standard Form Contracts.

Thesis, Technical University of Munich.

Daniel Braun and Florian Matthes. 2021.

NLP for Consumer Protection: Battling Illegal Clauses in German Terms and Conditions in Online Shopping.

In Proceedings of the 1st Workshop on NLP for Positive Impact, pages 93--99, Online. Association for Computational Linguistics. doi: 10.18653/v1/2021.nlp4posimpact-1.10.

Tim Schopf, Daniel Braun, and Florian Matthes. 2021.

Lbl2Vec: An Embedding-based Approach for Unsupervised Document Retrieval on Predefined Topics.

In Proceedings of the 17th International Conference on Web Information Systems and Technologies - WEBIST, pages 124-132. SciTePress. doi: 10.5220/0010710300003058.

2020

Daniel Braun and Florian Matthes. 2020.

Automatic Detection of Terms and Conditions in German and English Online Shops.

In Proceedings of the 16th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST, pages 233-237. SciTePress. doi: 10.5220/0010154302330237.

Daniel Braun, Manoj Bhat, Andreas Biesdorf, and Florian Matthes. 2020.

Would You Lie To Me Bot? Supporting Decision-Making Processes with Deceiving Virtual Agents.

In Procedia Computer Science, pages 587 - 592. doi: https://doi.org/10.1016/j.procs.2020.10.083.

Kira Klimt, Daniel Braun, Daniela Schneider, and Florian Matthes. 2020.

MucLex: A German Lexicon for Surface Realisation.

In Proceedings of The 12th Language Resources and Evaluation Conference, pages 4655--4659, Marseille, France. European Language Resources Association.

Oleksandra Klymenko, Daniel Braun, and Florian Matthes. 2020.

Automatic Text Summarization: A State-of-the-Art Review.

In Proceedings of the 22nd International Conference on Enterprise Information Systems - Volume 1: ICEIS, pages 648-655. SciTePress. doi: 10.5220/0009723306480655.

Daniel Braun, Anupama Sajwan, and Florian Matthes. 2020.

User-adaptable Natural Language Generation for Regression Testing within the Finance Domain.

In Proceedings of the 22nd International Conference on Enterprise Information Systems - Volume 1: ICEIS, pages 613-618. SciTePress. doi: 10.5220/0009563306130618.

2019

Daniel Braun, Elena Scepankova, Patrick Holl, and Florian Matthes. 2019.

The Potential of Customer-Centered LegalTech.

In Datenschutz und Datensicherheit - DuD, pages 760--766. doi: 10.1007/s11623-019-1202-7.

Daniel Braun, Kira Klimt, Daniela Schneider, and Florian Matthes. 2019.

SimpleNLG-DE: Adapting SimpleNLG 4 to German.

In Proceedings of the 12th International Conference on Natural Language Generation, pages 415--420, Tokyo, Japan. Association for Computational Linguistics. doi: 10.18653/v1/W19-8651.

Daniel Braun, Elena Scepankova, Patrick Holl, and Florian Matthes. 2019.

Consumer Protection in the Digital Era: The Potential of Customer-Centered LegalTech.

In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft, pages 407-420, Bonn. Gesellschaft für Informatik e.V.. doi: 10.18420/inf2019_58.

Daniel Braun and Florian Matthes. 2019.

Towards a Framework for Classifying Chatbots.

In Proceedings of the 21th International Conference on Enterprise Information Systems (ICEIS 2019), pages 484-489, Heraklion, Greece. SCITEPRESS. doi: 10.5220/0007772704960501.

2018

Daniel Braun, Anne Faber, Adrian Hernandez-Mendez, and Florian Matthes. 2018.

Automatic Relation Extraction for Building Smart City Ecosystems using Dependency Parsing.

In Proceedings of the 2nd Workshop on Natural Language for Artificial Intelligence (NL4AI 2018).

Daniel Braun, Ehud Reiter, and Advaith Siddharthan. 2018.

SaferDrive: An NLG-based behaviour change support system for drivers.

In Natural Language Engineering, pages 551-588. Cambridge University Press. doi: 10.1017/S1351324918000050.

Daniel Braun, Adrian Hernandez-Mendez, Anne Faber, Manfred Langen, and Florian Matthes. 2018.

Customer-Centred Intermodal Combination of Mobility Services with Conversational Interfaces.

In Multikonferenz Wirtschaftsinformatik (MKWI) 2018. Leuphana Universität Lüneburg.

Daniel Braun and Florian Matthes. 2018.

Generating Explanations for Algorithmic Decisions of Usage-Based Insurances using Natural Language Generation.

In Software Engineering und Software Management 2018, pages 219-220, Bonn. Gesellschaft für Informatik. Lecture Notes in Informatics (LNI). doi: 20.500.12116/16354.

Daniel Braun, Elena Scepankova, Patrick Holl, and Florian Matthes. 2018.

Customer-centered LegalTech: Automated Analysis of Standard Form Contracts.

In Tagungsband Internationales Rechtsinformatik Symposium (IRIS) 2018, pages 627-634. Editions Weblaw.

2017

Daniel Braun, Elena Scepankova, Patrick Holl, and Florian Matthes. 2017.

SaToS: Assessing and Summarising Terms of Services from German Webshops.

In Proceedings of the 10th International Conference on Natural Language Generation, pages 223--227, Santiago de Compostela, Spain. Association for Computational Linguistics . doi: 10.18653/v1/W17-3534.

Daniel Braun, Adrian Hernandez-Mendez, Florian Matthes, and Manfred Langen. 2017.

Evaluating Natural Language Understanding Services for Conversational Question Answering Systems.

In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 174--185, Saarbrücken, Germany. Association for Computational Linguistics. doi: 10.18653/v1/W17-5522.

Adrian Hernandez-Mendez, Daniel Braun, Florian Matthes, and Manfred Langen. 2017.

Towards a Context-Aware Vertical Social Software Ecosystem.

In 2017 IEEE 19th Conference on Business Informatics (CBI), pages 76-82. doi: 10.1109/CBI.2017.7.

Jörg Landthaler, Bernhard Waltl, Dominik Huth, Daniel Braun, Florian Matthes, Christoph Stocker, and Thomas Geiger. 2017.

Improving Thesauri Using Word Embeddings and a Novel Intersection Method.

In Proceedings of the Second Workshop on Automated Semantic Analysis of Information in Legal Texts.

2016

Daniel Braun. 2016.

Creating Textual Driver Feedback from Telemetric Data.

Thesis, University of Aberdeen.

2015

Daniel Braun, Ehud Reiter, and Advaith Siddharthan. 2015.

Creating Textual Driver Feedback from Telemetric Data.

In Proceedings of the 15th European Workshop on Natural Language Generation (ENLG), pages 156--165, Brighton, UK. Association for Computational Linguistics. doi: 10.18653/v1/W15-4726.

2014

Daniel Braun. 2014.

Processing Semantic Information from Procedural Modelling Rules for Driving Simulation.

Thesis, Universität des Saarlandes.

2012

Christoph Endres, Rafael Math, and Daniel Braun. 2012.

Simulator-based evaluation on the impact of visual complexity and speed on driver’s cognitive load.

In Adjunct Proceedings of the 4th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, pages 30--31.

2011

Christoph Endres, Daniel Braun, and Christian Müller. 2011.

Prototyping a Semi-Automatic In-Car Texting Assistant.

In Proceedings of the 3rd Workshop on Multimodal Interfaces for Automotive Applications (MIAA 2011), pages 57--60.

Daniel Braun, Christoph Endres, and Christian Müller. 2011.

Determination of Mobility Context using Low-Level Data.

In Adjunct Proceedings of the 3rd International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI 2011), pages 41--42.

2010

Christoph Endres and Daniel Braun. 2010.

Pleopatra: A semi-automatic status-posting prototype for future in-car use.

In Adjunct proceedings of the 2nd International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI 2010), pages 7.

Christoph Endres, Jan Miksatko, and Daniel Braun. 2010.

Youldeco-Exploiting the Power of Online Social Networks for Eco-Friendly Driving.

In Adjunct proceedings of the 2nd International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI 2010), pages 5.

Teaching

Lectures

2023-24

2022-23

2021-22

Previous teaching

Community

I am a member of the Association for Computational Linguistics, Association for Computing Machinery, European Language Resources Association, and the German Gesellschaft für Informatik.

Community Service

  • Program Committee Member Workshop on Human Evaluation of NLP System at LREC-COLING 2024
  • Program Committee Member LREC-COLING 2024
  • Co-Organiser Workshop on Annotation of Legal Data at JURIX 2023
  • Program Committee Member EMNLP 2023
  • Program Committee Member NLP-OSS 2023
  • Program Committee Member JUSMOD 2023
  • Program Committee Member INLG 2023
  • Program Committee Member ACL 2023
  • Technical Committee Member NLPIR 2022
  • Program Committee Member NLG4Health 2022
  • Organizer Munich Legal Tech Summer School 2021
  • Workshop Chair INLG 2020
  • Program Committee Member NLP-OSS 2020
  • Program Committee Member IJCAI 2020
  • Journal Reviewer:
    • Natural Language Engineering
    • Artificial Intelligence
    • Information and Software Technology
    • Artificial Intelligence and Law
    • Language Resources and Evaluation
    • Computer Speech and Language
    • Neurocomputing
    • Computers in Biology and Medicine
    • Journal of Financial Services Marketing
    • Transactions on Information Systems
    • Telematics and Informatics Reports
    • Medien im Diskurs