2025

1. Natural Language Processing for Social Good: contributing to research and society

   Daniel Braun

   it - Information Technology. 2025

   DOI Bib PDF

   @article{Braun+2025,
     title = {Natural Language Processing for Social Good: contributing to research and society},
     journal = {it - Information Technology},
     doi = {10.1515/itit-2024-0095},
     year = {2025},
     author = {Braun, Daniel},
   }

2. Position: Editing Large Language Models Poses Serious Safety Risks

   Paul Youssef, Zhixue Zhao, Daniel Braun, and 2 more authors

   arXiv, 2025

   DOI Abs Bib

   Large Language Models (LLMs) contain large amounts of facts about the world. These facts can become outdated over time, which has led to the development of knowledge editing methods (KEs) that can change specific facts in LLMs with limited side effects. This position paper argues that editing LLMs poses serious safety risks that have been largely overlooked. First, we note the fact that KEs are widely available, computationally inexpensive, highly performant, and stealthy makes them an attractive tool for malicious actors. Second, we discuss malicious use cases of KEs, showing how KEs can be easily adapted for a variety of malicious purposes. Third, we highlight vulnerabilities in the AI ecosystem that allow unrestricted uploading and downloading of updated models without verification. Fourth, we argue that a lack of social and institutional awareness exacerbates this risk, and discuss the implications for different stakeholders. We call on the community to (i) research tamper-resistant models and countermeasures against malicious model editing, and (ii) actively engage in securing the AI ecosystem.

   @misc{youssef2025positioneditinglargelanguage,
     title = {Position: Editing Large Language Models Poses Serious Safety Risks},
     author = {Youssef, Paul and Zhao, Zhixue and Braun, Daniel and Schlötterer, Jörg and Seifert, Christin},
     year = {2025},
     eprint = {2502.02958},
     archiveprefix = {arXiv},
     primaryclass = {cs.CL},
     doi = {10.48550/arXiv.2502.02958},
     publisher = {arXiv}
   }

2024

1. Leveraging Annotator Disagreement for Text Classification

   Jin Xu, Mariët Theune, and Daniel Braun

   In Proceedings of the 7th International Conference on Natural Language and Speech Processing (ICNLSP 2024). Association for Computational Linguistics, 2024

   DOI Link Bib PDF

   @inproceedings{xu-etal-2024-leveraging,
     title = {Leveraging Annotator Disagreement for Text Classification},
     author = {Xu, Jin and Theune, Mariët and Braun, Daniel},
     editor = {Abbas, Mourad and Freihat, Abed Alhakim},
     booktitle = {Proceedings of the 7th International Conference on Natural Language and Speech Processing (ICNLSP 2024)},
     month = oct,
     year = {2024},
     address = {Trento},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2024.icnlsp-1.1},
     pages = {1--10},
     doi = {10.48550/arXiv.2409.17577},
   }

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

   Vitalii Fishchuk, and Daniel Braun

   International Journal of Speech Technology. Springer, 2024

   DOI Link Abs Bib PDF

   The increased quality and human-likeness of AI generated texts has resulted in a rising demand for neural text detectors, i.e. software that is able to detect whether a text was written by a human or generated by an AI. Such tools are often used in contexts where the use of AI is restricted or completely prohibited, e.g. in educational contexts. It is, therefore, important for the effectiveness of such tools that they are robust towards deliberate attempts to hide the fact that a text was generated by an AI. In this article, we investigate a broad range of adversarial attacks in English texts with six different neural text detectors, including commercial and research tools. While the results show that no detector is completely invulnerable to adversarial attacks, the latest generation of commercial detectors proved to be very robust and not significantly influenced by most of the evaluated attack strategies.

   @article{IJST-D-24-00132,
     title = {Robustness of generative AI detection: adversarial attacks on black-box neural text detectors},
     author = {Fishchuk, Vitalii and Braun, Daniel},
     year = {2024},
     month = dec,
     day = {1},
     doi = {10.1007/s10772-024-10144-2},
     journal = {International Journal of Speech Technology},
     issn = {1572-8110},
     publisher = {Springer},
     volume = {27},
     issue = {4},
     url = {https://link.springer.com/article/10.1007/s10772-024-10144-2}
   }

3. Daten und Datenkennzeichnung im Kontext der KI‑VO

   Daniel Braun

   Künstliche Intelligenz und Recht. C.H. Beck, 2024

   Link Abs Bib

   Daten sind die Grundlage des maschinellen Lernens und beeinflussen das Verhalten und die Entwicklung von darauf basierenden KI-Systemen entscheidend. Entsprechend kommt Daten, deren Sammlung, Auswahl, Kennzeichnung und Bereinigung auch iRd KI-Verordnung (KI‑VO) eine wichtige Rolle zu. Dieser Beitrag beschreibt die verschiedenen Arten von Daten und Verfahren zur Datenkennzeichnung iSd KI‑VO sowie deren Dokumentation.

   @article{braun2024KIR,
     title = {Daten und Datenkennzeichnung im Kontext der KI‑VO},
     author = {Braun, Daniel},
     year = {2024},
     journal = {Künstliche Intelligenz und Recht},
     publisher = {C.H. Beck},
     pages = {43--46},
     number = {2},
     address = {München},
     url = {https://beck-online.beck.de/Bcid/Y-300-Z-KIR-B-2024-S-43-N-1}
   }

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

   Daniel Braun

   In Professionalisierung im Verbraucherschutz. Jahrbuch Konsum & Verbraucherwissenschaften 2023/2024. Verbraucherzentrale, 2024

   Bib

   @incollection{braun2024klauselkontrolle,
     author = {Braun, Daniel},
     title = {KI-gestützte Klauselkontrolle in allgemeinen Geschäftsbedingungen: Wie künstliche Intelligenz dabei helfen kann, den Verbraucherschutz beim Onlineshopping zu stärken},
     editor = {Bala, Christian and Boden, Alexander and Lamla, Jörn and Stevens, Gunnar and Schuldzinski, Wolfgang},
     booktitle = {Professionalisierung im Verbraucherschutz. Jahrbuch Konsum & Verbraucherwissenschaften 2023/2024},
     year = {2024},
     pages = {87--100},
     publisher = {Verbraucherzentrale},
     address = {Düsseldorf}
   }

5. Why "Artificial Intelligence" Should Not Be Regulated

   Daniel Braun

   Digit. Gov.: Res. Pract.. Association for Computing Machinery, 2024

   Just Accepted

   DOI Link Abs Bib PDF

   Lawmakers all over the world have started to draft new regulations for Artificial Intelligence (AI). While the European Union is currently leading the way with its AI Act, many other legislators will follow and already positioned themselves with white papers and other publications. This commentary argues that “Artificial Intelligence”, including Generative AI, should not be used as a regulatory category. Not because there is no potential for harm from AI systems and not because AI systems should not be regulated, but because “Artificial Intelligence” is a vaguely defined label that is neither suitable nor necessary for comprehensive regulation of technological risks. Instead of regulating a particular set of approaches and algorithms, lawmakers should focus and double down on regulating high-risk applications of software, independent of whether it is labelled as AI or not.

   @article{10.1145/3696010,
     author = {Braun, Daniel},
     title = {Why "Artificial Intelligence" Should Not Be Regulated},
     year = {2024},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3696010},
     doi = {10.1145/3696010},
     note = {Just Accepted},
     journal = {Digit. Gov.: Res. Pract.},
     month = sep,
     keywords = {Artificial Intelligence, Generative AI, Regulation, AI Act},
   }

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

   Daniel Braun, and Florian Matthes

   In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 2024

   DOI Link Abs Bib PDF

   Legal tasks and datasets are often used as benchmarks for the capabilities of language models. However, openly available annotated datasets are rare. In this paper, we introduce AGB-DE, a corpus of 3,764 clauses from German consumer contracts that have been annotated and legally assessed by legal experts. Together with the data, we present a first baseline for the task of detecting potentially void clauses, comparing the performance of an SVM baseline with three fine-tuned open language models and the performance of GPT-3.5. Our results show the challenging nature of the task, with no approach exceeding an F1-score of 0.54. While the fine-tuned models often performed better with regard to precision, GPT-3.5 outperformed the other approaches with regard to recall. An analysis of the errors indicates that one of the main challenges could be the correct interpretation of complex clauses, rather than the decision boundaries of what is permissible and what is not.

   @inproceedings{braun-matthes-2024-agb,
     title = {{AGB}-{DE}: A Corpus for the Automated Legal Assessment of Clauses in {G}erman Consumer Contracts},
     author = {Braun, Daniel and Matthes, Florian},
     editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
     booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
     month = aug,
     year = {2024},
     address = {Bangkok, Thailand},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2024.acl-long.559},
     doi = {10.18653/v1/2024.acl-long.559},
     pages = {10389--10405},
   }

7. Teaching Natural Language Processing in Law School

   Daniel Braun

   In Proceedings of the Sixth Workshop on Teaching NLP. Association for Computational Linguistics, 2024

   Link Abs Bib

   Fuelled by technical advances, the interest in Natural Language Processing in the legal domain has rapidly increased over the last months and years. The design, usage, and testing of domain-specific systems, but also assessing these systems from a legal perspective, needs competencies at the intersection of law and Natural Language Processing. While the demand for such competencies is high among students, only a few law schools, particularly in Europe, teach such competencies. In this paper, we present the design for a Natural Language Processing course for postgraduate law students that is based on the principle of constructive alignment and has proven to be successful over the last three years.

   @inproceedings{braun-2024-teaching-natural,
     title = {Teaching Natural Language Processing in Law School},
     author = {Braun, Daniel},
     editor = {Al-azzawi, Sana and Biester, Laura and Kov{\'a}cs, Gy{\"o}rgy and Marasovi{\'c}, Ana and Mathur, Leena and Mieskes, Margot and Weissweiler, Leonie},
     booktitle = {Proceedings of the Sixth Workshop on Teaching NLP},
     month = aug,
     year = {2024},
     address = {Bangkok, Thailand},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2024.teachingnlp-1.13},
     pages = {85--90}
   }

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

   Leixin Zhang, and Daniel Braun

   In Proceedings of the 11th Workshop on Argument Mining (ArgMining 2024). Association for Computational Linguistics, 2024

   DOI Link Abs Bib

   The paper describes our system for the Perspective Argument Retrieval Shared Task. The shared task consists of three scenarios in which relevant political arguments have to be retrieved based on queries (Scenario 1). In Scenario 2 explicit socio-cultural properties are provided and in Scenario 3 implicit socio-cultural properties within the arguments have to be used. We combined a Bi-Encoder and a Cross-Encoder to retrieve relevant arguments for each query. For the third scenario, we extracted linguistic features to predict socio-demographic labels as a separate task. However, the socio-demographic match task proved challenging due to the constraints of argument lengths and genres. The described system won both tracks of the shared task.

   @inproceedings{zhang-braun-2024-twente,
     title = {Twente-{BMS}-{NLP} at {P}erspective{A}rg 2024: Combining Bi-Encoder and Cross-Encoder for Argument Retrieval},
     author = {Zhang, Leixin and Braun, Daniel},
     editor = {Ajjour, Yamen and Bar-Haim, Roy and El Baff, Roxanne and Liu, Zhexiong and Skitalinskaya, Gabriella},
     booktitle = {Proceedings of the 11th Workshop on Argument Mining (ArgMining 2024)},
     month = aug,
     year = {2024},
     address = {Bangkok, Thailand},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2024.argmining-1.17},
     doi = {10.18653/v1/2024.argmining-1.17},
     pages = {164--168}
   }

9. Exploring Lexical Alignment in a Price Bargain Chatbot

   Zhenqi Zhao, Mariët Theune, Sumit Srivastava, and 1 more author

   In ACM Conversational User Interfaces 2024. Association for Computing Machinery, Luxembourg, Luxembourg, 2024

   DOI Link Bib

   @inproceedings{10.1145/3640794.3665576,
     author = {Zhao, Zhenqi and Theune, Mariët and Srivastava, Sumit and Braun, Daniel},
     title = {Exploring Lexical Alignment in a Price Bargain Chatbot},
     year = {2024},
     isbn = {9798400705113},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3640794.3665576},
     doi = {10.1145/3640794.3665576},
     booktitle = {ACM Conversational User Interfaces 2024},
     articleno = {40},
     numpages = {7},
     keywords = {chatGPT, chatbot, lexical alignment},
     location = {Luxembourg, Luxembourg},
     series = {CUI '24}
   }

2023

1. Efficient Black-Box Adversarial Attacks on Neural Text Detectors

   Vitalii Fishchuk, and Daniel Braun

   In Proceedings of the 6th International Conference on Natural Language and Speech Processing (ICNLSP 2023). Association for Computational Linguistics, 2023

   DOI Link Bib

   @inproceedings{fishchuk-braun-2023-efficient,
     title = {Efficient Black-Box Adversarial Attacks on Neural Text Detectors},
     author = {Fishchuk, Vitalii and Braun, Daniel},
     editor = {Abbas, Mourad and Freihat, Abed Alhakim},
     booktitle = {Proceedings of the 6th International Conference on Natural Language and Speech Processing (ICNLSP 2023)},
     month = dec,
     year = {2023},
     address = {Online},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2023.icnlsp-1.8},
     pages = {78--83},
     doi = {10.48550/arXiv.2311.01873}
   }

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

   Daniel Braun

   Artificial Intelligence and Law. Springer, 2023

   DOI Link Abs Bib PDF

   Legal documents, like contracts or laws, are subject to interpretation. Different people can have different interpretations of the very same document. Large parts of judicial branches all over the world are concerned with settling disagreements that arise, in part, from these different interpretations. In this context, it only seems natural that during the annotation of legal machine learning data sets, disagreement, how to report it, and how to handle it should play an important role. This article presents an analysis of the current state-of-the-art in the annotation of legal machine learning data sets. The results of the analysis show that all of the analysed data sets remove all traces of disagreement, instead of trying to utilise the information that might be contained in conflicting annotations. Additionally, the publications introducing the data sets often do provide little information about the process that derives the “gold standard” from the initial annotations, often making it difficult to judge the reliability of the annotation process. Based on the state-of-the-art, the article provides easily implementable suggestions on how to improve the handling and reporting of disagreement in the annotation of legal machine learning data sets.

   @article{ibegtodiffer,
     title = {I Beg to Differ: How Disagreement is Handled in the Annotation of Legal Machine Learning Data Sets},
     author = {Braun, Daniel},
     url = {https://link.springer.com/article/10.1007/s10506-023-09369-4},
     doi = {10.1007/s10506-023-09369-4},
     year = {2023},
     date = {2023-06-27},
     volume = {32},
     number = {3},
     pages = {839-862},
     issn = {1572-8382},
     journal = {Artificial Intelligence and Law},
     publisher = {Springer},
   }

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

   Daniel Braun, Patricia Rogetzer, Eva Stoica, and 1 more author

   In Proceedings of the 15th International Conference on Computer Supported Education - Volume 2: CSEDU. SciTePress, 2023

   DOI Bib

   @inproceedings{csedu23,
     author = {Braun, Daniel and Rogetzer, Patricia and Stoica, Eva and Kurzhals, Henry},
     title = {Students' Perspective on AI-Supported Assessment of Open-Ended Questions in Higher Education},
     booktitle = {Proceedings of the 15th International Conference on Computer Supported Education - Volume 2: CSEDU},
     year = {2023},
     pages = {73-79},
     publisher = {SciTePress},
     organization = {INSTICC},
     doi = {10.5220/0011648900003470},
     isbn = {978-989-758-641-5},
     issn = {2184-5026}
   }

4. Investigating Conversational Search Behavior for Domain Exploration

   Phillip Schneider, Anum Afzal, Juraj Vladika, and 2 more authors

   In Advances in Information Retrieval. Springer Nature Switzerland, 2023

   DOI Abs Bib

   Conversational search has evolved as a new information retrieval paradigm, marking a shift from traditional search systems towards interactive dialogues with intelligent search agents. This change especially affects exploratory information-seeking contexts, where conversational search systems can guide the discovery of unfamiliar domains. In these scenarios, users find it often difficult to express their information goals due to insufficient background knowledge. Conversational interfaces can provide assistance by eliciting information needs and narrowing down the search space. However, due to the complexity of information-seeking behavior, the design of conversational interfaces for retrieving information remains a great challenge. Although prior work has employed user studies to empirically ground the system design, most existing studies are limited to well-defined search tasks or known domains, thus being less exploratory in nature. Therefore, we conducted a laboratory study to investigate open-ended search behavior for navigation through unknown information landscapes. The study comprised of 26 participants who were restricted in their search to a text chat interface. Based on the collected dialogue transcripts, we applied statistical analyses and process mining techniques to uncover general information-seeking patterns across five different domains. We not only identify core dialogue acts and their interrelations that enable users to discover domain knowledge, but also derive design suggestions for conversational search systems.

   @inproceedings{10.1007/978-3-031-28238-6_52,
     author = {Schneider, Phillip and Afzal, Anum and Vladika, Juraj and Braun, Daniel and Matthes, Florian},
     editor = {Kamps, Jaap and Goeuriot, Lorraine and Crestani, Fabio and Maistro, Maria and Joho, Hideo and Davis, Brian and Gurrin, Cathal and Kruschwitz, Udo and Caputo, Annalina},
     title = {Investigating Conversational Search Behavior for Domain Exploration},
     booktitle = {Advances in Information Retrieval},
     year = {2023},
     publisher = {Springer Nature Switzerland},
     address = {Cham},
     pages = {608--616},
     isbn = {978-3-031-28238-6},
     doi = {10.1007/978-3-031-28238-6_52}
   }

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

   Anum Afzal, Juraj Vladika, Daniel Braun, and 1 more author

   In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART. SciTePress, 2023

   DOI Bib

   @inproceedings{icaart23,
     author = {Afzal, Anum and Vladika, Juraj and Braun, Daniel and Matthes, Florian},
     title = {Challenges in Domain-Specific Abstractive Summarization and How to Overcome Them},
     booktitle = {Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
     year = {2023},
     pages = {682-689},
     publisher = {SciTePress},
     organization = {INSTICC},
     doi = {10.5220/0011744500003393},
     isbn = {978-989-758-623-1},
     issn = {2184-433X}
   }

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

   Tim Schopf, Daniel Braun, and Florian Matthes

   In Web Information Systems and Technologies. Springer International Publishing, 2023

   DOI Abs Bib

   In this paper, we evaluate the Lbl2Vec approach for unsupervised text document classification. Lbl2Vec requires only a small number of keywords describing the respective classes to create semantic label representations. For classification, Lbl2Vec uses cosine similarities between label and document representations, but no annotation information. We show that Lbl2Vec significantly outperforms common unsupervised text classification approaches and a widely used zero-shot text classification approach. Furthermore, we show that using more precise keywords can significantly improve the classification results of similarity-based text classification approaches.

   @inproceedings{10.1007/978-3-031-24197-0_4,
     author = {Schopf, Tim and Braun, Daniel and Matthes, Florian},
     editor = {Marchiori, Massimo and Dom{\'i}nguez Mayo, Francisco Jos{\'e} and Filipe, Joaquim},
     title = {Semantic Label Representations with Lbl2Vec: A Similarity-Based Approach for Unsupervised Text Classification},
     booktitle = {Web Information Systems and Technologies},
     year = {2023},
     publisher = {Springer International Publishing},
     address = {Cham},
     pages = {59--73},
     isbn = {978-3-031-24197-0},
     doi = {10.1007/978-3-031-24197-0_4}
   }

2022

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

   Tim Schopf, Daniel Braun, and Florian Matthes

   In Proceedings of the 2022 6th International Conference on Natural Language Processing and Information Retrieval. Association for Computing Machinery, Bangkok, Thailand, 2022

   DOI Link Abs Bib

   Text classification of unseen classes is a challenging Natural Language Processing task and is mainly attempted using two different types of approaches. Similarity-based approaches attempt to classify instances based on similarities between text document representations and class description representations. Zero-shot text classification approaches aim to generalize knowledge gained from a training task by assigning appropriate labels of unknown classes to text documents. Although existing studies have already investigated individual approaches to these categories, the experiments in literature do not provide a consistent comparison. This paper addresses this gap by conducting a systematic evaluation of different similarity-based and zero-shot approaches for text classification of unseen classes. Different state-of-the-art approaches are benchmarked on four text classification datasets, including a new dataset from the medical domain. Additionally, novel SimCSE [7] and SBERT-based [26] baselines are proposed, as other baselines used in existing work yield weak classification results and are easily outperformed. Finally, the novel similarity-based Lbl2TransformerVec approach is presented, which outperforms previous state-of-the-art approaches in unsupervised text classification. Our experiments show that similarity-based approaches significantly outperform zero-shot approaches in most cases. Additionally, using SimCSE or SBERT embeddings instead of simpler text representations increases similarity-based classification results even further.

   @inproceedings{10.1145/3582768.3582795,
     author = {Schopf, Tim and Braun, Daniel and Matthes, Florian},
     title = {Evaluating Unsupervised Text Classification: Zero-Shot and Similarity-Based Approaches},
     year = {2022},
     isbn = {9781450397629},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3582768.3582795},
     doi = {10.1145/3582768.3582795},
     booktitle = {Proceedings of the 2022 6th International Conference on Natural Language Processing and Information Retrieval},
     pages = {6–15},
     numpages = {10},
     keywords = {Unsupervised Text Classification, Zero-shot Text Classification, Natural Language Processing},
     location = {Bangkok, Thailand},
     series = {NLPIR '22}
   }

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

   Daniel Braun

   In Proceedings of the Natural Legal Language Processing Workshop 2022. Association for Computational Linguistics, 2022

   DOI Link Abs Bib

   Language and its usage change over time. While legal language is arguably more stable than everyday language, it is still subject to change. Sometimes it changes gradually and slowly, sometimes almost instantaneously, for example through legislative changes. This paper presents an application of diachronic word embeddings to track changes in the usage of language by German courts triggered by changing legislation, based on a corpus of more than 200,000 documents. The results show the swift and lasting effect that changes in legislation can have on the usage of language by courts and suggest that using time-restricted word embedding models could be beneficial for downstream NLP tasks.

   @inproceedings{braun-2022-tracking,
     title = {Tracking Semantic Shifts in {G}erman Court Decisions with Diachronic Word Embeddings},
     author = {Braun, Daniel},
     booktitle = {Proceedings of the Natural Legal Language Processing Workshop 2022},
     month = dec,
     year = {2022},
     address = {Abu Dhabi, United Arab Emirates (Hybrid)},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2022.nllp-1.19},
     doi = {10.18653/v1/2022.nllp-1.19},
     pages = {218--227}
   }

3. Clause Topic Classification in German and English Standard Form Contracts

   Daniel Braun, and Florian Matthes

   In Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5). Association for Computational Linguistics, 2022

   DOI Link Abs Bib

   So-called standard form contracts, i.e. contracts that are drafted unilaterally by one party, like terms and conditions of online shops or terms of services of social networks, are cornerstones of our modern economy. Their processing is, therefore, of significant practical value. Often, the sheer size of these contracts allows the drafting party to hide unfavourable terms from the other party. In this paper, we compare different approaches for automatically classifying the topics of clauses in standard form contracts, based on a data-set of more than 6,000 clauses from more than 170 contracts, which we collected from German and English online shops and annotated based on a taxonomy of clause topics, that we developed together with legal experts. We will show that, in our comparison of seven approaches, from simple keyword matching to transformer language models, BERT performed best with an F1-score of up to 0.91, however much simpler and computationally cheaper models like logistic regression also achieved similarly good results of up to 0.87.

   @inproceedings{braun-matthes-2022-clause,
     title = {Clause Topic Classification in {G}erman and {E}nglish Standard Form Contracts},
     author = {Braun, Daniel and Matthes, Florian},
     booktitle = {Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5)},
     month = may,
     year = {2022},
     address = {Dublin, Ireland},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2022.ecnlp-1.23},
     doi = {10.18653/v1/2022.ecnlp-1.23},
     pages = {199--209}
   }

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

   Tobias Schamel, Daniel Braun, and Florian Matthes

   In Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5). Association for Computational Linguistics, 2022

   DOI Link Abs Bib

   The automated analysis of Terms and Conditions has gained attention in recent years, mainly due to its relevance to consumer protection. Well-structured data sets are the base for every analysis. While content extraction, in general, is a well-researched field and many open source libraries are available, our evaluation shows, that existing solutions cannot extract Terms and Conditions in sufficient quality, mainly because of their special structure. In this paper, we present an approach to extract the content and hierarchy of Terms and Conditions from German and English online shops. Our evaluation shows, that the approach outperforms the current state of the art. A python implementation of the approach is made available under an open license.

   @inproceedings{schamel-etal-2022-structured,
     title = {Structured Extraction of Terms and Conditions from {G}erman and {E}nglish Online Shops},
     author = {Schamel, Tobias and Braun, Daniel and Matthes, Florian},
     booktitle = {Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5)},
     month = may,
     year = {2022},
     address = {Dublin, Ireland},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2022.ecnlp-1.21},
     pages = {181--190},
     doi = {10.18653/v1/2022.ecnlp-1.21}
   }

2021

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

   Daniel Braun, Oleksandra Klymenko, Tim Schopf, and 2 more authors

   In 2021 3rd International Conference on Management Science and Industrial Engineering. Association for Computing Machinery, Osaka, Japan, 2021

   DOI Link Abs Bib

   Since the introduction of Word2Vec in 2013, so-called word embeddings, dense vector representation of words that are supposed to capture their semantic meaning, have become a universally applied technique in a wide range of Natural Language Processing (NLP) tasks and domains. The vector representations they provide are learned on huge corpora of unlabeled text data. Due to the large amount of data and computing power that is necessary to train such embedding models, very often, pre-trained models are applied which have been trained on domain unspecific data like newspaper articles or Wikipedia entries. In this paper, we present a domain-specific embedding model that is trained exclusively on texts from the domain of engineering. We will show that such a domain-specific embeddings model performs better in different NLP tasks and can therefore help to improve NLP-based AI in the domain of Engineering.

   @inproceedings{10.1145/3460824.3460826,
     author = {Braun, Daniel and Klymenko, Oleksandra and Schopf, Tim and Kaan Akan, Yusuf and Matthes, Florian},
     title = {The Language of Engineering: Training a Domain-Specific Word Embedding Model for Engineering},
     year = {2021},
     isbn = {9781450388887},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3460824.3460826},
     doi = {10.1145/3460824.3460826},
     booktitle = {2021 3rd International Conference on Management Science and Industrial Engineering},
     pages = {8–12},
     numpages = {5},
     keywords = {Word Embeddings, Engineering},
     location = {Osaka, Japan},
     series = {MSIE 2021}
   }

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

   Daniel Braun

   Thesis, Technical University of Munich 2021

   Link Bib

   @phdthesis{braun2021automated,
     title = {Automated Semantic Analysis, Legal Assessment, and Summarization of Standard Form Contracts},
     author = {Braun, Daniel},
     year = {2021},
     school = {Technical University of Munich},
     url = https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20210602-1581193-1-8
   }

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

   Daniel Braun, and Florian Matthes

   In Proceedings of the 1st Workshop on NLP for Positive Impact. Association for Computational Linguistics, 2021

   DOI Link Abs Bib

   Online shopping is an ever more important part of the global consumer economy, not just in times of a pandemic. When we place an order online as consumers, we regularly agree to the so-called “Terms and Conditions” (T&C), a contract unilaterally drafted by the seller. Often, consumers do not read these contracts and unwittingly agree to unfavourable and often void terms. Government and non-government organisations (NGOs) for consumer protection battle such terms on behalf of consumers, who often hesitate to take on legal actions themselves. However, the growing number of online shops and a lack of funding makes it increasingly difficult for such organisations to monitor the market effectively. This paper describes how Natural Language Processing (NLP) can be applied to support consumer advocates in their efforts to protect consumers. Together with two NGOs from Germany, we developed an NLP-based application that legally assesses clauses in T&C from German online shops under the European Union’s (EU) jurisdiction. We report that we could achieve an accuracy of 0.9 in the detection of void clauses by fine-tuning a pre-trained German BERT model. The approach is currently used by two NGOs and has already helped to challenge void clauses in T&C.

   @inproceedings{braun-matthes-2021-nlp,
     title = {{NLP} for Consumer Protection: Battling Illegal Clauses in {G}erman Terms and Conditions in Online Shopping},
     author = {Braun, Daniel and Matthes, Florian},
     booktitle = {Proceedings of the 1st Workshop on NLP for Positive Impact},
     month = aug,
     year = {2021},
     address = {Online},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2021.nlp4posimpact-1.10},
     doi = {10.18653/v1/2021.nlp4posimpact-1.10},
     pages = {93--99}
   }

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

   Tim Schopf, Daniel Braun, and Florian Matthes

   In Proceedings of the 17th International Conference on Web Information Systems and Technologies - WEBIST. SciTePress, 2021

   DOI Bib

   @inproceedings{webist21,
     title = {Lbl2Vec: An Embedding-based Approach for Unsupervised Document Retrieval on Predefined Topics},
     author = {Schopf, Tim and Braun, Daniel and Matthes, Florian},
     doi = {10.5220/0010710300003058},
     issn = {2184-3252},
     year = {2021},
     date = {2021-01-01},
     urldate = {2021-01-01},
     booktitle = {Proceedings of the 17th International Conference on Web Information Systems and Technologies - WEBIST},
     pages = {124-132},
     publisher = {SciTePress},
     organization = {INSTICC},
     keywords = {NLP},
     pubstate = {published},
     tppubtype = {conference}
   }

2020

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

   Daniel Braun, and Florian Matthes

   In Proceedings of the 16th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST. SciTePress, 2020

   DOI Bib

   @inproceedings{webist20,
     title = {Automatic Detection of Terms and Conditions in German and English Online Shops},
     author = {Braun, Daniel and Matthes, Florian},
     doi = {10.5220/0010154302330237},
     isbn = {978-989-758-478-7},
     year = {2020},
     date = {2020-11-16},
     booktitle = {Proceedings of the 16th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST},
     pages = {233-237},
     publisher = {SciTePress},
     organization = {INSTICC},
     keywords = {artificial intelligence, legaltech},
     pubstate = {published},
     tppubtype = {conference}
   }

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

   Daniel Braun, Manoj Bhat, Andreas Biesdorf, and 1 more author

   Procedia Computer Science. 2020

   DOI Link Abs Bib

   Although we learn as children that "you shall not lie", it is widely accepted that deceptions and lies are necessary, yet unloved, parts of human communication. They are part of the clay that holds together the bricks of our society. In human-computer interaction, however, deceiving machines are seen as a taboo. In this paper, we want to challenge this perception by describing a virtual agent that improves decision-making processes by deceiving decision-makers in a controlled manner. A first survey we conducted shows that such a bot could indeed lead to a more informed decision-making process.

   @article{BRAUN2020587,
     title = {Would You Lie To Me Bot? Supporting Decision-Making Processes with Deceiving Virtual Agents},
     author = {Braun, Daniel and Bhat, Manoj and Biesdorf, Andreas and Matthes, Florian},
     url = {http://www.sciencedirect.com/science/article/pii/S1877050920323541},
     doi = {https://doi.org/10.1016/j.procs.2020.10.083},
     issn = {1877-0509},
     year = {2020},
     date = {2020-11-11},
     journal = {Procedia Computer Science},
     volume = {177},
     pages = {587 - 592},
     keywords = {artificial intelligence, bots, decision-making, software architecture},
     pubstate = {published},
     tppubtype = {article}
   }

3. MucLex: A German Lexicon for Surface Realisation

   Kira Klimt, Daniel Braun, Daniela Schneider, and 1 more author

   In Proceedings of The 12th Language Resources and Evaluation Conference. European Language Resources Association, 2020

   Link Abs Bib

   Language resources for languages other than English are often scarce. Rule-based surface realisers need elaborate lexica in order to be able to generate correct language, especially in languages like German, which include many irregular word forms. In this paper, we present MucLex, a German lexicon for the Natural Language Generation task of surface realisation, based on the crowd-sourced online lexicon Wiktionary. MucLex contains more than 100,000 lemmata and more than 670,000 different word forms in a well-structured XML file and is available under the Creative Commons BY-SA 3.0 license.

   @inproceedings{klimt-etal-2020-muclex,
     title = {MucLex: A German Lexicon for Surface Realisation},
     author = {Klimt, Kira and Braun, Daniel and Schneider, Daniela and Matthes, Florian},
     url = {https://www.aclweb.org/anthology/2020.lrec-1.572},
     isbn = {979-10-95546-34-4},
     year = {2020},
     date = {2020-05-01},
     booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference},
     pages = {4655--4659},
     publisher = {European Language Resources Association},
     address = {Marseille, France},
     keywords = {},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

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

   Oleksandra Klymenko, Daniel Braun, and Florian Matthes

   In Proceedings of the 22nd International Conference on Enterprise Information Systems - Volume 1: ICEIS. SciTePress, 2020

   DOI Bib

   @inproceedings{Klymenko2020,
     title = {Automatic Text Summarization: A State-of-the-Art Review},
     author = {Klymenko, Oleksandra and Braun, Daniel and Matthes, Florian},
     doi = {10.5220/0009723306480655},
     isbn = {978-989-758-423-7},
     year = {2020},
     date = {2020-01-01},
     booktitle = {Proceedings of the 22nd International Conference on Enterprise Information Systems - Volume 1: ICEIS},
     pages = {648-655},
     publisher = {SciTePress},
     organization = {INSTICC},
     keywords = {},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

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

   Daniel Braun, Anupama Sajwan, and Florian Matthes

   In Proceedings of the 22nd International Conference on Enterprise Information Systems - Volume 1: ICEIS. SciTePress, 2020

   DOI Bib

   @inproceedings{iceis20b,
     title = {User-adaptable Natural Language Generation for Regression Testing within the Finance Domain},
     author = {Braun, Daniel and Sajwan, Anupama and Matthes, Florian},
     doi = {10.5220/0009563306130618},
     isbn = {978-989-758-423-7},
     year = {2020},
     date = {2020-01-01},
     booktitle = {Proceedings of the 22nd International Conference on Enterprise Information Systems - Volume 1: ICEIS},
     pages = {613-618},
     publisher = {SciTePress},
     organization = {INSTICC},
     keywords = {},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

2019

1. The Potential of Customer-Centered LegalTech

   Daniel Braun, Elena Scepankova, Patrick Holl, and 1 more author

   Datenschutz und Datensicherheit - DuD. 2019

   DOI Link Abs Bib

   New technologies and tools, often summarised under the term “LegalTech,,, are changing the way inwhich legal professionals work. The digital transformation has changed many aspects of our daily life anddemocratised access to knowledge and services. In the legal domain, however, consumers rarely benefit fromdigitisation. On the contrary, they are often overpowered by big corporations and their well-equipped legaldepartments. In this paper, we outline how LegalTech can be used to empower consumers in the digital era,by building tools to support consumers and those who protect them. In order to show the potential of customer-centredLegalTech, we present two prototypes which semantically analyse, assess, and summarise Terms of Servicesfrom German web shops.

   @article{Braun2019c,
     title = {The Potential of Customer-Centered LegalTech},
     author = {Braun, Daniel and Scepankova, Elena and Holl, Patrick and Matthes, Florian},
     url = {https://doi.org/10.1007/s11623-019-1202-7},
     doi = {10.1007/s11623-019-1202-7},
     issn = {1862-2607},
     year = {2019},
     date = {2019-12-01},
     journal = {Datenschutz und Datensicherheit - DuD},
     volume = {43},
     number = {12},
     pages = {760--766},
     keywords = {},
     pubstate = {published},
     tppubtype = {article}
   }

2. SimpleNLG-DE: Adapting SimpleNLG 4 to German

   Daniel Braun, Kira Klimt, Daniela Schneider, and 1 more author

   In Proceedings of the 12th International Conference on Natural Language Generation. Association for Computational Linguistics, 2019

   DOI Link Abs Bib

   SimpleNLG is a popular open source surface realiser for the English language. For German, however, the availability of open source and non-domain specific realisers is sparse, partly due to the complexity of the German language. In this paper, we present SimpleNLG-DE, an adaption of SimpleNLG to German. We discuss which parts of the German language have been implemented and how we evaluated our implementation using the TIGER Corpus and newly created data-sets.

   @inproceedings{braun-etal-2019-simplenlg,
     title = {{S}imple{NLG}-{DE}: Adapting {S}imple{NLG} 4 to {G}erman},
     author = {Braun, Daniel and Klimt, Kira and Schneider, Daniela and Matthes, Florian},
     booktitle = {Proceedings of the 12th International Conference on Natural Language Generation},
     month = oct,
     year = {2019},
     address = {Tokyo, Japan},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/W19-8651},
     doi = {10.18653/v1/W19-8651},
     pages = {415--420}
   }

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

   Daniel Braun, Elena Scepankova, Patrick Holl, and 1 more author

   In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft. Gesellschaft für Informatik e.V., 2019

   DOI Abs Bib

   New technologies and tools, often summarised under the term “LegalTech”, are changing the way in which legal professionals work. The digital transformation has changed many aspects of our daily life and democratised access to knowledge and services. In the legal domain, however, consumers rarely benefit from digitisation. On the contrary, they are often overpowered by big corporations and their well equipped legal departments. In this paper, we outline how LegalTech can be used to empower consumers in the digital era, by building tools to support consumers and those who protect them. In order to show the potential of customer-centered LegalTech, we present two prototypes which semantically analyse, assess, and summarise Terms of Services from German web shops.

   @inproceedings{mci/Braun2019,
     title = {Consumer Protection in the Digital Era: The Potential of Customer-Centered LegalTech},
     author = {Braun, Daniel and Scepankova, Elena and Holl, Patrick and Matthes, Florian},
     editor = {David, Klaus and Geihs, Kurt and Lange, Martin and Stumme, Gerd},
     doi = {10.18420/inf2019_58},
     isbn = { 978-3-88579-688-6},
     year = {2019},
     date = {2019-09-17},
     booktitle = {INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft},
     pages = {407-420},
     publisher = {Gesellschaft für Informatik e.V.},
     address = {Bonn},
     keywords = {legaltech, NLP},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

4. Towards a Framework for Classifying Chatbots

   Daniel Braun, and Florian Matthes

   In Proceedings of the 21th International Conference on Enterprise Information Systems (ICEIS 2019). SCITEPRESS, 2019

   DOI Abs Bib

   From sophisticated personal voice assistants like Siri or Alexa to simplistic keyword-based search bots, today, the label "chatbot" is used broadly for all kinds of systems that use natural language as input. However, the systems summarized under this term are so diverse, that they often have very little in common with regard to technology, usage, and their theoretical background. In order to make such systems more comparable, we propose a framework that classifies chatbots based on six categories, which allow a meaningful comparison based on features which are relevant for developers, scientists, and users. Ultimately, we hope to support the scientific discourse, as well as the development of chatbots, by providing an instrument to classify and analyze different groups of chatbot systems regarding their requirements, possible evaluation strategies, available toolsets, and other common features.

   @inproceedings{Braun2019ChatbotClassification,
     title = {Towards a Framework for Classifying Chatbots},
     author = {Braun, Daniel and Matthes, Florian},
     editor = {INSTICC},
     isbn = {978-989-758-372-8},
     year = {2019},
     date = {2019-05-02},
     booktitle = {Proceedings of the 21th International Conference on Enterprise Information Systems (ICEIS 2019)},
     volume = {1},
     pages = {484-489},
     publisher = {SCITEPRESS},
     address = {Heraklion, Greece},
     keywords = {Chatbots},
     pubstate = {published},
     tppubtype = {inproceedings},
     doi = {10.5220/0007772704960501}
   }

2018

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

   Daniel Braun, Anne Faber, Adrian Hernandez-Mendez, and 1 more author

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

   Link Abs Bib PDF

   Understanding and analysing rapidly changing and growing business ecosystems, like smart city and mobility ecosystems, becomes increasingly difficult. However, the understanding of these ecosystems is the key to being successful for all involved parties, like companies and public institutions. Modern Natural Language Processing technologies can help to automatically identify and extract relevant information from sources like online news and blog articles and hence support the analysis of complex ecosystems. In this paper, we present an approach to automatically extract directed relations between entities within business ecosystems from online news and blog articles by using dependency parsing .

   @inproceedings{Br18e,
     title = {Automatic Relation Extraction for Building Smart City Ecosystems using Dependency Parsing},
     author = {Braun, Daniel and Faber, Anne and Hernandez-Mendez, Adrian and Matthes, Florian},
     year = {2018},
     date = {2018-11-14},
     booktitle = {Proceedings of the 2nd Workshop on Natural Language for Artificial Intelligence (NL4AI 2018)},
     keywords = {Dependency Parsing, Ecosystem, NLP, Smart City},
     url = {https://ceur-ws.org/Vol-2244/paper_03.pdf},
     pages = {29-39},
   }

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

   Daniel Braun, Ehud Reiter, and Advaith Siddharthan

   Natural Language Engineering. Cambridge University Press, 2018

   DOI Abs Bib

   Despite the long history of Natural Language Generation (NLG) research, the potential for influencing real world behaviour through automatically generated texts has not received much attention. In this paper, we present SaferDrive, a behaviour change support system that uses NLG and telematic data in order to create weekly textual feedback for automobile drivers, which is delivered through a smartphone application. Usage-based car insurances use sensors to track driver behaviour. Although the data collected by such insurances could provide detailed feedback about the driving style, they are typically withheld from the driver and used only to calculate insurance premiums. SaferDrive instead provides detailed textual feedback about the driving style, with the intent to help drivers improve their driving habits. We evaluate the system with real drivers and report that the textual feedback generated by our system does have a positive influence on driving habits, especially with regard to speeding.

   @article{braun_reiter_siddharthan_2018,
     title = {SaferDrive: An NLG-based behaviour change support system for drivers},
     author = {Braun, Daniel and Reiter, Ehud and Siddharthan, Advaith},
     editor = {Press, Cambridge University},
     doi = {10.1017/S1351324918000050},
     year = {2018},
     date = {2018-07-01},
     journal = {Natural Language Engineering},
     volume = {24},
     number = {4},
     pages = {551-588},
     publisher = {Cambridge University Press},
     keywords = {},
     pubstate = {published},
     tppubtype = {article}
   }

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

   Daniel Braun, Adrian Hernandez-Mendez, Anne Faber, and 2 more authors

   In Multikonferenz Wirtschaftsinformatik (MKWI) 2018. 2018

   Link Abs Bib

   The way we consume mobility is drastically changing. Mobility is no longer only provided by traditional public transport and goods we own, like cars and bicycles, but also by service providers which offer mobility as a service, like car sharing companies. This new mobility ecosystem enables more flexibility, but also introduces additional complexity, especially for intermodal travel, i.e. reaching one’s destination by using multiple means of transportation. In this paper, we present an approach to combine mobility services in a customer-centred way, which enables intermodal journey planning through an intuitive natural language interface. In contrast to other approaches, our architecture does not rely on the cooperation of mobility service providers, which has proven to be one of the main obstacles towards an integrated solution of multiple mobility services in the past.

   @inproceedings{Braun2018b,
     title = {Customer-Centred Intermodal Combination of Mobility Services with Conversational Interfaces},
     author = {Braun, Daniel and Hernandez-Mendez, Adrian and Faber, Anne and Langen, Manfred and Matthes, Florian},
     editor = {Drews, Paul and Funk, Burkhardt and Niemeyer, Peter and Xie, Lin},
     url = {http://mkwi2018.leuphana.de/wp-content/uploads/MKWI_277.pdf},
     isbn = {978-3-935786-72-0},
     year = {2018},
     date = {2018-03-06},
     booktitle = {Multikonferenz Wirtschaftsinformatik (MKWI) 2018},
     volume = {4},
     organization = {Leuphana Universität Lüneburg},
     keywords = {VSS},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

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

   Daniel Braun, and Florian Matthes

   In Software Engineering und Software Management 2018. Gesellschaft für Informatik, 2018

   DOI Abs Bib

   Usage-based insurances are becoming more and more popular, especially for cars. We present an approach to use Natural Language Generation (NLG) in order to explain customers which aspects of their behaviour influenced the assessment which is performed by these insurances.

   @inproceedings{mci/Braun2018,
     title = {Generating Explanations for Algorithmic Decisions of Usage-Based Insurances using Natural Language Generation},
     author = {Braun, Daniel and Matthes, Florian},
     editor = {Tichy, Matthias and Bodden, Eric and Kuhrmann, Marco and Wagner, Stefan and Steghöfer, Jan-Philipp},
     doi = {20.500.12116/16354},
     isbn = {978-3-88579-673-2},
     year = {2018},
     date = {2018-03-01},
     booktitle = {Software Engineering und Software Management 2018},
     pages = {219-220},
     publisher = {Gesellschaft für Informatik},
     address = {Bonn},
     series = {Lecture Notes in Informatics (LNI)},
     keywords = {},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

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

   Daniel Braun, Elena Scepankova, Patrick Holl, and 1 more author

   In Tagungsband Internationales Rechtsinformatik Symposium (IRIS) 2018. Editions Weblaw, 2018

   Link Abs Bib

   Customers are regularly confronted with complex standard form contracts, especially online. Most of the time, customers do not read these contracts at all and even if they try, they are not always able to understand them. In this paper, we present a technological approach to address this imbalance of powers between customers and companies and a prototypically implementation which analyses, assesses, and summarizes terms of services from German web shops.

   @inproceedings{Braun2018LegalTech,
     title = {Customer-centered LegalTech: Automated Analysis of Standard Form Contracts},
     author = {Braun, Daniel and Scepankova, Elena and Holl, Patrick and Matthes, Florian},
     url = {http://jusletter-it.weblaw.ch/issues/2018/IRIS/customer-centered-le_86c0d312a1.html},
     year = {2018},
     date = {2018-02-22},
     booktitle = {Tagungsband Internationales Rechtsinformatik Symposium (IRIS) 2018},
     pages = {627-634},
     publisher = {Editions Weblaw},
     keywords = {legaltech},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

2017

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

   Daniel Braun, Elena Scepankova, Patrick Holl, and 1 more author

   In Proceedings of the 10th International Conference on Natural Language Generation. 2017

   DOI Link Bib

   @inproceedings{W17-3528,
     title = {SaToS: Assessing and Summarising Terms of Services from German Webshops},
     author = {Braun, Daniel and Scepankova, Elena and Holl, Patrick and Matthes, Florian},
     url = {http://aclweb.org/anthology/W17-3528},
     doi = {10.18653/v1/W17-3534},
     year = {2017},
     date = {2017-09-01},
     booktitle = {Proceedings of the 10th International Conference on Natural Language Generation},
     pages = {223--227},
     address = {Santiago de Compostela, Spain},
     organization = {Association for Computational Linguistics },
     keywords = {},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

2. Evaluating Natural Language Understanding Services for Conversational Question Answering Systems

   Daniel Braun, Adrian Hernandez-Mendez, Florian Matthes, and 1 more author

   In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue. Association for Computational Linguistics, 2017

   DOI Link Abs Bib

   Conversational interfaces recently gained a lot of attention. One of the reasons for the current hype is the fact that chatbots (one particularly popular form of conversational interfaces) nowadays can be created without any programming knowledge, thanks to different toolkits and so-called Natural Language Understanding (NLU) services. While these NLU services are already widely used in both, industry and science, so far, they have not been analysed systematically. In this paper, we present a method to evaluate the classification performance of NLU services. Moreover, we present two new corpora, one consisting of annotated questions and one consisting of annotated questions with the corresponding answers. Based on these corpora, we conduct an evaluation of some of the most popular NLU services. Thereby we want to enable both, researchers and companies to make more educated decisions about which service they should use.

   @inproceedings{braun-EtAl:2017:SIGDIAL,
     title = {Evaluating Natural Language Understanding Services for Conversational Question Answering Systems},
     author = {Braun, Daniel and Hernandez-Mendez, Adrian and Matthes, Florian and Langen, Manfred},
     url = {http://www.aclweb.org/anthology/W17-3622},
     doi = {10.18653/v1/W17-5522},
     year = {2017},
     date = {2017-08-01},
     booktitle = {Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue},
     pages = {174--185},
     publisher = {Association for Computational Linguistics},
     address = {Saarbrücken, Germany},
     keywords = {},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

3. Towards a Context-Aware Vertical Social Software Ecosystem

   Adrian Hernandez-Mendez, Daniel Braun, Florian Matthes, and 1 more author

   In 2017 IEEE 19th Conference on Business Informatics (CBI). 2017

   DOI Abs Bib

   Advances in software and hardware technology open up new potential for context-aware vertical social software. Companies are facing the challenge to incorporate these ideas into their existing software solutions. In this paper, we propose a reference architecture for Context-Aware Vertical Social Software platforms to facilitate reuse and enable synergies across different existing and new social software applications and workflows. This architecture enables external software developers to meet the needs of improving existing products and services of companies. Moreover, we present the lessons we learned from the implementation of such a platform and two case studies in collaboration with a large industry partner.

   @inproceedings{8012943,
     title = {Towards a Context-Aware Vertical Social Software Ecosystem},
     author = {Hernandez-Mendez, Adrian and Braun, Daniel and Matthes, Florian and Langen, Manfred},
     doi = {10.1109/CBI.2017.7},
     year = {2017},
     date = {2017-07-01},
     booktitle = {2017 IEEE 19th Conference on Business Informatics (CBI)},
     volume = {02},
     pages = {76-82},
     keywords = {Collaboration;Companies;Computer architecture;Ecosystems;Instant messaging;Software},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

4. Improving Thesauri Using Word Embeddings and a Novel Intersection Method

   Jörg Landthaler, Bernhard Waltl, Dominik Huth, and 4 more authors

   In Proceedings of the Second Workshop on Automated Semantic Analysis of Information in Legal Texts. 2017

   Link Bib

   @inproceedings{Landthaler2018,
     title = {Improving Thesauri Using Word Embeddings and a Novel Intersection Method},
     author = {Landthaler, Jörg and Waltl, Bernhard and Huth, Dominik and Braun, Daniel and Matthes, Florian and Stocker, Christoph and Geiger, Thomas},
     editor = {CEUR-WS.org},
     url = {http://ceur-ws.org/Vol-2143/paper6.pdf},
     issn = {1613-0073},
     year = {2017},
     date = {2017-06-23},
     booktitle = {Proceedings of the Second Workshop on Automated Semantic Analysis of Information in Legal Texts},
     keywords = {legaltech},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

2015

1. Creating Textual Driver Feedback from Telemetric Data

   Daniel Braun, Ehud Reiter, and Advaith Siddharthan

   In Proceedings of the 15th European Workshop on Natural Language Generation (ENLG). Association for Computational Linguistics, 2015

   DOI Link Bib

   @inproceedings{braun2015enlg,
     title = {Creating Textual Driver Feedback from Telemetric Data},
     author = {Braun, Daniel and Reiter, Ehud and Siddharthan, Advaith},
     url = {http://aclanthology.coli.uni-saarland.de/pdf/W/W15/W15-4726.pdf},
     doi = {10.18653/v1/W15-4726},
     year = {2015},
     date = {2015-01-01},
     booktitle = {Proceedings of the 15th European Workshop on Natural Language Generation (ENLG)},
     pages = {156--165},
     publisher = {Association for Computational Linguistics},
     address = {Brighton, UK},
     organization = {Association for Computational Linguistics},
     keywords = {},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

2012

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

   Christoph Endres, Rafael Math, and Daniel Braun

   In Adjunct Proceedings of the 4th International Conference on Automotive User Interfaces and Interactive Vehicular Applications. 2012

   Bib

   @inproceedings{endres2012simulator,
     title = {Simulator-based evaluation on the impact of visual complexity and speed on driver’s cognitive load},
     author = {Endres, Christoph and Math, Rafael and Braun, Daniel},
     year = {2012},
     date = {2012-01-01},
     booktitle = {Adjunct Proceedings of the 4th International Conference on Automotive User Interfaces and Interactive Vehicular Applications},
     pages = {30--31},
     keywords = {},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

2011

1. Prototyping a Semi-Automatic In-Car Texting Assistant

   Christoph Endres, Daniel Braun, and Christian Müller

   In Proceedings of the 3rd Workshop on Multimodal Interfaces for Automotive Applications (MIAA 2011). 2011

   Bib

   @inproceedings{endres2011prototyping,
     title = {Prototyping a Semi-Automatic In-Car Texting Assistant},
     author = {Endres, Christoph and Braun, Daniel and Müller, Christian},
     year = {2011},
     date = {2011-01-01},
     booktitle = {Proceedings of the 3rd Workshop on Multimodal Interfaces for Automotive Applications (MIAA 2011)},
     pages = {57--60},
     keywords = {},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

2. Determination of Mobility Context using Low-Level Data

   Daniel Braun, Christoph Endres, and Christian Müller

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

   Bib

   @inproceedings{braun2011determination,
     title = {Determination of Mobility Context using Low-Level Data},
     author = {Braun, Daniel and Endres, Christoph and Müller, Christian},
     year = {2011},
     date = {2011-01-01},
     booktitle = {Adjunct Proceedings of the 3rd International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI 2011)},
     pages = {41--42},
     keywords = {},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

2010

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

   Christoph Endres, and Daniel Braun

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

   Bib

   @inproceedings{endres2010pleopatra,
     title = {Pleopatra: A semi-automatic status-posting prototype for future in-car use},
     author = {Endres, Christoph and Braun, Daniel},
     year = {2010},
     date = {2010-01-01},
     booktitle = {Adjunct proceedings of the 2nd International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI 2010)},
     pages = {7},
     keywords = {},
     pubstate = {published},
     tppubtype = {inproceedings}
   }

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

   Christoph Endres, Jan Miksatko, and Daniel Braun

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

   Bib

   @inproceedings{endres2010youldeco,
     title = {Youldeco-Exploiting the Power of Online Social Networks for Eco-Friendly Driving},
     author = {Endres, Christoph and Miksatko, Jan and Braun, Daniel},
     year = {2010},
     date = {2010-01-01},
     booktitle = {Adjunct proceedings of the 2nd International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI 2010)},
     pages = {5},
     keywords = {},
     pubstate = {published},
     tppubtype = {inproceedings}
   }