@inbook{45882, author = {{Bäumer, Frederik Simon and Chen, Wei-Fan and Geierhos, Michaela and Kersting, Joschka and Wachsmuth, Henning}}, booktitle = {{On-The-Fly Computing -- Individualized IT-services in dynamic markets}}, editor = {{Haake, Claus-Jochen and Meyer auf der Heide, Friedhelm and Platzner, Marco and Wachsmuth, Henning and Wehrheim, Heike}}, pages = {{65--84}}, publisher = {{Heinz Nixdorf Institut, Universität Paderborn}}, title = {{{Dialogue-based Requirement Compensation and Style-adjusted Data-to-text Generation}}}, doi = {{10.5281/zenodo.8068456}}, volume = {{412}}, year = {{2023}}, } @inbook{46205, abstract = {{We present a concept for quantifying evaluative phrases to later compare rating texts numerically instead of just relying on stars or grades. We achievethis by combining deep learning models in an aspect-based sentiment analysis pipeline along with sentiment weighting, polarity, and correlation analyses that combine deep learning results with metadata. The results provide new insights for the medical field. Our application domain, physician reviews, shows that there are millions of review texts on the Internet that cannot yet be comprehensively analyzed because previous studies have focused on explicit aspects from other domains (e.g., products). We identify, extract, and classify implicit and explicit aspect phrases equally from German-language review texts. To do so, we annotated aspect phrases representing reviews on numerous aspects of a physician, medical practice, or practice staff. We apply the best performing transformer model, XLM-RoBERTa, to a large physician review dataset and correlate the results with existing metadata. As a result, we can show different correlations between the sentiment polarity of certain aspect classes (e.g., friendliness, practice equipment) and physicians’ professions (e.g., surgeon, ophthalmologist). As a result, we have individual numerical scores that contain a variety of information based on deep learning algorithms that extract textual (evaluative) information and metadata from the Web.}}, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Data Management Technologies and Applications}}, editor = {{Cuzzocrea, Alfredo and Gusikhin, Oleg and Hammoudi, Slimane and Quix, Christoph}}, isbn = {{9783031378898}}, issn = {{1865-0929}}, pages = {{45--65}}, publisher = {{Springer Nature Switzerland}}, title = {{{Towards Comparable Ratings: Quantifying Evaluative Phrases in Physician Reviews}}}, doi = {{10.1007/978-3-031-37890-4_3}}, volume = {{1860}}, year = {{2023}}, } @book{45863, abstract = {{In the proposal for our CRC in 2011, we formulated a vision of markets for IT services that describes an approach to the provision of such services that was novel at that time and, to a large extent, remains so today: „Our vision of on-the-fly computing is that of IT services individually and automatically configured and brought to execution from flexibly combinable services traded on markets. At the same time, we aim at organizing markets whose participants maintain a lively market of services through appropriate entrepreneurial actions.“ Over the last 12 years, we have developed methods and techniques to address problems critical to the convenient, efficient, and secure use of on-the-fly computing. Among other things, we have made the description of services more convenient by allowing natural language input, increased the quality of configured services through (natural language) interaction and more efficient configuration processes and analysis procedures, made the quality of (the products of) providers in the marketplace transparent through reputation systems, and increased the resource efficiency of execution through reconfigurable heterogeneous computing nodes and an integrated treatment of service description and configuration. We have also developed network infrastructures that have a high degree of adaptivity, scalability, efficiency, and reliability, and provide cryptographic guarantees of anonymity and security for market participants and their products and services. To demonstrate the pervasiveness of the OTF computing approach, we have implemented a proof-of-concept for OTF computing that can run typical scenarios of an OTF market. We illustrated the approach using a cutting-edge application scenario – automated machine learning (AutoML). Finally, we have been pushing our work for the perpetuation of On-The-Fly Computing beyond the SFB and sharing the expertise gained in the SFB in events with industry partners as well as transfer projects. This work required a broad spectrum of expertise. Computer scientists and economists with research interests such as computer networks and distributed algorithms, security and cryptography, software engineering and verification, configuration and machine learning, computer engineering and HPC, microeconomics and game theory, business informatics and management have successfully collaborated here.}}, author = {{Haake, Claus-Jochen and Meyer auf der Heide, Friedhelm and Platzner, Marco and Wachsmuth, Henning and Wehrheim, Heike}}, pages = {{247}}, publisher = {{Heinz Nixdorf Institut, Universität Paderborn}}, title = {{{On-The-Fly Computing -- Individualized IT-services in dynamic markets}}}, doi = {{10.17619/UNIPB/1-1797}}, volume = {{412}}, year = {{2023}}, } @inproceedings{33274, author = {{Chen, Wei-Fan and Chen, Mei-Hua and Mudgal, Garima and Wachsmuth, Henning}}, booktitle = {{Proceedings of the 9th Workshop on Argument Mining (ArgMining 2022)}}, pages = {{51 -- 61}}, title = {{{Analyzing Culture-Specific Argument Structures in Learner Essays}}}, year = {{2022}}, } @inbook{32179, abstract = {{This work addresses the automatic resolution of software requirements. In the vision of On-The-Fly Computing, software services should be composed on demand, based solely on natural language input from human users. To enable this, we build a chatbot solution that works with human-in-the-loop support to receive, analyze, correct, and complete their software requirements. The chatbot is equipped with a natural language processing pipeline and a large knowledge base, as well as sophisticated dialogue management skills to enhance the user experience. Previous solutions have focused on analyzing software requirements to point out errors such as vagueness, ambiguity, or incompleteness. Our work shows how apps can collaborate with users to efficiently produce correct requirements. We developed and compared three different chatbot apps that can work with built-in knowledge. We rely on ChatterBot, DialoGPT and Rasa for this purpose. While DialoGPT provides its own knowledge base, Rasa is the best system to combine the text mining and knowledge solutions at our disposal. The evaluation shows that users accept 73% of the suggested answers from Rasa, while they accept only 63% from DialoGPT or even 36% from ChatterBot.}}, author = {{Kersting, Joschka and Ahmed, Mobeen and Geierhos, Michaela}}, booktitle = {{HCI International 2022 Posters}}, editor = {{Stephanidis, Constantine and Antona, Margherita and Ntoa, Stavroula}}, isbn = {{9783031064166}}, issn = {{1865-0929}}, keywords = {{On-The-Fly Computing, Chatbot, Knowledge Base}}, location = {{Virtual}}, pages = {{419----426}}, publisher = {{Springer International Publishing}}, title = {{{Chatbot-Enhanced Requirements Resolution for Automated Service Compositions}}}, doi = {{10.1007/978-3-031-06417-3_56}}, volume = {{1580}}, year = {{2022}}, } @inproceedings{31054, abstract = {{This paper aims at discussing past limitations set in sentiment analysis research regarding explicit and implicit mentions of opinions. Previous studies have regularly neglected this question in favor of methodical research on standard-datasets. Furthermore, they were limited to linguistically less-diverse domains, such as commercial product reviews. We face this issue by annotating a German-language physician review dataset that contains numerous implicit, long, and complex statements that indicate aspect ratings, such as the physician’s friendliness. We discuss the nature of implicit statements and present various samples to illustrate the challenge described.}}, author = {{Kersting, Joschka and Bäumer, Frederik Simon}}, booktitle = {{Proceedings of the Fourteenth International Conference on Pervasive Patterns and Applications (PATTERNS 2022): Special Track AI-DRSWA: Maturing Artificial Intelligence - Data Science for Real-World Applications}}, editor = {{Kersting, Joschka}}, keywords = {{Sentiment analysis, Natural language processing, Aspect phrase extraction}}, location = {{Barcelona, Spain}}, pages = {{5--9}}, publisher = {{IARIA}}, title = {{{Implicit Statements in Healthcare Reviews: A Challenge for Sentiment Analysis}}}, year = {{2022}}, } @inproceedings{31068, author = {{Chen, Mei-Hua and Mudgal, Garima and Chen, Wei-Fan and Wachsmuth, Henning}}, booktitle = {{EUROCALL}}, title = {{{Investigating the argumentation structures of EFL learners from diverse language backgrounds}}}, year = {{2022}}, } @inproceedings{26049, abstract = {{Content is the new oil. Users consume billions of terabytes a day while surfing on news sites or blogs, posting on social media sites, and sending chat messages around the globe. While content is heterogeneous, the dominant form of web content is text. There are situations where more diversity needs to be introduced into text content, for example, to reuse it on websites or to allow a chatbot to base its models on the information conveyed rather than of the language used. In order to achieve this, paraphrasing techniques have been developed: One example is Text spinning, a technique that automatically paraphrases text while leaving the intent intact. This makes it easier to reuse content, or to change the language generated by the bot more human. One method for modifying texts is a combination of translation and back-translation. This paper presents NATTS, a naive approach that uses transformer-based translation models to create diversified text, combining translation steps in one model. An advantage of this approach is that it can be fine-tuned and handle technical language.}}, author = {{Bäumer, Frederik Simon and Kersting, Joschka and Denisov, Sergej and Geierhos, Michaela}}, booktitle = {{PROCEEDINGS OF THE INTERNATIONAL CONFERENCES ON WWW/INTERNET 2021 AND APPLIED COMPUTING 2021}}, keywords = {{Software Requirements, Natural Language Processing, Transfer Learning, On-The-Fly Computing}}, location = {{Lisbon, Portugal}}, pages = {{221----225}}, publisher = {{IADIS}}, title = {{{IN OTHER WORDS: A NAIVE APPROACH TO TEXT SPINNING}}}, year = {{2021}}, } @inbook{17905, abstract = {{This chapter concentrates on aspect-based sentiment analysis, a form of opinion mining where algorithms detect sentiments expressed about features of products, services, etc. We especially focus on novel approaches for aspect phrase extraction and classification trained on feature-rich datasets. Here, we present two new datasets, which we gathered from the linguistically rich domain of physician reviews, as other investigations have mainly concentrated on commercial reviews and social media reviews so far. To give readers a better understanding of the underlying datasets, we describe the annotation process and inter-annotator agreement in detail. In our research, we automatically assess implicit mentions or indications of specific aspects. To do this, we propose and utilize neural network models that perform the here-defined aspect phrase extraction and classification task, achieving F1-score values of about 80% and accuracy values of more than 90%. As we apply our models to a comparatively complex domain, we obtain promising results. }}, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Natural Language Processing in Artificial Intelligence -- NLPinAI 2020}}, editor = {{Loukanova, Roussanka}}, pages = {{163----189 }}, publisher = {{Springer}}, title = {{{Towards Aspect Extraction and Classification for Opinion Mining with Deep Sequence Networks}}}, doi = {{10.1007/978-3-030-63787-3_6}}, volume = {{939}}, year = {{2021}}, } @inproceedings{22051, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Proceedings of the 10th International Conference on Data Science, Technology and Applications (DATA 2021)}}, location = {{Online}}, pages = {{275----284}}, publisher = {{SCITEPRESS}}, title = {{{Well-being in Plastic Surgery: Deep Learning Reveals Patients' Evaluations}}}, year = {{2021}}, } @inbook{22052, abstract = {{In this study, we describe a text processing pipeline that transforms user-generated text into structured data. To do this, we train neural and transformer-based models for aspect-based sentiment analysis. As most research deals with explicit aspects from product or service data, we extract and classify implicit and explicit aspect phrases from German-language physician review texts. Patients often rate on the basis of perceived friendliness or competence. The vocabulary is difficult, the topic sensitive, and the data user-generated. The aspect phrases come with various wordings using insertions and are not noun-based, which makes the presented case equally relevant and reality-based. To find complex, indirect aspect phrases, up-to-date deep learning approaches must be combined with supervised training data. We describe three aspect phrase datasets, one of them new, as well as a newly annotated aspect polarity dataset. Alongside this, we build an algorithm to rate the aspect phrase importance. All in all, we train eight transformers on the new raw data domain, compare 54 neural aspect extraction models and, based on this, create eight aspect polarity models for our pipeline. These models are evaluated by using Precision, Recall, and F-Score measures. Finally, we evaluate our aspect phrase importance measure algorithm.}}, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Natural Language Processing and Information Systems}}, editor = {{Kapetanios, Epaminondas and Horacek, Helmut and Métais, Elisabeth and Meziane, Farid}}, location = {{Saarbrücken, Germany}}, pages = {{231----242}}, publisher = {{Springer}}, title = {{{Human Language Comprehension in Aspect Phrase Extraction with Importance Weighting}}}, volume = {{12801}}, year = {{2021}}, } @inproceedings{21178, abstract = {{When engaging in argumentative discourse, skilled human debaters tailor claims to the beliefs of the audience, to construct effective arguments. Recently, the field of computational argumentation witnessed extensive effort to address the automatic generation of arguments. However, existing approaches do not perform any audience-specific adaptation. In this work, we aim to bridge this gap by studying the task of belief-based claim generation: Given a controversial topic and a set of beliefs, generate an argumentative claim tailored to the beliefs. To tackle this task, we model the people's prior beliefs through their stances on controversial topics and extend state-of-the-art text generation models to generate claims conditioned on the beliefs. Our automatic evaluation confirms the ability of our approach to adapt claims to a set of given beliefs. In a manual study, we additionally evaluate the generated claims in terms of informativeness and their likelihood to be uttered by someone with a respective belief. Our results reveal the limitations of modeling users' beliefs based on their stances, but demonstrate the potential of encoding beliefs into argumentative texts, laying the ground for future exploration of audience reach.}}, author = {{Alshomary, Milad and Chen, Wei-Fan and Gurcke, Timon and Wachsmuth, Henning}}, booktitle = {{Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume}}, location = {{Online}}, pages = {{224--223}}, publisher = {{Association for Computational Linguistics}}, title = {{{Belief-based Generation of Argumentative Claims}}}, year = {{2021}}, } @inproceedings{23709, author = {{Chen, Wei-Fan and Al Khatib, Khalid and Stein, Benno and Wachsmuth, Henning}}, booktitle = {{Findings of the Association for Computational Linguistics: EMNLP 2021}}, pages = {{2683 -- 2693}}, title = {{{Controlled Neural Sentence-Level Reframing of News Articles}}}, year = {{2021}}, } @inproceedings{22229, author = {{Alshomary, Milad and Syed, Shahbaz and Potthast, Martin and Wachsmuth, Henning}}, booktitle = {{Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021)}}, location = {{Online}}, pages = {{1816–1827}}, publisher = {{Association for Computational Linguistics}}, title = {{{Argument Undermining: Counter-Argument Generation by Attacking Weak Premises}}}, doi = {{10.18653/v1/2021.findings-acl.159}}, year = {{2021}}, } @inbook{17347, abstract = {{Peer-to-Peer news portals allow Internet users to write news articles and make them available online to interested readers. Despite the fact that authors are free in their choice of topics, there are a number of quality characteristics that an article must meet before it is published. In addition to meaningful titles, comprehensibly written texts and meaning- ful images, relevant tags are an important criteria for the quality of such news. In this case study, we discuss the challenges and common mistakes that Peer-to-Peer reporters face when tagging news and how incorrect information can be corrected through the orchestration of existing Natu- ral Language Processing services. Lastly, we use this illustrative example to give insight into the challenges of dealing with bottom-up taxonomies.}}, author = {{Bäumer, Frederik Simon and Kersting, Joschka and Buff, Bianca and Geierhos, Michaela}}, booktitle = {{Information and Software Technologies}}, editor = {{Audrius, Lopata and Rita, Butkienė and Daina, Gudonienė and Vilma, Sukackė}}, location = {{Kaunas, Litauen}}, pages = {{368----382}}, publisher = {{Springer}}, title = {{{Tag Me If You Can: Insights into the Challenges of Supporting Unrestricted P2P News Tagging}}}, doi = {{https://doi.org/10.1007/978-3-030-59506-7_30}}, volume = {{1283}}, year = {{2020}}, } @inproceedings{18686, author = {{Kersting, Joschka and Bäumer, Frederik Simon}}, booktitle = {{PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON APPLIED COMPUTING 2020}}, keywords = {{Software Requirements, Natural Language Processing, Transfer Learning, On-The-Fly Computing}}, location = {{Lisbon, Portugal}}, pages = {{119----123}}, publisher = {{IADIS}}, title = {{{SEMANTIC TAGGING OF REQUIREMENT DESCRIPTIONS: A TRANSFORMER-BASED APPROACH}}}, year = {{2020}}, } @inproceedings{15580, abstract = {{This paper deals with aspect phrase extraction and classification in sentiment analysis. We summarize current approaches and datasets from the domain of aspect-based sentiment analysis. This domain detects sentiments expressed for individual aspects in unstructured text data. So far, mainly commercial user reviews for products or services such as restaurants were investigated. We here present our dataset consisting of German physician reviews, a sensitive and linguistically complex field. Furthermore, we describe the annotation process of a dataset for supervised learning with neural networks. Moreover, we introduce our model for extracting and classifying aspect phrases in one step, which obtains an F1-score of 80%. By applying it to a more complex domain, our approach and results outperform previous approaches.}}, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Proceedings of the 12th International Conference on Agents and Artificial Intelligence (ICAART 2020) -- Special Session on Natural Language Processing in Artificial Intelligence (NLPinAI 2020)}}, keywords = {{Deep Learning, Natural Language Processing, Aspect-based Sentiment Analysis}}, location = {{Valetta, Malta}}, pages = {{391----400}}, publisher = {{SCITEPRESS}}, title = {{{Aspect Phrase Extraction in Sentiment Analysis with Deep Learning}}}, year = {{2020}}, } @inproceedings{15582, abstract = {{When it comes to increased digitization in the health care domain, privacy is a relevant topic nowadays. This relates to patient data, electronic health records or physician reviews published online, for instance. There exist different approaches to the protection of individuals’ privacy, which focus on the anonymization and masking of personal information subsequent to their mining. In the medical domain in particular, measures to protect the privacy of patients are of high importance due to the amount of sensitive data that is involved (e.g. age, gender, illnesses, medication). While privacy breaches in structured data can be detected more easily, disclosure in written texts is more difficult to find automatically due to the unstructured nature of natural language. Therefore, we take a detailed look at existing research on areas related to privacy protection. Likewise, we review approaches to the automatic detection of privacy disclosure in different types of medical data. We provide a survey of several studies concerned with privacy breaches in the medical domain with a focus on Physician Review Websites (PRWs). Finally, we briefly develop implications and directions for further research.}}, author = {{Buff, Bianca and Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2020)}}, keywords = {{Identity Disclosure, Privacy Protection, Physician Review Website, De-Anonymization, Medical Domain}}, location = {{Valetta, Malta}}, pages = {{630----637}}, publisher = {{SCITEPRESS}}, title = {{{Detection of Privacy Disclosure in the Medical Domain: A Survey}}}, year = {{2020}}, } @inproceedings{15635, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Proceedings of the 33rd International Florida Artificial Intelligence Research Symposium (FLAIRS) Conference}}, location = {{North Miami Beach, FL, USA}}, pages = {{282----285}}, publisher = {{AAAI}}, title = {{{Neural Learning for Aspect Phrase Extraction and Classification in Sentiment Analysis}}}, year = {{2020}}, } @article{15025, abstract = {{In software engineering, the imprecise requirements of a user are transformed to a formal requirements specification during the requirements elicitation process. This process is usually guided by requirements engineers interviewing the user. We want to partially automate this first step of the software engineering process in order to enable users to specify a desired software system on their own. With our approach, users are only asked to provide exemplary behavioral descriptions. The problem of synthesizing a requirements specification from examples can partially be reduced to the problem of grammatical inference, to which we apply an active coevolutionary learning approach. However, this approach would usually require many feedback queries to be sent to the user. In this work, we extend and generalize our active learning approach to receive knowledge from multiple oracles, also known as proactive learning. The ‘user oracle’ represents input received from the user and the ‘knowledge oracle’ represents available, formalized domain knowledge. We call our two-oracle approach the ‘first apply knowledge then query’ (FAKT/Q) algorithm. We compare FAKT/Q to the active learning approach and provide an extensive benchmark evaluation. As result we find that the number of required user queries is reduced and the inference process is sped up significantly. Finally, with so-called On-The-Fly Markets, we present a motivation and an application of our approach where such knowledge is available.}}, author = {{Wever, Marcel Dominik and van Rooijen, Lorijn and Hamann, Heiko}}, journal = {{Evolutionary Computation}}, number = {{2}}, pages = {{165–193}}, publisher = {{MIT Press Journals}}, title = {{{Multi-Oracle Coevolutionary Learning of Requirements Specifications from Examples in On-The-Fly Markets}}}, doi = {{10.1162/evco_a_00266}}, volume = {{28}}, year = {{2020}}, }