@inproceedings{KloeserKohlKraftetal.2021, author = {Kl{\"o}ser, Lars and Kohl, Philipp and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {Multi-attribute relation extraction (MARE): simplifying the application of relation extraction}, series = {Proceedings of the 2nd International Conference on Deep Learning Theory and Applications DeLTA - Volume 1}, booktitle = {Proceedings of the 2nd International Conference on Deep Learning Theory and Applications DeLTA - Volume 1}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-526-5}, doi = {10.5220/0010559201480156}, pages = {148 -- 156}, year = {2021}, abstract = {Natural language understanding's relation extraction makes innovative and encouraging novel business concepts possible and facilitates new digitilized decision-making processes. Current approaches allow the extraction of relations with a fixed number of entities as attributes. Extracting relations with an arbitrary amount of attributes requires complex systems and costly relation-trigger annotations to assist these systems. We introduce multi-attribute relation extraction (MARE) as an assumption-less problem formulation with two approaches, facilitating an explicit mapping from business use cases to the data annotations. Avoiding elaborated annotation constraints simplifies the application of relation extraction approaches. The evaluation compares our models to current state-of-the-art event extraction and binary relation extraction methods. Our approaches show improvement compared to these on the extraction of general multi-attribute relations.}, language = {en} } @article{JungStaat2020, author = {Jung, Alexander and Staat, Manfred}, title = {Erratum to "Modeling and simulation of human induced pluripotent stem cell-derived cardiac tissue" [GAMM-Mitteilungen, (2019), 42, 4, 10.1002/gamm.201900002]}, series = {GAMM-Mitteilungen}, volume = {43}, journal = {GAMM-Mitteilungen}, number = {4}, publisher = {Wiley-VCH GmbH}, address = {Weinheim}, issn = {1522-2608}, doi = {10.1002/gamm.202000011}, year = {2020}, language = {en} } @misc{JungMuellerStaat2021, author = {Jung, Alexander and M{\"u}ller, Wolfram and Staat, Manfred}, title = {Corrigendum to "Wind and fairness in ski jumping: A computer modelling analysis" [J. Biomech. 75 (2018) 147-153]}, series = {Journal of Biomechanics}, volume = {128}, journal = {Journal of Biomechanics}, number = {Article number: 110690}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0021-9290}, doi = {10.1016/j.jbiomech.2021.110690}, pages = {1 Seite}, year = {2021}, language = {en} } @article{HeelDiktaBraekers2021, author = {Heel, Mareike van and Dikta, Gerhard and Braekers, Roel}, title = {Bootstrap based goodness‑of‑fit tests for binary multivariate regression models}, series = {Journal of the Korean Statistical Society}, volume = {51}, journal = {Journal of the Korean Statistical Society}, publisher = {Springer Nature}, address = {Singapur}, issn = {2005-2863 (Online)}, doi = {10.1007/s42952-021-00142-4}, pages = {28 Seiten}, year = {2021}, abstract = {We consider a binary multivariate regression model where the conditional expectation of a binary variable given a higher-dimensional input variable belongs to a parametric family. Based on this, we introduce a model-based bootstrap (MBB) for higher-dimensional input variables. This test can be used to check whether a sequence of independent and identically distributed observations belongs to such a parametric family. The approach is based on the empirical residual process introduced by Stute (Ann Statist 25:613-641, 1997). In contrast to Stute and Zhu's approach (2002) Stute \& Zhu (Scandinavian J Statist 29:535-545, 2002), a transformation is not required. Thus, any problems associated with non-parametric regression estimation are avoided. As a result, the MBB method is much easier for users to implement. To illustrate the power of the MBB based tests, a small simulation study is performed. Compared to the approach of Stute \& Zhu (Scandinavian J Statist 29:535-545, 2002), the simulations indicate a slightly improved power of the MBB based method. Finally, both methods are applied to a real data set.}, language = {en} } @book{DiktaScheer2021, author = {Dikta, Gerhard and Scheer, Marsel}, title = {Bootstrap Methods: With Applications in R}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-73480-0}, doi = {10.1007/978-3-030-73480-0}, pages = {XVI, 256 Seiten}, year = {2021}, abstract = {This book provides a compact introduction to the bootstrap method. In addition to classical results on point estimation and test theory, multivariate linear regression models and generalized linear models are covered in detail. Special attention is given to the use of bootstrap procedures to perform goodness-of-fit tests to validate model or distributional assumptions. In some cases, new methods are presented here for the first time. The text is motivated by practical examples and the implementations of the corresponding algorithms are always given directly in R in a comprehensible form. Overall, R is given great importance throughout. Each chapter includes a section of exercises and, for the more mathematically inclined readers, concludes with rigorous proofs. The intended audience is graduate students who already have a prior knowledge of probability theory and mathematical statistics.}, language = {en} } @inproceedings{SchmidtsKraftWinkensetal.2021, author = {Schmidts, Oliver and Kraft, Bodo and Winkens, Marvin and Z{\"u}ndorf, Albert}, title = {Catalog integration of heterogeneous and volatile product data}, series = {DATA 2020: Data Management Technologies and Applications}, booktitle = {DATA 2020: Data Management Technologies and Applications}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-83013-7}, doi = {10.1007/978-3-030-83014-4_7}, pages = {134 -- 153}, year = {2021}, abstract = {The integration of frequently changing, volatile product data from different manufacturers into a single catalog is a significant challenge for small and medium-sized e-commerce companies. They rely on timely integrating product data to present them aggregated in an online shop without knowing format specifications, concept understanding of manufacturers, and data quality. Furthermore, format, concepts, and data quality may change at any time. Consequently, integrating product catalogs into a single standardized catalog is often a laborious manual task. Current strategies to streamline or automate catalog integration use techniques based on machine learning, word vectorization, or semantic similarity. However, most approaches struggle with low-quality or real-world data. We propose Attribute Label Ranking (ALR) as a recommendation engine to simplify the integration process of previously unknown, proprietary tabular format into a standardized catalog for practitioners. We evaluate ALR by focusing on the impact of different neural network architectures, language features, and semantic similarity. Additionally, we consider metrics for industrial application and present the impact of ALR in production and its limitations.}, language = {en} } @inproceedings{KohlSchmidtsKloeseretal.2021, author = {Kohl, Philipp and Schmidts, Oliver and Kl{\"o}ser, Lars and Werth, Henri and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {STAMP 4 NLP - an agile framework for rapid quality-driven NLP applications development}, series = {Quality of Information and Communications Technology. QUATIC 2021}, booktitle = {Quality of Information and Communications Technology. QUATIC 2021}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-85346-4}, doi = {10.1007/978-3-030-85347-1_12}, pages = {156 -- 166}, year = {2021}, abstract = {The progress in natural language processing (NLP) research over the last years, offers novel business opportunities for companies, as automated user interaction or improved data analysis. Building sophisticated NLP applications requires dealing with modern machine learning (ML) technologies, which impedes enterprises from establishing successful NLP projects. Our experience in applied NLP research projects shows that the continuous integration of research prototypes in production-like environments with quality assurance builds trust in the software and shows convenience and usefulness regarding the business goal. We introduce STAMP 4 NLP as an iterative and incremental process model for developing NLP applications. With STAMP 4 NLP, we merge software engineering principles with best practices from data science. Instantiating our process model allows efficiently creating prototypes by utilizing templates, conventions, and implementations, enabling developers and data scientists to focus on the business goals. Due to our iterative-incremental approach, businesses can deploy an enhanced version of the prototype to their software environment after every iteration, maximizing potential business value and trust early and avoiding the cost of successful yet never deployed experiments.}, language = {en} } @inproceedings{BornheimGriegerBialonski2021, author = {Bornheim, Tobias and Grieger, Niklas and Bialonski, Stephan}, title = {FHAC at GermEval 2021: Identifying German toxic, engaging, and fact-claiming comments with ensemble learning}, series = {Proceedings of the GermEval 2021 Workshop on the Identification of Toxic, Engaging, and Fact-Claiming Comments : 17th Conference on Natural Language Processing KONVENS 2021}, booktitle = {Proceedings of the GermEval 2021 Workshop on the Identification of Toxic, Engaging, and Fact-Claiming Comments : 17th Conference on Natural Language Processing KONVENS 2021}, publisher = {Heinrich Heine University}, address = {D{\"u}sseldorf}, doi = {10.48415/2021/fhw5-x128}, pages = {105 -- 111}, year = {2021}, language = {en} } @incollection{EngelmannShashaSlabu2021, author = {Engelmann, Ulrich M. and Shasha, Carolyn and Slabu, Ioana}, title = {Magnetic nanoparticle relaxation in biomedical application: focus on simulating nanoparticle heating}, series = {Magnetic nanoparticles in human health and medicine}, booktitle = {Magnetic nanoparticles in human health and medicine}, publisher = {Wiley-Blackwell}, address = {Hoboken, New Jeersey}, isbn = {978-1-119-75467-1}, pages = {327 -- 354}, year = {2021}, language = {en} } @inproceedings{OlderogMohrBegingetal.2021, author = {Olderog, M. and Mohr, P. and Beging, Stefan and Tsoumpas, C. and Ziemons, Karl}, title = {Simulation study on the role of tissue-scattered events in improving sensitivity for a compact time of flight compton positron emission tomograph}, series = {2020 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC)}, booktitle = {2020 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC)}, publisher = {IEEE}, address = {New York, NY}, isbn = {978-1-7281-7693-2}, doi = {10.1109/NSS/MIC42677.2020.9507901}, pages = {4 Seiten}, year = {2021}, abstract = {In positron emission tomography improving time, energy and spatial detector resolutions and using Compton kinematics introduces the possibility to reconstruct a radioactivity distribution image from scatter coincidences, thereby enhancing image quality. The number of single scattered coincidences alone is in the same order of magnitude as true coincidences. In this work, a compact Compton camera module based on monolithic scintillation material is investigated as a detector ring module. The detector interactions are simulated with Monte Carlo package GATE. The scattering angle inside the tissue is derived from the energy of the scattered photon, which results in a set of possible scattering trajectories or broken line of response. The Compton kinematics collimation reduces the number of solutions. Additionally, the time of flight information helps localize the position of the annihilation. One of the questions of this investigation is related to how the energy, spatial and temporal resolutions help confine the possible annihilation volume. A comparison of currently technically feasible detector resolutions (under laboratory conditions) demonstrates the influence on this annihilation volume and shows that energy and coincidence time resolution have a significant impact. An enhancement of the latter from 400 ps to 100 ps leads to a smaller annihilation volume of around 50\%, while a change of the energy resolution in the absorber layer from 12\% to 4.5\% results in a reduction of 60\%. The inclusion of single tissue-scattered data has the potential to increase the sensitivity of a scanner by a factor of 2 to 3 times. The concept can be further optimized and extended for multiple scatter coincidences and subsequently validated by a reconstruction algorithm.}, language = {en} }