TY - JOUR A1 - Anik, Sabri A1 - Frohberg, Martin G. A1 - Kapoor, Madan Lal T1 - Experiments and theoretical considerations on the solution of oxygen in binary metal alloys JF - Berichte der Bunsengesellschaft für physikalische Chemie Y1 - 1983 SN - 0005-9021 SN - 0940-483X VL - 87 IS - 12 SP - 1201 EP - 1204 ER - TY - JOUR A1 - Wang, Mao A1 - Anik, Sabri A1 - Frohberg, Martin G. T1 - Experiments on the electrochemical determination of the sulphur activities in the system copper-silver at 1200°C JF - Zeitschrift für Metallkunde Y1 - 1988 SN - 0044-3093 VL - 79 IS - 5 SP - 336 EP - 339 ER - TY - CHAP A1 - Klöser, Lars A1 - Büsgen, André A1 - Kohl, Philipp A1 - Kraft, Bodo A1 - Zündorf, Albert ED - Conte, Donatello ED - Fred, Ana ED - Gusikhin, Oleg ED - Sansone, Carlo T1 - Explaining relation classification models with semantic extents T2 - Deep Learning Theory and Applications N2 - In recent years, the development of large pretrained language models, such as BERT and GPT, significantly improved information extraction systems on various tasks, including relation classification. State-of-the-art systems are highly accurate on scientific benchmarks. A lack of explainability is currently a complicating factor in many real-world applications. Comprehensible systems are necessary to prevent biased, counterintuitive, or harmful decisions. We introduce semantic extents, a concept to analyze decision patterns for the relation classification task. Semantic extents are the most influential parts of texts concerning classification decisions. Our definition allows similar procedures to determine semantic extents for humans and models. We provide an annotation tool and a software framework to determine semantic extents for humans and models conveniently and reproducibly. Comparing both reveals that models tend to learn shortcut patterns from data. These patterns are hard to detect with current interpretability methods, such as input reductions. Our approach can help detect and eliminate spurious decision patterns during model development. Semantic extents can increase the reliability and security of natural language processing systems. Semantic extents are an essential step in enabling applications in critical areas like healthcare or finance. Moreover, our work opens new research directions for developing methods to explain deep learning models. KW - Relation classification KW - Natural language processing KW - Natural language understanding KW - Information extraction KW - Trustworthy artificial intelligence Y1 - 2023 SN - 978-3-031-39058-6 (Print) SN - 978-3-031-39059-3 (Online) U6 - https://doi.org/10.1007/978-3-031-39059-3_13 N1 - 4th International Conference, DeLTA 2023, Rome, Italy, July 13–14, 2023. SP - 189 EP - 208 PB - Springer CY - Cham ER - TY - JOUR A1 - Siepmann, Thomas T1 - Exploitation Plan of the TELEflow Project Y1 - 1999 N1 - 4th Framework Programme Report CY - Brussels ER - TY - CHAP A1 - Spasov, Yulian A1 - Döring, Bernd A1 - Griffin, Allan T1 - Exploiting the thermal mass in an energy efficient building - a comparison exercise between IES Apache and TRNSYS models T2 - Clima 2007 WellBeing Indoors: 9th Rehva World Congress, 10-14 June 2007, Helsinki, Finland : proceedings Y1 - 2007 SN - 978-952-99898-2-9 SP - 1 EP - 7 CY - Helsinki ER - TY - CHAP A1 - Büsgen, André A1 - Klöser, Lars A1 - Kohl, Philipp A1 - Schmidts, Oliver A1 - Kraft, Bodo A1 - Zündorf, Albert T1 - Exploratory analysis of chat-based black market profiles with natural language processing T2 - Proceedings of the 11th International Conference on Data Science, Technology and Applications N2 - Messenger apps like WhatsApp or Telegram are an integral part of daily communication. Besides the various positive effects, those services extend the operating range of criminals. Open trading groups with many thousand participants emerged on Telegram. Law enforcement agencies monitor suspicious users in such chat rooms. This research shows that text analysis, based on natural language processing, facilitates this through a meaningful domain overview and detailed investigations. We crawled a corpus from such self-proclaimed black markets and annotated five attribute types products, money, payment methods, user names, and locations. Based on each message a user sends, we extract and group these attributes to build profiles. Then, we build features to cluster the profiles. Pretrained word vectors yield better unsupervised clustering results than current state-of-the-art transformer models. The result is a semantically meaningful high-level overview of the user landscape of black market chatrooms. Additionally, the extracted structured information serves as a foundation for further data exploration, for example, the most active users or preferred payment methods. KW - Clustering KW - Natural Language Processing KW - Information Extraction KW - Profile Extraction KW - Text Mining Y1 - 2022 SN - 978-989-758-583-8 U6 - https://doi.org/10.5220/0011271400003269 SN - 2184-285X N1 - 11th International Conference on Data Science, Technology and Applications DATA - Volume 1, 83-94, 2022, Lisbon, Portugal SP - 83 EP - 94 ER - TY - CHAP A1 - Siegert, Petra A1 - Pohl, Martina A1 - Kneen, Malea M. A1 - Pogozheva, Irina D. A1 - Kenyon, George L. A1 - McLeish, Michael J. T1 - Exploring the substrate specificity of benzoylformate decarboxylase, pyruvate decarboxylase, and benzaldehyde lyase T2 - Thiamine : catalytic mechanisms in normal and disease states / ed. by Frank Jordan ... Y1 - 2004 SN - 0-8247-4062-9 SP - 275 EP - 290 PB - Dekker CY - New York, NY ER - TY - JOUR A1 - Göddeke, Dominik A1 - Strzodka, Robert A1 - Mohd-Yusof, Jamaludin A1 - McCormick, Patrick A1 - Buijssen, Sven H.M. A1 - Grajewski, Matthias A1 - Turek, Stefan T1 - Exploring weak scalability for FEM calculations on a GPU-enhanced cluster JF - Parallel Computing Y1 - 2007 U6 - https://doi.org/10.1016/j.parco.2007.09.002 SN - 0167-8191 VL - 33 IS - 10-11 SP - 685 EP - 699 ER - TY - BOOK A1 - Janz, Norbert A1 - Ebling, Günther T1 - Export and Innovation Activities in the German Service Sector. Empirical Evidence at the Firm Level / Ebling, G.. und N. Janz Y1 - 1999 N1 - ZEW-Discussion Paper 99-53 online unter ftp://ftp.zew.de/pub/zew-docs/dp/dp5399.pdf PB - ZEW Zentrum für Europäische Wirtschaftsförderung CY - Mannheim ER - TY - JOUR A1 - Reinhardt, T. A1 - Bitz, Andreas A1 - El Ouardi, A. A1 - Streckert, J. A1 - Sommer, A. A1 - Lerchl, A. A1 - Hansen, V. T1 - Exposure set-ups for in vivo experiments using radial waveguides JF - Radiation Protection Dosimetry Y1 - 2007 U6 - https://doi.org/10.1093/rpd/ncm370 SN - 1742-3406 VL - 124 IS - 1 SP - 21 EP - 26 ER -