Paper accepted: Betty van Aken, Jens-Michalis Papaioannou, Marcel G. Naik, Georgios Eleftheriadis, Wolfgang Nejdl, Felix Gers and Alexander Löser, This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text @ AACL 2022
Paper accepted: Paul Grundmann, Tom Oberhauser, Felix Gers, Alexander Löser, Attention Networks for Augmenting Clinical Text with Support Sets for Diagnosis Prediction @ COLING 2022
Paper accepted: Jens-Michalis Papaioannou, Paul Grundmann, Betty van Aken, Athanasios Samaras Ilias Kyparissidis, George Giannakoulas, Felix Gers, Alexander Löser, Cross-Lingual Knowledge Transfer for Clinical Phenotyping, LREC 2022
Paper accepted: KIMERA: Injecting Domain Knowledge into Vacant Transformer Heads: Benjamin Winter, Alexei Figueroa, Amy Siu, Felix Gers, Alexander Löser, LREC 2022
2021
Acatech Talk about different Skills for running AI Projects with SMEs
New BMBF Project: "KI in der Pflege - Sturz/Delir/Medication" together with Felix Biessmann and DATEXIS
Introduction into Deep Patient Representation with Alexander Löser [link]
Paper accepted: Patrick Erdelt: Orchestrating DBMS Benchmarking in the Cloud with Kubernetes. VLDB Workshop TPCTC 2021
Plattform Lernende Systeme - KI im Mittelstand mit Alexander Löser[link]
Dr. Sebastian Arnold has been awarded with the Faculty Prize 2021 in Theoretical Sciences of the Faculty of Science and Medicine of University of Friburg (Switzerland)
Paper accepted: Betty van Aken, Ivana Trajanovska, Amy Siu, Manuel Mayrdorfer, Klemens Budde, Alexander Loeser: Assertion Detection in Clinical Notes: Medical Language Models to the Rescue? , Proceedings of the Second Workshop on Natural Language Processing for Medical Conversations @ NAACL 2021 [PDF] [Dataset] [Demo]
Erklärbare KI: Anforderungen, Anwendungsfälle und Lösungen - mit Betty van Aken und Alexander Löser [link]
PhD Defense: Konstantina Lazaridou defended her thesis "Revealing Hidden Patterns in Political News and Social Media with Machine Learning" on March 2nd 2021 (Supervision with Felix Naumann from HPI) [slides]
Plattform lernende Systeme, Drei Fragen an Alexander Löser, KI im Mittelstand: Chancen in der Wertschöpfungskette erkennen [Link]
Invited Talk: Tom Oberhauser was invited to the DFKI Research Colloquium to give a talk about "Bi-Encoders for Small-Data Named Entity Linking"
Paper accepted: Betty van Aken, Jens-Michalis Papaioannou, Manuel Mayrdorfer, Klemens Budde, Felix Gers, Alexander Löser: Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration, Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics EACL 2021 [Link]
Paper accepted: Jens-Michalis Papaioannou, Manuel Mayrdorfer, Sebastian Arnold, Felix A. Gers, Klemens Budde and Alexander Löser: Aspect-based Passage Retrieval with Contextualized Discourse Vectors, Proceedings of the 43rd European Conference on Information Retrieval ECIR 2021
Sebastian Arnold has successfully completed his PhD [Slides]
Data Science und Humanoide Robotik: Neue Forschungsverbünde an der BHT [Link]
Paper accepted: Tom Oberhauser, Tim Bischoff, Karl Brendel, Maluna Menke, Tobias Klatt, Amy Siu, Felix Alexander Gers and Alexander Löser: TrainX – Named Entity Linking with Active Sampling and Bi-Encoders. COLING 2020 Demo Track
eco Akademie Webinar, Legal Tech: Einsatzmöglichkeiten von KI am Beispiel NLP und Semantische Suche (Vortrag: Alexander Löser)
Paper accepted: Betty van Aken, Benjamin Winter, Felix A. Gers and Alexander Löser. VisBERT: Hidden-State Visualizations for Transformers. Accepted to The Web Conference 2020 (WWW'20) Demo Track
Paper accepted: Rudolf Schneider, Tom Oberhauser, Paul Grundmann, Felix Alexander Gers, Alexander Loeser and Steffen Staab: Is Language Modeling enough? Evaluating Effective Embedding Combinations LREC 2020
Paper accepted: Konstantina Lazaridou, Alexander Löser, Maria Mestre, Felix Naumann : Discovering Biased News Articles Leveraging Multiple Human Annotations. LREC 2020
Paper accepted: Sebastian Arnold, Betty van Aken, Paul Grundmann, Felix Gers, Alexander Löser: Learning Contexualized Document Representations for Heathcare Answer Retrieval. ACM WWW 2020
2019
Datexis-Startup Pyramics aquired by Hella Aglaia GmbH, see press release (PDF)
Best Thesis Award: Team members Thomas Steffek with bachelor's thesis "Neural Facet Detection on Medical Resources" and Tom Oberhauser with master's thesis "Neural Information Retrieval with Vector Space Queries" awarded degrees with distinction as best faculty thesis in Summer Term 2019
Germany's leading AI-Plattform "Learning Systems" (BMBF) publishes results. Alexander Löser is one of the experts recommending deep learning techniques for next generation AI applications
BMWi recommends AI project servicemeister for funding (initial study phase 1). Project members are Beuth, Karlsruhe Institute of Technology, USU AG, eco e.V.
Our MACSS project with the Charité and the SAP will be awarded the Max Rubner Preison January 15, 2019. The project is about measures to prevent a kidney transplant or to keep a transplanted kidney "in" longer. (Increase therapy adherence).
Paper accepted: Sebastian Arnold, Rudolf Schneider, Philippe Cudré-Mauroux, Felix A. Gers and Alexander Löser. "SECTOR: A Neural Model for Coherent Topic Segmentation and Classification." Transactions of the Association for Computational Linguistics (2019).
Paper accepted: Torsten Kilias, Alexander Löser, Felix Gers, Ying Zhang, Richard Koopmanschap and Martin Kersten. "IDEL: In-Database Neural Entity Linking". IEEE BigCom 2019
Christopher Kümmel gives a talk at Data&Drinks "Reducing Machine Learning costs with Active Learning" on 7.11.2018
Alexander Löser gives talk at science match with Tagesspiegel 2018
Alexander Löser invited Expert for H2020 in Brussels in June 2018
Rudolf Schneider, Betty van Aken and Alexander Löser present our work on neural text mining at German Finnish Information Exchange 2018 in the Finnish Embassy Berlin and the smart data forum
Joint Beuth-Team (Betty van Aken, Iurri Chernusheko) and HPI (Julian Risch) achive notable 54th. rank (out of of 4000) at Kaggle Hate Speech Competition
Invited Talk at BISCUITS first workshop on Software Foundations for Data Interoperability with Alex Löser at Kyoto University, Japan (21.3.2018)
Paper accepted: Rudolf Schneider, Sebastian Arnold, Tom Oberhauser, Tobias Klatt, Thomas Steffek, Alexander Löser, "Smart-MD: Neural Paragraph Retrieval of Medical Topics". In WWW ’18 Companion: The 2018 Web Conference Companion, April 23–27, 2018, Lyon, France. ACM, New York, NY, USA, 4 pages. [video]
Former Team Member Cordula Guder (now with SAP Innovation Center) awarded as best master student in computer science at Beuth for winter term 17/18.
2017
Newspaper article about the NOHATE project in "Der Tagesspiegel" (2.12.2017)
Paper accepted: Rudolf Schneider, Tom Oberhauser, Tobias Klatt, Felix A. Gers, and Alexander Löser, “Analysing Errors of Open Information Extraction Systems,” accepted for BLGNLP 2017 Building Linguistically Generalizable NLP Systems at EMNLP 2017
Lukas Abegg with Thesis on "Maschine Learning for Search Engine Optimization" awarded as best bachelor student for summer term 2017.
Leading article Data Science in Beuth Magazin 1/2017 about the new Data Science Master in english language starting this Winterterm 2017 at Beuth University [pdf]
Presentations by Sebastian Arnold, Torsten Kilias and Rudolf Schneider at the Hasso Plattner Institut Department for Information Systems (9.6.2017)
Long Night of Sciences with DATEXIS: My Search Engine reads me. With Sebastian Arnold and Robert Dzuiba. 11.6.2016, Beuth-HS, Haus Grashof 6:00 PM, 8:00 PM 10:00 PM
PT Jühlich recommends EXIST SEED Project Pyramics: The technique recognizes from a mini-camera at the shop flor faces, age, sex and viewing angles of potential customers. Alexander Löser from DATEXIS mentors the team.
Proposal accepted: DATEXIS won BMWi challenge "Smart Service Welt" with MACSS proposal (with Charité, SAP SE, SmartPatient GmbH, DFKI GmbH, DOSING GmbH)
Final presentations for Enterprise Data Management class are online, this time with Zalando and HERE.
Final presentations for Enterprise Data Management class are online.
2014
ERCIM (European Research Consortium for Informatics and Mathematics) Study:New White Paper on Big Data Analytics with contributions from Alexander Löser.
Paper accepted: INDREX: In-Database Relation Extraction. Torsten Kilias, Alexander Löser, Periklis Andritsos. To appear in: Information Systems Journal. (Impact Factor 1.23)
The development of ICT for big data management is a logical priority of the Federal Ministry of Economics and Technology, and one which particularly merits support. The Big Data Managament Report of the BMWi is online now. Alexander Löser coordinated this effort in 2013.
Talk at CEBIT (Hall 9 / Stand 43) in collaboration with the German Research Center for Artifical Intelligence (DFKI).
11/3/2014 Talk at CEBIT (Hall 9 / Stand E24) in collaboration with BMWi
02/2014: Final presentations for Enterprise Data Management class are online.
10/01/2014 PhD Defense: Klemens Muthmann defended his Ph.D. thesis "Community based Answer Detection" at TU Dresden. Alexander Löser was part of the comitee. Congrats to Klemens!
2013
12/2013 Paper Informatik Spektrum 12/2103:Preismodelle für Datenmarktplatze. Florian Stahl, Alexander Löser and Gottfried Vossen.
Deutsch