Refine
Year of publication
- 2024 (26) (remove)
Institute
- Fachbereich Medizintechnik und Technomathematik (26) (remove)
Document Type
- Article (16)
- Conference Proceeding (5)
- Book (2)
- Part of a Book (1)
- Preprint (1)
- Working Paper (1)
Keywords
- Ageing (1)
- Agent-based modeling (1)
- Analytical models (1)
- Anatomy (1)
- Boundary integral equations, (1)
- Capacitive model (1)
- Coal (1)
- Comparative simulation (1)
- Complex-valued eigenvalues (1)
- Constitutive model (1)
We conducted a scoping review for active learning in the domain of natural language processing (NLP), which we summarize in accordance with the PRISMA-ScR guidelines as follows:
Objective: Identify active learning strategies that were proposed for entity recognition and their evaluation environments (datasets, metrics, hardware, execution time).
Design: We used Scopus and ACM as our search engines. We compared the results with two literature surveys to assess the search quality. We included peer-reviewed English publications introducing or comparing active learning strategies for entity recognition.
Results: We analyzed 62 relevant papers and identified 106 active learning strategies. We grouped them into three categories: exploitation-based (60x), exploration-based (14x), and hybrid strategies (32x). We found that all studies used the F1-score as an evaluation metric. Information about hardware (6x) and execution time (13x) was only occasionally included. The 62 papers used 57 different datasets to evaluate their respective strategies. Most datasets contained newspaper articles or biomedical/medical data. Our analysis revealed that 26 out of 57 datasets are publicly accessible.
Conclusion: Numerous active learning strategies have been identified, along with significant open questions that still need to be addressed. Researchers and practitioners face difficulties when making data-driven decisions about which active learning strategy to adopt. Conducting comprehensive empirical comparisons using the evaluation environment proposed in this study could help establish best practices in the domain.
The growing body of political texts opens up new opportunities for rich insights into political dynamics and ideologies but also increases the workload for manual analysis. Automated speaker attribution, which detects who said what to whom in a speech event and is closely related to semantic role labeling, is an important processing step for computational text analysis. We study the potential of the large language model family Llama 2 to automate speaker attribution in German parliamentary debates from 2017-2021. We fine-tune Llama 2 with QLoRA, an efficient training strategy, and observe our approach to achieve competitive performance in the GermEval 2023 Shared Task On Speaker Attribution in German News Articles and Parliamentary Debates. Our results shed light on the capabilities of large language models in automating speaker attribution, revealing a promising avenue for computational analysis of political discourse and the development of semantic role labeling systems.
Das Diskussionspapier beschreibt einen Prozess an der FH Aachen zur Entwicklung und Implementierung eines Self-Assessment-Tools für Studiengänge. Dieser Prozess zielte darauf ab, die Relevanz der Themen Digitalisierung, Internationalisierung und Nachhaltigkeit in Studiengängen zu stärken. Durch Workshops und kollaborative Entwicklung mit Studiendekan:innen entstand ein Fragebogen, der zur Reflexion und strategischen Weiterentwicklung der Studiengänge dient.
As one class of molecular imprinted polymers (MIPs), surface imprinted polymer (SIP)-based biosensors show great potential in direct whole-bacteria detection. Micro-contact imprinting, that involves stamping the template bacteria immobilized on a substrate into a pre-polymerized polymer matrix, is the most straightforward and prominent method to obtain SIP-based biosensors. However, the major drawbacks of the method arise from the requirement for fresh template bacteria and often non-reproducible bacteria distribution on the stamp substrate. Herein, we developed a positive master stamp containing photolithographic mimics of the template bacteria (E. coli) enabling reproducible fabrication of biomimetic SIP-based biosensors without the need for the “real” bacteria cells. By using atomic force and scanning electron microscopy imaging techniques, respectively, the E. coli-capturing ability of the SIP samples was tested, and compared with non-imprinted polymer (NIP)-based samples and control SIP samples, in which the cavity geometry does not match with E. coli cells. It was revealed that the presence of the biomimetic E. coli imprints with a specifically designed geometry increases the sensor E. coli-capturing ability by an “imprinting factor” of about 3. These findings show the importance of geometry-guided physical recognition in bacterial detection using SIP-based biosensors. In addition, this imprinting strategy was employed to interdigitated electrodes and QCM (quartz crystal microbalance) chips. E. coli detection performance of the sensors was demonstrated with electrochemical impedance spectroscopy (EIS) and QCM measurements with dissipation monitoring technique (QCM-D).