Article
Refine
Year of publication
- 2024 (15)
- 2023 (24)
- 2022 (34)
- 2021 (39)
- 2020 (44)
- 2019 (52)
- 2018 (47)
- 2017 (45)
- 2016 (32)
- 2015 (43)
- 2014 (42)
- 2013 (49)
- 2012 (41)
- 2011 (69)
- 2010 (61)
- 2009 (76)
- 2008 (51)
- 2007 (48)
- 2006 (32)
- 2005 (40)
- 2004 (75)
- 2003 (39)
- 2002 (45)
- 2001 (49)
- 2000 (53)
- 1999 (31)
- 1998 (32)
- 1997 (29)
- 1996 (27)
- 1995 (18)
- 1994 (9)
- 1993 (18)
- 1992 (11)
- 1991 (11)
- 1990 (15)
- 1989 (17)
- 1988 (20)
- 1987 (19)
- 1986 (6)
- 1985 (8)
- 1984 (7)
- 1983 (5)
- 1982 (20)
- 1981 (15)
- 1980 (29)
- 1979 (20)
- 1978 (25)
- 1977 (13)
- 1976 (16)
- 1975 (12)
- 1974 (4)
- 1973 (2)
- 1972 (6)
- 1968 (2)
- 1967 (1)
Institute
- Fachbereich Medizintechnik und Technomathematik (1593) (remove)
Document Type
- Article (1593) (remove)
Keywords
- Einspielen <Werkstoff> (7)
- FEM (4)
- Finite-Elemente-Methode (4)
- LAPS (4)
- CellDrum (3)
- Label-free detection (3)
- biosensors (3)
- hydrogen peroxide (3)
- impedance spectroscopy (3)
- shakedown analysis (3)
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.
Using a cell-based gas biosensor for investigation of adverse effects of acetone vapors in vitro
(2013)
Cell-based sensors for the detection of gases have long been underrepresented, due to the cellular requirement of being cultured in a liquid environment. In this work we established a cell-based gas biosensor for the detection of toxic substances in air, by adapting a commercial sensor chip (Bionas®), previously used for the measurement of pollutants in liquids. Cells of the respiratory tract (A549, RPMI 2650, V79), which survive at a gas phase in a natural context, are used as biological receptors. The physiological cell parameters acidification, respiration and morphology are continuously monitored in parallel. Ammonia was used as a highly water-soluble model gas to test the feasibility of the sensor system. Infrared measurements confirmed the sufficiency of the medium draining method. This sensor system provides a basis for many sensor applications such as environmental monitoring, building technology and public security.