1 code implementation • EMNLP (BlackboxNLP) 2020 • David Yenicelik, Florian Schmidt, Yannic Kilcher
The recent paradigm shift to contextual word embeddings has seen tremendous success across a wide range of down-stream tasks.
no code implementations • 12 Feb 2021 • Soeren Becker, Florian Schmidt, Anton Gulenko, Alexander Acker, Odej Kao
Edge computing was introduced as a technical enabler for the demanding requirements of new network technologies like 5G.
no code implementations • 25 Jan 2021 • Kevin Styp-Rekowski, Florian Schmidt, Odej Kao
Forecasting of time series in continuous systems becomes an increasingly relevant task due to recent developments in IoT and 5G.
no code implementations • 15 Jan 2021 • Jasmin Bogatinovski, Sasho Nedelkoski, Alexander Acker, Florian Schmidt, Thorsten Wittkopp, Soeren Becker, Jorge Cardoso, Odej Kao
Finally, all this will result in faster adoption of AIOps, further increase the interest in this research field and contribute to bridging the gap towards fully-autonomous operating IT systems.
no code implementations • 17 Dec 2020 • Katrin D. Bartl-Pokorny, Florian B. Pokorny, Anton Batliner, Shahin Amiriparian, Anastasia Semertzidou, Florian Eyben, Elena Kramer, Florian Schmidt, Rainer Schönweiler, Markus Wehler, Björn W. Schuller
Group differences in the front vowels /i:/ and /e:/ are additionally reflected in the variation of the fundamental frequency and the harmonics-to-noise ratio, group differences in back vowels /o:/ and /u:/ in statistics of the Mel-frequency cepstral coefficients and the spectral slope.
no code implementations • 5 Mar 2020 • Florian Schmidt, Thomas Hofmann
Measuring the quality of a generated sequence against a set of references is a central problem in many learning frameworks, be it to compute a score, to assign a reward, or to perform discrimination.
no code implementations • WS 2019 • Florian Schmidt
Exposure bias refers to the train-test discrepancy that seemingly arises when an autoregressive generative model uses only ground-truth contexts at training time but generated ones at test time.
1 code implementation • IJCNLP 2019 • Florian Schmidt, Stephan Mandt, Thomas Hofmann
Autoregressive state transitions, where predictions are conditioned on past predictions, are the predominant choice for both deterministic and stochastic sequential models.
no code implementations • 12 Oct 2018 • Oleh Bodunov, Florian Schmidt, André Martin, Andrey Brito, Christof Fetzer
The challenge asks to provide a prediction for (i) a destination and the (ii) arrival time of ships in a streaming-fashion using Geo-spatial data in the maritime context.
no code implementations • NeurIPS 2018 • Florian Schmidt, Thomas Hofmann
Autoregressive feedback is considered a necessity for successful unconditional text generation using stochastic sequence models.
no code implementations • 23 Apr 2018 • Nicolas Weber, Florian Schmidt, Mathias Niepert, Felipe Huici
Neural network frameworks such as PyTorch and TensorFlow are the workhorses of numerous machine learning applications ranging from object recognition to machine translation.
no code implementations • 2 Feb 2018 • Florian Schmidt, Mathias Niepert, Felipe Huici
Creating a model of a computer system that can be used for tasks such as predicting future resource usage and detecting anomalies is a challenging problem.
1 code implementation • 1 Dec 2016 • Paulina Grnarova, Florian Schmidt, Stephanie L. Hyland, Carsten Eickhoff
We present an automatic mortality prediction scheme based on the unstructured textual content of clinical notes.