1 code implementation • 6 Mar 2024 • Arik Reuter, Anton Thielmann, Christoph Weisser, Benjamin Säfken, Thomas Kneib
With the rise of transformers in Natural Language Processing, however, several successful models that rely on straightforward clustering approaches in transformer-based embedding spaces have emerged and consolidated the notion of topics as clusters of embedding vectors.
no code implementations • 6 Mar 2024 • Arik Reuter, Anton Thielmann, Christoph Weisser, Sebastian Fischer, Benjamin Säfken
Topic modeling seems to be almost synonymous with generating lists of top words to represent topics within large text corpora.
no code implementations • 30 Mar 2023 • Anton Thielmann, Quentin Seifert, Arik Reuter, Elisabeth Bergherr, Benjamin Säfken
We demonstrate the competitive performance of our method with a large benchmark study, and achieve superior results compared to state-of-the-art topic modeling and document clustering models.
1 code implementation • 18 Feb 2023 • Mattias Luber, Anton Thielmann, Benjamin Säfken
Deep neural networks (DNNs) have shown exceptional performances in a wide range of tasks and have become the go-to method for problems requiring high-level predictive power.
1 code implementation • 27 Jan 2023 • Anton Thielmann, René-Marcel Kruse, Thomas Kneib, Benjamin Säfken
We propose Neural Additive Models for Location Scale and Shape (NAMLSS), a modelling framework that combines the predictive power of classical deep learning models with the inherent advantages of distributional regression while maintaining the interpretability of additive models.
no code implementations • 19 Dec 2022 • Anton Thielmann, Christoph Weisser, Benjamin Säfken
Few-shot methods for accurate modeling under sparse label-settings have improved significantly.
no code implementations • 17 Nov 2021 • Mattias Luber, Anton Thielmann, Christoph Weisser, Benjamin Säfken
Extracting topics from large collections of unstructured text-documents has become a central task in current NLP applications and algorithms like NMF, LDA as well as their generalizations are the well-established current state of the art.