2 code implementations • Findings (EMNLP) 2021 • Jonas Rieger, Carsten Jentsch, Jörg Rahnenführer
We propose a rolling version of the Latent Dirichlet Allocation, called RollingLDA.
2 code implementations • sdp (COLING) 2022 • André Bittermann, Jonas Rieger
The ever growing amount of research publications demands computational assistance for everyone trying to keep track with scientific processes.
no code implementations • 28 Dec 2023 • Jonas Rieger, Kostiantyn Yanchenko, Mattes Ruckdeschel, Gerret von Nordheim, Katharina Kleinen-von Königslöw, Gregor Wiedemann
In this study, we address these challenges by using a multilingual transformer model in combination with the adapter extension to transformers, and few-shot learning methods.
no code implementations • 26 Sep 2022 • Kai-Robin Lange, Jonas Rieger, Carsten Jentsch
Unsupervised sentiment analysis is traditionally performed by counting those words in a text that are stored in a sentiment lexicon and then assigning a label depending on the proportion of positive and negative words registered.
no code implementations • 14 Feb 2020 • Jonas Rieger, Lars Koppers, Carsten Jentsch, Jörg Rahnenführer
Based on the newly proposed measure for LDA stability, we propose a method to increase the reliability and hence to improve the reproducibility of empirical findings based on topic modeling.