Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Wagner, Stefan Sylvius"'
Online spaces allow people to discuss important issues and make joint decisions, regardless of their location or time zone. However, without proper support and thoughtful design, these discussions often lack structure and politeness during the exchan
Externí odkaz:
http://arxiv.org/abs/2409.07780
Stance detection holds great potential for enhancing the quality of online political discussions, as it has shown to be useful for summarizing discussions, detecting misinformation, and evaluating opinion distributions. Usually, transformer-based mod
Externí odkaz:
http://arxiv.org/abs/2406.12480
Stance detection is an important task for many applications that analyse or support online political discussions. Common approaches include fine-tuning transformer based models. However, these models require a large amount of labelled data, which mig
Externí odkaz:
http://arxiv.org/abs/2404.08078
Autor:
Behrendt, Maike, Wagner, Stefan Sylvius, Ziegele, Marc, Wilms, Lena, Stoll, Anke, Heinbach, Dominique, Harmeling, Stefan
Measuring the quality of contributions in political online discussions is crucial in deliberation research and computer science. Research has identified various indicators to assess online discussion quality, and with deep learning advancements, auto
Externí odkaz:
http://arxiv.org/abs/2404.02761
In this paper we adopt a representation-centric perspective on exploration in reinforcement learning, viewing exploration fundamentally as a density estimation problem. We investigate the effectiveness of clustering representations for exploration in
Externí odkaz:
http://arxiv.org/abs/2402.03138
In environments with sparse rewards, finding a good inductive bias for exploration is crucial to the agent's success. However, there are two competing goals: novelty search and systematic exploration. While existing approaches such as curiosity-drive
Externí odkaz:
http://arxiv.org/abs/2308.15911
Autor:
Uelwer, Tobias, Robine, Jan, Wagner, Stefan Sylvius, Höftmann, Marc, Upschulte, Eric, Konietzny, Sebastian, Behrendt, Maike, Harmeling, Stefan
Learning meaningful representations is at the heart of many tasks in the field of modern machine learning. Recently, a lot of methods were introduced that allow learning of image representations without supervision. These representations can then be
Externí odkaz:
http://arxiv.org/abs/2308.11455