1 code implementation • 4 May 2023 • Vageesh Saxena, Nils Rethmeier, Gijs Van Dijck, Gerasimos Spanakis
The anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between markets.
1 code implementation • 14 Feb 2022 • Malte Ostendorff, Nils Rethmeier, Isabelle Augenstein, Bela Gipp, Georg Rehm
Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics.
Ranked #1 on Document Classification on SciDocs (MeSH)
no code implementations • 25 Feb 2021 • Nils Rethmeier, Isabelle Augenstein
Contrastive self-supervised training objectives enabled recent successes in image representation pretraining by learning to contrast input-input pairs of augmented images as either similar or dissimilar.
no code implementations • 2 Oct 2020 • Nils Rethmeier, Isabelle Augenstein
For natural language processing `text-to-text' tasks, the prevailing approaches heavily rely on pretraining large self-supervised models on increasingly larger `task-external' data.
no code implementations • 28 Sep 2020 • Nils Rethmeier, Isabelle Augenstein
We thus approach pretraining from a miniaturisation perspective, such as not to require massive external data sources and models, or learned translations from continuous input embeddings to discrete labels.
2 code implementations • 2 Dec 2019 • Nils Rethmeier, Vageesh Kumar Saxena, Isabelle Augenstein
While state-of-the-art NLP explainability (XAI) methods focus on explaining per-sample decisions in supervised end or probing tasks, this is insufficient to explain and quantify model knowledge transfer during (un-)supervised training.
Explainable Artificial Intelligence (XAI) Model Compression +1
1 code implementation • WS 2019 • Nils Rethmeier, Barbara Plank
Word embeddings have undoubtedly revolutionized NLP.
no code implementations • WS 2018 • Nils Rethmeier, Marc H{\"u}bner, Leonhard Hennig
Comments on web news contain controversies that manifest as inter-group agreement-conflicts.
no code implementations • EACL 2017 • Hans Uszkoreit, Aleks Gabryszak, ra, Leonhard Hennig, J{\"o}rg Steffen, Renlong Ai, Stephan Busemann, Jon Dehdari, Josef van Genabith, Georg Heigold, Nils Rethmeier, Raphael Rubino, Sven Schmeier, Philippe Thomas, He Wang, Feiyu Xu
Web debates play an important role in enabling broad participation of constituencies in social, political and economic decision-taking.