Zobrazeno 1 - 10
of 1 709
pro vyhledávání: '"Walde, P"'
The visual representation of a concept varies significantly depending on its meaning and the context where it occurs; this poses multiple challenges both for vision and multimodal models. Our study focuses on concreteness, a well-researched lexical-s
Externí odkaz:
http://arxiv.org/abs/2410.11657
We present a novel dataset for physical and abstract plausibility of events in English. Based on naturally occurring sentences extracted from Wikipedia, we infiltrate degrees of abstractness, and automatically generate perturbed pseudo-implausible ev
Externí odkaz:
http://arxiv.org/abs/2404.04035
Autor:
Eichel, Annerose, Deeg, Tana, Blessing, André, Belosevic, Milena, Arndt-Lappe, Sabine, Walde, Sabine Schulte im
We present a comprehensive computational study of the under-investigated phenomenon of personal name compounds (PNCs) in German such as Willkommens-Merkel ('Welcome-Merkel'). Prevalent in news, social media, and political discourse, PNCs are hypothes
Externí odkaz:
http://arxiv.org/abs/2404.04031
We provide a toolbox of extension, gluing, and assembly techniques for factorization algebras. Using these tools, we fill various gaps in the literature on factorization algebras on stratified manifolds, the main one being that constructible factoriz
Externí odkaz:
http://arxiv.org/abs/2403.19472
We introduce notions of lax semiadditive and lax additive $(\infty,2)$-categories, categorifying the classical notions of semiadditive and additive 1-categories. To establish a well-behaved axiomatic framework, we develop a calculus of lax matrices a
Externí odkaz:
http://arxiv.org/abs/2402.12251
Multiword expressions (MWEs) are composed of multiple words and exhibit variable degrees of compositionality. As such, their meanings are notoriously difficult to model, and it is unclear to what extent this issue affects transformer architectures. A
Externí odkaz:
http://arxiv.org/abs/2401.15393
Autor:
Schlechtweg, Dominik, Virk, Shafqat Mumtaz, Sander, Pauline, Sköldberg, Emma, Linke, Lukas Theuer, Zhang, Tuo, Tahmasebi, Nina, Kuhn, Jonas, Walde, Sabine Schulte im
We present the DURel tool that implements the annotation of semantic proximity between uses of words into an online, open source interface. The tool supports standardized human annotation as well as computational annotation, building on recent advanc
Externí odkaz:
http://arxiv.org/abs/2311.12664
Humans tend to strongly agree on ratings on a scale for extreme cases (e.g., a CAT is judged as very concrete), but judgements on mid-scale words exhibit more disagreement. Yet, collected rating norms are heavily exploited across disciplines. Our stu
Externí odkaz:
http://arxiv.org/abs/2311.04563
We propose a novel approach to learn domain-specific plausible materials for components in the vehicle repair domain by probing Pretrained Language Models (PLMs) in a cloze task style setting to overcome the lack of annotated datasets. We devise a ne
Externí odkaz:
http://arxiv.org/abs/2304.14745
We study complexes of stable $\infty$-categories, referred to as categorical complexes. As we demonstrate, examples of such complexes arise in a variety of subjects including representation theory, algebraic geometry, symplectic geometry, and differe
Externí odkaz:
http://arxiv.org/abs/2301.02606