Search Results for author:
Found 4 papers, 3 papers with code
Architectural Sweet Spots for Modeling Human Label Variation by the Example of Argument Quality: It's Best to Relate Perspectives!
To best represent the interplay of individual and shared perspectives, we consider a continuum of approaches ranging from models that fully aggregate perspectives into a majority label to "share nothing"-architectures in which each annotator is considered in isolation from all other annotators.
The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics
To account for sociodemographics in models of individual annotator behaviour, we introduce group-specific layers to multi-annotator models.
Learning Diachronic Analogies to Analyze Concept Change
We show that a model which treats the concept terms as analogous and learns weights to compensate for diachronic changes (weighted linear combination) is able to more accurately predict the missing term than a learned transformation and two baselines for most of the evaluated concepts.
