Multitask semi-supervised learning for class-imbalanced discourse classification
As labeling schemas evolve over time, small differences can render datasets following older
schemas unusable. This prevents researchers from building on top of previous annotation …
schemas unusable. This prevents researchers from building on top of previous annotation …
QURATOR: innovative technologies for content and data curation
G Rehm, P Bourgonje, S Hegele, F Kintzel… - ar** NLP applications for content curation
Time and again we are faced, in a number of collaborative research projects, with the
challenge of interconnecting various language processing tools to implement certain …
challenge of interconnecting various language processing tools to implement certain …
Multitask learning for class-imbalanced discourse classification
Small class-imbalanced datasets, common in many high-level semantic tasks like discourse
analysis, present a particular challenge to current deep-learning architectures. In this work …
analysis, present a particular challenge to current deep-learning architectures. In this work …
Not all refugees are framed equal: Explaining the difference between the news coverage in the Global North and the Global South
This study analyses 14,854 news articles about refugees from 72 English-language
newspapers worldwide in 2016. Using a combination of topic modelling and network …
newspapers worldwide in 2016. Using a combination of topic modelling and network …
Cultural Heritage Interactive Dissemination through Natural Interaction
Virtual Heritage is widely used in education, enhancing the learning process by motivation
and by providing a natural experience. New ways for the user to explore cultural heritage …
and by providing a natural experience. New ways for the user to explore cultural heritage …