We propose a fully unsupervised method to detect bias in contextualized
...
We present a novel approach incorporating transformer-based language mod...
Geographic linguistic features are commonly used to improve the performa...
Labelled data is the foundation of most natural language processing task...
The increasing polarization of online political discourse calls for
comp...
Language use differs between domains and even within a domain, language ...
How does the input segmentation of pretrained language models (PLMs) aff...
Static word embeddings that represent words by a single vector cannot ca...
Can BERT generate derivationally complex words? We present the first stu...