Biases
Related Papers
Confounds and Consequences in Geotagged Twitter Data
Twitter is often used in quantitative stud- ies that identify geographically-preferred topics, writing styles, and entities. These studies rely on either GPS coordinates at- tached to individual messages, or on …...
BERT Busters: Outlier Dimensions that Disrupt Transformers
Multiple studies have shown that Transform- ers are remarkably robust to pruning. Con- trary to this received wisdom, we demon- strate that pre-trained Transformer encoders are surprisingly fragile to the …...
Gender and Racial Fairness in Depression Research using Social Media
AbstractMultiple studies have demonstrated that behaviors expressed on online social media platforms can indicate the mental health state of an individual. The widespread availability of such data has spurred interest …...
Measuring Context-Word Biases in Lexical Semantic Datasets
AbstractState-of-the-art pretrained contextualized models (PCM) eg. BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that performance in these tasks reflect how well …...
Transformers and the Representation of Biomedical Background Knowledge
AbstractSpecialized transformers-based models (such as BioBERT and BioMegatron) are adapted for the biomedical domain based on publicly available biomedical corpora. As such, they have the potential to encode large-scale biological …...