-
Fortifying Toxic Speech Detectors Against Veiled Toxicity
Modern toxic speech detectors are incompetent in recognizing disguised o...
read it
-
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions
Modern deep learning models for NLP are notoriously opaque. This has mot...
read it
-
No Permanent Friends or Enemies: Tracking Relationships between Nations from News
Understanding the dynamics of international politics is important yet ch...
read it
-
Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling
Contextualized word embeddings such as ELMo and BERT provide a foundatio...
read it
-
Unsupervised Domain Adaptation of Contextualized Embeddings: A Case Study in Early Modern English
Contextualized word embeddings such as ELMo and BERT provide a foundatio...
read it
-
Mind Your POV: Convergence of Articles and Editors Towards Wikipedia's Neutrality Norm
Wikipedia has a strong norm of writing in a 'neutral point of view' (NPO...
read it

Xiaochuang Han
is this you? claim profile