Clean-label (CL) attack is a form of data poisoning attack where an adve...
Can language models transform inputs to protect text classifiers against...
Sanskrit is a low-resource language with a rich heritage. Digitized Sans...
Symbolic knowledge can provide crucial inductive bias for training neura...
In this work, we introduce X-FACT: the largest publicly available
multil...
Neural dependency parsing has achieved remarkable performance for many
d...
In this paper, we study the response of large models from the BERT famil...
Neural sequence labelling approaches have achieved state of the art resu...
Data-driven approaches for dependency parsing have been of great interes...