Harmful content detection models tend to have higher false positive rate...
Natural Language Processing (NLP) models propagate social biases about
p...
Technology for language generation has advanced rapidly, spurred by
adva...
Dialogue systems in the form of chatbots and personal assistants are bei...
There is a growing collection of work analyzing and mitigating societal
...
Ad hominem attacks are those that attack some feature of a person's char...
We present a general approach towards controllable societal biases in na...
We present a systematic study of biases in natural language generation (...
In biomedical literature, it is common for entity boundaries to not alig...
Characterizing the content of a technical document in terms of its learn...