most citedExploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model

2 citations · 2 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CL2023★ 2 cited

Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model

Chantal Amrhein, Florian Schottmann, Rico Sennrich +1

Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to…