Year: 2020
Type: preprint
Abstract: There is a growing collection of work analyzing and mitigating societal biases in language understanding, generation, and retrieval tasks, though examining biases in creative tasks remains underexplored. Creative language applications are meant for direct interaction with users, so it is important to quantify and mitigate societal biases in these applications. We introduce a novel study on a pipeline to mitigate societal biases when retrieving next verse suggestions in a poetry composition system. Our results suggest that data augmentation through sentiment style transfer has potential for mitigating societal biases.
Source: arXiv (Cornell University)
Authors: Sheng, Emily, Uthus, David
Institutions: University of Southern California, Google (United States)
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
SDG: Reduced inequalities
Open Access status: green
OpenAlex ID: W3095399481