Investigating Societal Biases in a Poetry Composition System
arXiv:2011.02686
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.
arXiv comment14 pages, 2nd Workshop on Gender Bias in NLP
References in corpus (7)
- Semantics derived automatically from language corpora contain human-like biases
- Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
- Fairness of Exposure in Rankings
- FA*IR: A Fair Top-k Ranking Algorithm
- Efficient Natural Language Response Suggestion for Smart Reply
- Gender Bias in Neural Natural Language Processing
- Reducing Sentiment Bias in Language Models via Counterfactual Evaluation