HIGHLIGHTS
- who: Tommaso Dolci from the Department of Electronics, Information and Bioengineering, Politecnico di Milano, Piazza Leonardo da Vinci, , Milano, Italy have published the research work: Improving Gender-Related Fairness in Sentence Encoders: A Semantics-Based Approach, in the Journal: (JOURNAL)
- what: The authors propose a new metric to estimate gender bias in sentence embeddings named bias score. The authors compare the experiments with traditional methods for reducing bias in embedding-based language models. In the second part of the paper, the authors leverage bias score to retrieve the more stereotyped sentences from the Stanford Natural . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.