Search Results for author:
Found 6 papers, 1 papers with code
Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scale
Our initial findings show that translation quality for EN-to-XX translations is an average of 8 spBLEU better when evaluating with the masculine human reference compared to feminine.
Polyhedral geometry and combinatorics of an autocatalytic ecosystem
Developing a mathematical understanding of autocatalysis in reaction networks has both theoretical and practical implications.
Toxicity in Multilingual Machine Translation at Scale
We evaluate and analyze added toxicity when translating a large evaluation dataset (HOLISTICBIAS, over 472k sentences, covering 13 demographic axes) from English into 164 languages.
Perturbation Augmentation for Fairer NLP
Unwanted and often harmful social biases are becoming ever more salient in NLP research, affecting both models and datasets.
Multiple-Attribute Text Rewriting
The dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "style".
