Published in Focus On Microscopy, 2021
We demonstrate a neural net capable of recognizing and correcting common misalignments and aberrations in STED microscopy.
Recommended citation: Jahr, Wiebke. McGovern, Hope. Danzl, Johann Georg (2020). "Paper Title Number 3." Journal 1. 1(3). https://www.focusonmicroscopy.org/past/2021/PDF/1081_Jahr.pdf
Published in ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI, 2021
It is well-documented that word embeddings trained on large public corpora consistently exhibit known human social biases. Although many methods for debiasing exist, almost all fixate on completely eliminating biased information from the embeddings and often diminish training set size in the process. In this paper, we present a simple yet effective method for debiasing GloVe word embeddings (Pennington et al., 2014) which works by incorporating explicit information about training set bias rather than removing biased data outright. Our method runs quickly and efficiently with the help of a fast bias gradient approximation method from Brunet et al. (2019). As our approach is akin to the notion of ‘source crit-icism’ in the humanities, we term our method Source-Critical GloVe (SC-GloVe). We show that SC-GloVe reduces the effect size on Word Embedding Association Test (WEAT) sets without sacrificing training data or TOP-1 performance.
Recommended citation: McGovern, Hope. (2021). "A Source-Criticism Debiasing Method for GloVe Embeddings." ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI. 1(1). https://arxiv.org/pdf/2106.13382.pdf