← Search

Diego Fernandez Slezak

2 accepted papers

2023

On the Interpretability and Significance of Bias Metrics in Texts: a PMI-based Approach

ACL 2023short

In recent years, word embeddings have been widely used to measure biases in texts. Even if they have proven to be effective in detecting a wide variety of biases, metrics based on word embeddings lack transparency and interpretability. We analyze an alternative PMI-based metric to quantify biases in…

2022

The Undesirable Dependence on Frequency of Gender Bias Metrics Based on Word Embeddings

EMNLP 2022finding

Numerous works use word embedding-based metrics to quantify societal biases and stereotypes in texts. Recent studies have found that word embeddings can capture semantic similarity but may be affected by word frequency. In this work we study the effect of frequency when measuring female vs. male gen…