Giuseppe Attanasio

ferret. A python package for benchmarking interpretability techniques on Transformers.

ear. Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"

l3wrapper. A lightweight Python 3 wrapper around the binaries of the L3 associative classifier.

multilingual-asr-gender-gap. Code associated with the paper "Multilingual Speech Models for Automatic Speech Recognition Exhibit Gender Performance Gaps."

sherlook. Python

speech-models-on-telegram. Python

gender-bias-qe-metrics. Code associated with the paper "Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation."

yet_another_jax_transformer. Makefile

confidence_intervals. Simple evaluation of classification confidence intervals.

interpretable-trading. Jupyter Notebook