P
Álvaro Parafita
@aparafita.bsky.social
PhD in Causal Estimation with estimand-agnostic frameworks, working on Explainability and Fairness applications for ML black-boxes.
Github: @aparafita
12 followers8 following1 posts
Reposted by Álvaro Parafita
We're presenting, "Enhancing Interpretability using Human Similarity Judgements to Prune Word Embeddings", at the BlackboxNLP workshop in EMNLP2023. We improve prediction of human similarity judgments for co-hyponyms and provide interpretability of pruned embeddings. #MLSky #CogSci Link: t.ly/NTRRS
P
Álvaro Parafita
@aparafita.bsky.social
PhD in Causal Estimation with estimand-agnostic frameworks, working on Explainability and Fairness applications for ML black-boxes.
Github: @aparafita
12 followers8 following1 posts