AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations

AAAI 2020 · Probabilistic and scientific modeling › Treatment effects · approach: Proximal and deep causal effect estimation · 34 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Apply Half-Sibling Regression to GloVeGloVe word embeddings · GBWR-CorrelationPearson correlation coefficient: 0.6884 -> 0.6422Helped
Apply Half-Sibling Regression to GloVeGloVe word embeddings · GBWR-ProfessionPearson correlation coefficient: 0.7161 -> 0.6804Helped
Apply Half-Sibling Regression to GloVeGloVe word embeddings · Word similarity tasks (eight-task average)Spearman correlation: 6.96%Helped
Apply Half-Sibling Regression to GloVeGloVe word embeddings · Semantic textual similarity tasks (20-task average)Pearson correlation coefficient: 14.19%Helped
Apply Half-Sibling Regression to GloVeGloVe word embeddings · WinoBiasPRO-ANTI F1 difference: 87.26%Helped
Apply Half-Sibling Regression to GloVeGloVe word embeddings · OntoNotes-testaverage F1 score: 66.5 -> 66.2No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy