AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

On Measuring and Mitigating Biased Inferences of Word Embeddings

Sunipa Dev, Tao Li, Jeff M. Phillips, Vivek Srikumar

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 117 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
Project out the he-she directionGloVe · Gender-occupationNN: 0.387 -> 0.480; +24.7%Improved
Project out the demonym subspaceGloVe · Demonym-polarityNN: 0.713 -> 0.808; +13.3%Improved
Project out the adherent subspaceGloVe · Religion-polarityNN: 0.710 -> 0.794; +11.8%Improved
Project out a random vector instead of the gender direction (ablation)GloVe · Gender-occupationNN: 0.387 -> 0.362; -6.0%No clear effect
Project out the gender direction from all ELMo layers (ablation)ELMo · Gender-occupationNN: 0.417 -> 0.423; +1.6%No clear effect
Project out a random direction from all ELMo layers (ablation)ELMo · Gender-occupationT:0.7: 0.063 -> 0.115; +82.5%Mixed
Project out the he-she direction from ELMo layer 1ELMo · Gender-occupationNN: 0.417 -> 0.488; +17.3%Improved
Project out the demonym direction from ELMo layer 1 (ablation)ELMo · Demonym-polarityNN: -10.7%Hurt
Project out the adherent direction from ELMo layer 1 (ablation)ELMo · Religion-polarityNN: -13.2%Hurt
Apply the BERT gender projection only at test time (ablation)BERT · Gender-occupationNN: 0.421 -> 0.396; -5.9%Hurt
Apply the BERT gender projection during training and at test timeBERT · Gender-occupationNN: 0.421 -> 0.516; +22.6%Improved
Apply the BERT gender projection during training and at test timeBERT · SNLI testaccuracy: 90.22 -> 90.23No 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