Citation map · Study

SZodixStudyAcademic Library

Shelves Open access

Study · an open academic library·Metadata from OpenAlex (CC0)·Shelves·OpenAlex metadata, de-duplicated

A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces

9 references·5 citing·37 second hop

FromToDepth

this work references cited by second hop

References

1954Distributional Structure4,806 cited
2017Semantics derived automatically from language corpora contain human-like biases2,845 cited
2018Word embeddings quantify 100 years of gender and ethnic stereotypes1,064 cited
2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints829 cited
2019Gender Bias in Contextualized Word Embeddings334 cited
2019Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings262 cited
2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them242 cited
2019Attenuating Bias in Word Vectors99 cited
2019Are We Consistently Biased? Multidimensional Analysis of Biases in Distributional Word Vectors52 cited

Cited by

2021OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings33 cited
2022Multi-objective search for gender-fair and semantically correct word embeddings22 cited
2020AraWEAT: Multidimensional Analysis of Biases in Arabic Word Embeddings19 cited
2021Intrinsic Bias Metrics Do Not Correlate with Application Bias17 cited
2023CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models14 cited

Only edges whose both ends are imported exist here. Widen the year window, or show the whole map. Back to the work