A
Andrew Gaut
Publications - 4
Citations - 399
Andrew Gaut is an academic researcher. The author has contributed to research in topics: Debiasing & Counterfactual thinking. The author has an hindex of 4, co-authored 4 publications receiving 241 citations.
Papers
More filters
Proceedings ArticleDOI
Mitigating Gender Bias in Natural Language Processing: Literature Review
Tony Sun,Andrew Gaut,Shirlyn Tang,Yuxin Huang,Mai ElSherief,Jieyu Zhao,Diba Mirza,Elizabeth Belding,Kai-Wei Chang,William Yang Wang +9 more
TL;DR: This paper discusses gender bias based on four forms of representation bias and analyzes methods recognizing gender bias in NLP, and discusses the advantages and drawbacks of existing gender debiasing methods.
Posted Content
Mitigating Gender Bias in Natural Language Processing: Literature Review.
Tony Sun,Andrew Gaut,Shirlyn Tang,Yuxin Huang,Mai ElSherief,Jieyu Zhao,Diba Mirza,Elizabeth Belding,Kai-Wei Chang,William Yang Wang +9 more
TL;DR: This paper reviewed contemporary studies on recognizing and mitigating gender bias in NLP and discussed gender bias based on four forms of representation bias and analyzed methods for recognizing gender bias and debiasing methods.
Proceedings ArticleDOI
Towards Understanding Gender Bias in Relation Extraction
Andrew Gaut,Tony Sun,Shirlyn Tang,Yuxin Huang,Jing Qian,Mai ElSherief,Jieyu Zhao,Diba Mirza,Elizabeth Belding,Kai-Wei Chang,William Yang Wang +10 more
TL;DR: In this paper, the authors created WikiGenderBias, a distantly supervised dataset composed of over 45,000 sentences including a 10% human annotated test set for the purpose of analyzing gender bias in relation extraction systems.
Posted Content
Towards Understanding Gender Bias in Relation Extraction
Andrew Gaut,Tony Sun,Shirlyn Tang,Yuxin Huang,Jing Qian,Mai ElSherief,Jieyu Zhao,Diba Mirza,Elizabeth Belding,Kai-Wei Chang,William Yang Wang +10 more
TL;DR: This article created WikiGenderBias, a distantly supervised dataset with a human annotated test set to evaluate gender bias in relation extraction systems and found that NRE systems exhibit gender biased predictions.