Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings

Thomas Manzini, Yao Chong Lim, Alan W. Black, Yulia Tsvetkov. Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings. In Jill Burstein, Christy Doran, Thamar Solorio, editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers). pages 615-621, Association for Computational Linguistics, 2019. [doi]

@inproceedings{ManziniLBT19,
  title = {Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings},
  author = {Thomas Manzini and Yao Chong Lim and Alan W. Black and Yulia Tsvetkov},
  year = {2019},
  url = {https://aclweb.org/anthology/papers/N/N19/N19-1062/},
  researchr = {https://researchr.org/publication/ManziniLBT19},
  cites = {0},
  citedby = {0},
  pages = {615-621},
  booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers)},
  editor = {Jill Burstein and Christy Doran and Thamar Solorio},
  publisher = {Association for Computational Linguistics},
  isbn = {978-1-950737-13-0},
}