『人工智能』当谈论机器学习中的公平公正时，我们该谈论些什么？(11) |算法|软件|Google|

分析师介绍：仵冀颖，工学博士，毕业于北京交通大学，曾分别于香港中文大学和香港科技大学担任助理研究员和研究助理，现从事电子政务领域信息化新技术研究工作。主要研究方向为模式识别、计算机视觉，爱好科研，希望能保持学习、不断进步。
本文中引用的参考文献：
[1] Saxena, Nripsuta, Huang, Karen, DeFilippis, Evan,et al. How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness. https://arxiv.org/pdf/1908.09635.pdf.
[2] James Zou, Londa Schiebinger, AI can be sexist and racist—it』s time to make it fair. https://www.nature.com/articles/d41586-018-05707-8.
[3] Stephen Merity, Nitish Shirish Keskar, and Richard Socher. 2018. Regularizing and optimizing LSTM language models. In International Conference on Learning Representations.
[4] Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Or-donez, and Kai-Wei Chang. 2017. Men also likeshopping: Reducing gender bias amplification usingcorpus-level constraints. InEMNLP, pages 2979–2989. Association for Computational Linguistics.
[5] Tolga Bolukbasi, Kai-Wei Chang, James Y Zou,Venkatesh Saligrama, and Adam T Kalai. 2016.Man is to computer programmer as woman is tohomemaker? Debiasing word embeddings. In D. D.Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, andR. Garnett, editors,Advances in Neural InformationProcessing Systems 29, pages 4349–4357. CurranAssociates, Inc.
[6] Joel Escud ?e Font and Marta R. Costa-Juss`a. 2019.Equalizing gender biases in neural machine trans-lation with word embeddings techniques.CoRR,abs/1901.03116.
[7] Xu, B., Wang, N., Chen, T., and Li, M. Empirical evaluationof rectified activations in convolutional network.DeepLearning Workshop, ICML 2015, 2015.
[8] Ji, G., He, S., Xu, L., Liu, K., and Zhao, J. Knowledgegraph embedding via dynamic mapping matrix. InACL,2015.
[9] Toutanova, K., Chen, D., Pantel, P., Poon, H., Choudhury,P., and Gamon, M. Representing text for joint embeddingof text and knowledge bases. InEMNLP, 2015.
[10] Johnson, K. D., Foster, D. P., and Stine, R. A. Impartial predictive modeling: Ensuring fairness in arbitrary models. arXiv:1608.00528, 2016.
[11] Agarwal, A., Beygelzimer, A., Dud′?k, M., Langford, J., and Wallach, H. A reductions approach to fair classification. In ICML , 2018.