Abstract
Recent studies found out that supervised machine learning models can capture prejudices and stereotypes from training data. Our study focuses on the detection of gender stereotypes in relation to word embeddings. We review prior work on the topic and propose a comparative study of existing methods of gender stereotype detection. We evaluate various word embeddings models with these methods and conclude that the amount of bias does not depend on the corpora size and training algorithm, and does not correlate with embeddings performance on the standard evaluation benchmarks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Here and after we will use L2-normalized Euclidian distance in all cases where we measure the distance between the vectors: assuming that the vectors are normalized, the choice between Euclidian distance and cosine similarity does not affect their results [17].
References
Rogers, A., Hosur Ananthakrishna, S., Rumshisky, A.: What’s in your embedding, and how it predicts task performance. In: Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, New Mexico, USA, Association for Computational Linguistics, pp. 2690–2703, August 2018
Senel, L.K., Utlu, I., Yucesoy, V., Koc, A., Cukur, T.: Semantic structure and interpretability of word embeddings. arXiv preprint arXiv:1711.00331 (2017)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)
Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1521–1528. IEEE (2011)
Hardt, M., Price, E., Srebro, N., et al.: Equality of opportunity in supervised learning. In: Advances in Neural Information Processing Systems, pp. 3315–3323 (2016)
Gordon, J., Van Durme, B.: Reporting bias and knowledge extraction (2013)
Wagner, C., Garcia, D., Jadidi, M., Strohmaier, M.: It’s a man’s Wikipedia? Assessing gender inequality in an online encyclopedia. In: ICWSM, pp. 454–463 (2015)
Font, J.E., Costa-jussà, M.R.: Equalizing gender biases in neural machine translation with word embeddings techniques. arXiv preprint arXiv:1901.03116 (2019)
Mishra, A., Mishra, H., Rathee, S.: Examining the presence of gender bias in customer reviews using word embedding. arXiv preprint arXiv:1902.00496 (2019)
Blodgett, S.L., Barocas, S., Daumé III, H., Wallach, H.: Language (technology) is power: a critical survey of “bias” in NLP. arXiv preprint arXiv:2005.14050 (2020)
Schmidt, B.: Rejecting the gender binary: a vector-space operation (2015)
Bolukbasi, T., Chang, K.W., Zou, J.Y., Saligrama, V., Kalai, A.T.: Man is to computer programmer as woman is to homemaker? debiasing word embeddings. In: Advances in Neural Information Processing Systems, pp. 4349–4357 (2016)
Caliskan, A., Bryson, J.J., Narayanan, A.: Semantics derived automatically from language corpora contain human-like biases. Science 356(6334), 183–186 (2017)
Swinger, N., De-Arteaga, M., NeilThomasHeffernan, I., Leiserson, M.D.M., Kalai, A.T.: What are the biases in my word embedding? CoRR abs/1812.08769 (2018)
Zhao, J., Zhou, Y., Li, Z., Wang, W., Chang, K.W.: Learning gender-neutral word embeddings. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4847–4853 (2018)
Kozlowski, A.C., Taddy, M., Evans, J.A.: The geometry of culture: analyzing meaning through word embeddings. arXiv preprint arXiv:1803.09288 (2018)
Garg, N., Schiebinger, L., Jurafsky, D., Zou, J.: Word embeddings quantify 100 years of gender and ethnic stereotypes. Proc. Nat. Acad. Sci. 115(16), E3635–E3644 (2018)
Brunet, M.E., Alkalay-Houlihan, C., Anderson, A., Zemel, R.: Understanding the origins of bias in word embeddings. In: International Conference on Machine Learning, pp. 803–811 (2019)
Dev, S., Phillips, J.: Attenuating bias in word vectors. In: The 22nd International Conference on Artificial Intelligence and Statistics, pp. 879–887 (2019)
Lauscher, A., Glavaš, G., Ponzetto, S.P., Vulić, I.: A general framework for implicit and explicit debiasing of distributional word vector spaces. arXiv preprint arXiv:1909.06092 (2019)
Kaneko, M., Bollegala, D.: Gender-preserving debiasing for pre-trained word embeddings. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1641–1650 (2019)
Hoyle, A.M., Wolf-sonkin, L., Wallach, H., Augenstein, I., Cotterell, R.: Unsupervised discovery of gendered language through latent-variable modeling. In: 57th Annual Meeting of the Association for Computational Linguistics Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, pp. 1706–1716 (2019)
Basta, C., Costa-jussà, M.R., Casas, N.: Extensive study on the underlying gender bias in contextualized word embeddings. Neural Comput. Appl. 1–14 (2020). https://doi.org/10.1007/s00521-020-05211-z
Pujari, A.K., Mittal, A., Padhi, A., Jain, A., Jadon, M., Kumar, V.: Debiasing gender biased Hindi words with word-embedding. In: Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence, pp. 450–456 (2019)
Papakyriakopoulos, O., Hegelich, S., Serrano, J.C.M., Marco, F.: Bias in word embeddings. In: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pp. 446–457 (2020)
Gonen, H., Goldberg, Y.: Lipstick on a pig: debiasing methods cover up systematic gender biases in word embeddings but do not remove them. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 609–614 (2019)
Shin, S., Song, K., Jang, J., Kim, H., Joo, W., Moon, I.C.: Neutralizing gender bias in word embedding with latent disentanglement and counterfactual generation. arXiv preprint arXiv:2004.03133 (2020)
Gyamfi, E.O., Rao, Y., Gou, M., Shao, Y.: deb2viz: debiasing gender in word embedding data using subspace visualization. In: Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), vol. 11373, p. 113732F. International Society for Optics and Photonics (2020)
Wang, T., Lin, X.V., Rajani, N.F., McCann, B., Ordonez, V., Xiong, C.: Double-hard debias: tailoring word embeddings for gender bias mitigation. arXiv preprint arXiv:2005.00965 (2020)
Kumar, V., Bhotia, T.S., Kumar, V., Chakraborty, T.: Nurse is closer to woman than surgeon? Mitigating gender-biased proximities in word embeddings. Trans. Assoc. Comput. Linguist. 8, 486–503 (2020)
Rios, A., Joshi, R., Shin, H.: Quantifying 60 years of gender bias in biomedical research with word embeddings. In: Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing, pp. 1–13 (2020)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Kutuzov, A., Fares, M., Oepen, S., Velldal, E.: Word vectors, reuse, and replicability: towards a community repository of large-text resources. In: Proceedings of the 58th Conference on Simulation and Modelling, pp. 271–276. Linköping University Electronic Press (2017)
Rubenstein, H., Goodenough, J.B.: Contextual correlates of synonymy. Commun. ACM 8(10), 627–633 (1965)
Luong, M.T., Socher, R., Manning, C.D.: Better word representations with recursive neural networks for morphology. In: Proceedings of the Seventeenth Conference on Computational Natural Language Learning, pp. 104–113 (2013)
Agirre, E., Alfonseca, E., Hall, K., Kravalová, J., Pasca, M., Soroa, A.: A study on similarity and relatedness using distributional and wordnet-based approaches. In: Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 19–27 (2009)
Mikolov, T., Yih, W.t., Zweig, G.: Linguistic regularities in continuous space word representations. In: Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 746–751 (2013)
Bakarov, A.: A survey of word embeddings evaluation methods. arXiv preprint arXiv:1801.09536 (2018)
Acknowledgments
The reported study was funded by the Russian Foundation for Basic Research project 20-37-90153 “Development of framework for distributional semantic models evaluation”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Bakarov, A. (2021). Did You Just Assume My Vector? Detecting Gender Stereotypes in Word Embeddings. In: van der Aalst, W.M.P., et al. Recent Trends in Analysis of Images, Social Networks and Texts. AIST 2020. Communications in Computer and Information Science, vol 1357. Springer, Cham. https://doi.org/10.1007/978-3-030-71214-3_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-71214-3_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-71213-6
Online ISBN: 978-3-030-71214-3
eBook Packages: Computer ScienceComputer Science (R0)