--- title: "Lipstick on a Pig — Gonen 2019" description: "Gonen and Goldberg examine whether popular gender-debiasing techniques for word embeddings actually remove bias or only mask it." authors: ["Hila Gonen", "Yoav Goldberg"] year: 2019 venue: "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)" source: "https://aclanthology.org/N19-1061/" doi: "10.18653/v1/n19-1061" arxiv: "1903.03862" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/gonen-2019-lipstick-pig-debiasing-methods-cover/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/gonen-2019-lipstick-pig-debiasing-methods-cover/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2019](https://md.research.elamur.ai/free/en/papers/2019/page/3/) / Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them # Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them **Authors:** [Hila Gonen](https://md.research.elamur.ai/free/en/authors/hila-gonen/), [Yoav Goldberg](https://md.research.elamur.ai/free/en/authors/yoav-goldberg/) · **Year:** 2019 · **Venue:** 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) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/N19-1061/) · [PDF](https://aclanthology.org/N19-1061.pdf) · [DOI 10.18653/v1/n19-1061](https://doi.org/10.18653/v1/n19-1061) · [arXiv 1903.03862](https://arxiv.org/abs/1903.03862) · [OpenAlex](https://openalex.org/W2963381846) **Citations:** 155 citations (openalex-snapshot · 2026-10-14) · [257](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary Gonen and Goldberg examine whether popular gender-debiasing techniques for word embeddings actually remove bias or only mask it. They test two methods. HARD-DEBIASED (Bolukbasi et al., 2016b) is post-processing applied to word2vec trained on Google News. GN-GLOVE (Zhao et al., 2018) modifies the GloVe training objective. Both methods target a single bias definition: a word's projection onto the he–she gender direction. The authors measure bias in other ways and compare each debiased model with its original counterpart. Their tests include k-means clustering of strongly biased words, a new bias score based on the gender makeup of a word's nearest neighbours, WEAT association tests, and an SVM classifier that predicts the original gender association. In every test, much of the stereotypical structure survives debiasing. Words that were socially gendered still sit near each other, so the bias remains recoverable from the geometry of the space. The authors conclude that projection-based debiasing gives a misleading sense of gender neutrality. They argue that bias definitions and removal methods need to go beyond the gender direction. ## Key points - **Clustering:** The 1,000 most biased words were split into two k-means clusters. These clusters still matched the original gender with 92.5% accuracy for HARD-DEBIASED (99.9% before debiasing) and 85.6% for GN-GLOVE (100% before). - **Neighbour-based bias:** This score correlated with the original projection bias at Pearson 0.686 for HARD-DEBIASED and 0.736 for GN-GLOVE. For profession words, the correlations were 0.606 and 0.792. - **Classifier test:** An RBF-kernel SVM was trained on 1,000 of the 5,000 most biased words. It recovered gender for the remaining words with 88.88% accuracy for HARD-DEBIASED (98.25% before) and 96.53% for GN-GLOVE (98.65% before). - **WEAT tests:** All three Caliskan et al. (2017) WEAT tests (career/family, math/arts, science/arts, using names) remained significant after debiasing. - **Data and code:** The reduced vocabularies contained 26,189 words for HARD-DEBIASED and 47,698 for GN-GLOVE. The code is published at github.com/gonenhila/gender_bias_lipstick. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/) ## Cited by Cited by 257 papers of our library cite it (of the 140673 whose bibliographies we read); 39 of them have a page here, 218 not yet. - [JW300: A Wide-Coverage Parallel Corpus for Low-Resource Languages](https://md.research.elamur.ai/free/en/papers/agic-2019-jw300-wide-coverage-parallel-corpus/) - [The Arabic Parallel Gender Corpus 2.0: Extensions and Analyses](https://md.research.elamur.ai/free/en/papers/alhafni-2022-arabic-parallel-gender-corpus-2/) - [Language (Technology) is Power: A Critical Survey of “Bias” in NLP](https://md.research.elamur.ai/free/en/papers/blodgett-2020-language-technology-is-power-critical/) - [Interpreting Pretrained Contextualized Representations via Reductions to Static Embeddings](https://md.research.elamur.ai/free/en/papers/bommasani-2020-interpreting-pretrained-contextualized-representations-reductions/) - [On the Opportunities and Risks of Foundation Models](https://md.research.elamur.ai/free/en/papers/bommasani-2021-opportunities-risks-foundation-models/) - [Identifying and Reducing Gender Bias in Word-Level Language Models](https://md.research.elamur.ai/free/en/papers/bordia-2019-identifying-reducing-gender-bias-word/) - [Toward Gender-Inclusive Coreference Resolution](https://md.research.elamur.ai/free/en/papers/cao-2020-gender-inclusive-coreference-resolution/) - [Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle*](https://md.research.elamur.ai/free/en/papers/cao-2021-gender-inclusive-coreference-resolution-analysis/) - [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://md.research.elamur.ai/free/en/papers/davidson-2019-racial-bias-hate-speech-abusive/) - [RobBERT: a Dutch RoBERTa-based Language Model](https://md.research.elamur.ai/free/en/papers/delobelle-2020-robbert-dutch-roberta-based-language/) - [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://md.research.elamur.ai/free/en/papers/dinan-2020-queens-are-powerful-too-mitigating/) - [Bias and Fairness in Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/gallegos-2023-bias-fairness-large-language-models/) - [Auto-Debias: Debiasing Masked Language Models with Automated Biased Prompts](https://md.research.elamur.ai/free/en/papers/guo-2022-auto-debias-debiasing-masked-language/) - [Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual](https://md.research.elamur.ai/free/en/papers/he-2019-unlearn-dataset-bias-natural-language/) - [The Importance of Modeling Social Factors of Language: Theory and Practice](https://md.research.elamur.ai/free/en/papers/hovy-2021-importance-modeling-social-factors-language/) - [Debiasing Pre-trained Contextualised Embeddings](https://md.research.elamur.ai/free/en/papers/kaneko-2021-debiasing-pre-trained-contextualised-embeddings/) - [Towards Debiasing Sentence Representations](https://md.research.elamur.ai/free/en/papers/liang-2020-debiasing-sentence-representations/) - [Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings](https://md.research.elamur.ai/free/en/papers/manzini-2019-black-is-criminal-as-caucasian/) - [A Survey on Bias and Fairness in Machine Learning](https://md.research.elamur.ai/free/en/papers/mehrabi-2019-survey-bias-fairness-machine-learning/) - [Towards Reliable AI Fairness: Challenges in Steering Features within Bias-Implicated Neurons](https://md.research.elamur.ai/free/en/papers/munoz-2026-reliable-ai-fairness-challenges-steering/) - [StereoSet: Measuring stereotypical bias in pretrained language models](https://md.research.elamur.ai/free/en/papers/nadeem-2021-stereoset-measuring-stereotypical-bias-pretrained/) - [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://md.research.elamur.ai/free/en/papers/nangia-2020-crows-pairs-challenge-dataset-measuring/) - [HONEST: Measuring Hurtful Sentence Completion in Language Models](https://md.research.elamur.ai/free/en/papers/nozza-2021-honest-measuring-hurtful-sentence-completion/) - [GPT-4 Technical Report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/) - [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://md.research.elamur.ai/free/en/papers/ravfogel-2020-null-it-out-guarding-protected/) - [Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem](https://md.research.elamur.ai/free/en/papers/saunders-2020-reducing-gender-bias-neural-machine/) - [Gender Bias in Machine Translation](https://md.research.elamur.ai/free/en/papers/savoldi-2021-gender-bias-machine-translation/) - [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://md.research.elamur.ai/free/en/papers/schick-2021-self-diagnosis-self-debiasing-proposal/) - [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://md.research.elamur.ai/free/en/papers/shah-2019-predictive-biases-natural-language-processing/) - [On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning](https://md.research.elamur.ai/free/en/papers/shaikh-2023-second-thought-let-s-not/) - [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://md.research.elamur.ai/free/en/papers/srivastava-2022-imitation-game-quantifying-extrapolating-capabilities/) - [Uncertainty Quantification for Evaluating Gender Bias in Machine Translation](https://md.research.elamur.ai/free/en/papers/staliunaite-2026-uncertainty-quantification-evaluating-gender-bias/) - [Evaluating Gender Bias in Machine Translation](https://md.research.elamur.ai/free/en/papers/stanovsky-2019-evaluating-gender-bias-machine-translation/) - [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://md.research.elamur.ai/free/en/papers/sun-2019-mitigating-gender-bias-natural-language/) - [Intrinsic Bias Metrics Do Not Correlate with Application Bias](https://md.research.elamur.ai/free/en/papers/tarrant-2021-intrinsic-bias-metrics-do-not/) - [How Far Can Bias Go? Tracing Bias from Pre-Training Data to Alignment](https://md.research.elamur.ai/free/en/papers/thaler-2026-how-far-can-bias-go/) - [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://md.research.elamur.ai/free/en/papers/wang-2019-superglue-stickier-benchmark-general-purpose/) - [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://md.research.elamur.ai/free/en/papers/webster-2020-measuring-reducing-gendered-correlations-pre/) - [Gender Bias in Contextualized Word Embeddings](https://md.research.elamur.ai/free/en/papers/zhao-2019-gender-bias-contextualized-word-embeddings/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{gonen2019lipstick, title = {{Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them}}, author = {Gonen, Hila and Goldberg, Yoav}, booktitle = {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)}, year = {2019}, doi = {10.18653/v1/n19-1061}, eprint = {1903.03862}, archivePrefix = {arXiv}, url = {https://doi.org/10.18653/v1/n19-1061} } ``` - [← previous Linguistic-functional Analysis of the Biblical Hebrew Lexemes ʿaṭarâ, keter and nezer](https://md.research.elamur.ai/free/en/papers/hbo-2019-stornaiuolo-linguistic-functional-analysis-biblical-hebrew/) - [next → Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation](https://md.research.elamur.ai/free/en/papers/vanmassenhove-2019-lost-translation-loss-decay-linguistic/) - [↑ back to papers of 2019](https://md.research.elamur.ai/free/en/papers/2019/page/3/) ## References 2 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, and Adam Kalai. 2016a. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. arXiv:1607.06520. 3. The implicit gender of words with prevalent previous bias is easy to predict based on their vectors alone. [find](https://scholar.google.com/scholar?q=Tolga+Bolukbasi%2C+Kai%2DWei+Chang%2C+James+Zou%2C+Venkatesh+Saligrama%2C+and+Adam+Kalai%2E+2016a%2E+Man+is+to+computer+programmer+as+woman+is+to+homemaker%3F+debiasing+word+embeddings%2E+arXiv%3A1607%2E06520%2E+3%2E+The+impli) [our card](https://md.research.elamur.ai/free/en/papers/bolukbasi-2016-man-computer-programmer-woman-homemaker/) 2. Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016b. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. In Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Tolga+Bolukbasi%2C+Kai%2DWei+Chang%2C+James+Y+Zou%2C+Venkatesh+Saligrama%2C+and+Adam+T+Kalai%2E+2016b%2E+Man+is+to+computer+programmer+as+woman+is+to+homemaker%3F+debiasing+word+embeddings%2E+In+Advances+in+Neural+Info) [our card](https://md.research.elamur.ai/free/en/papers/bolukbasi-2016-man-computer-programmer-woman-homemaker/)