# Marked Attribute Bias in Natural Language Inference

arXiv: https://arxiv.org/abs/2109.14039 · HTML: https://mlsanity.com/paper/2109.14039/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 28 Sep 2021.

## Builds on (most cited first, 20 of 20)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [A Decomposable Attention Model for Natural Language Inference](https://mlsanity.com/paper/1606.01933/) (2016)
- [SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation](https://mlsanity.com/paper/1408.3456/) (2014)
- [Learning Gender-Neutral Word Embeddings](https://mlsanity.com/paper/1809.01496/) (2018)
- [On Measuring and Mitigating Biased Inferences of Word Embeddings](https://mlsanity.com/paper/1908.09369/) (2019)
- [Gender-preserving Debiasing for Pre-trained Word Embeddings](https://mlsanity.com/paper/1906.00742/) (2019)
- [OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings](https://mlsanity.com/paper/2007.00049/) (2020)
- [A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces](https://mlsanity.com/paper/1909.06092/) (2019)
- [Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation](https://mlsanity.com/paper/2005.00965/) (2020)
- [Nurse is Closer to Woman than Surgeon? Mitigating Gender-Biased Proximities in Word Embeddings](https://mlsanity.com/paper/2006.01938/) (2020)
- [How to evaluate word embeddings? On importance of data efficiency and simple supervised tasks](https://mlsanity.com/paper/1702.02170/) (2017)
- [Decision-Directed Data Decomposition](https://mlsanity.com/paper/1909.08159/) (2019)

## Built on by (most cited first, 6 of 6)

- [NBIAS: A Natural Language Processing Framework for Bias Identification in Text](https://mlsanity.com/paper/2308.01681/) (2023)
- [Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation](https://mlsanity.com/paper/2205.12593/) (2022)
- [On Measuring Social Biases in Prompt-Based Multi-Task Learning](https://mlsanity.com/paper/2205.11605/) (2022)
- [(Ir)rationality in AI: State of the Art, Research Challenges and Open Questions](https://mlsanity.com/paper/2311.17165/) (2023)
- [Labels Need Prompts Too: Mask Matching for Natural Language Understanding Tasks](https://mlsanity.com/paper/2312.08726/) (2023)
- [Projective Methods for Mitigating Gender Bias in Pre-trained Language Models](https://mlsanity.com/paper/2403.18803/) (2024)

## Abstract (arXiv)

Reporting and providing test sets for harmful bias in NLP applications is essential for building a robust understanding of the current problem. We present a new observation of gender bias in a downstream NLP application: marked attribute bias in natural language inference. Bias in downstream applications can stem from training data, word embeddings, or be amplified by the model in use. However, focusing on biased word embeddings is potentially the most impactful first step due to their universal nature. Here we seek to understand how the intrinsic properties of word embeddings contribute to this observed marked attribute effect, and whether current post-processing methods address the bias successfully. An investigation of the current debiasing landscape reveals two open problems: none of the current debiased embeddings mitigate the marked attribute error, and none of the intrinsic bias measures are predictive of the marked attribute effect. By noticing that a new type of intrinsic bias measure correlates meaningfully with the marked attribute effect, we propose a new postprocessing debiasing scheme for static word embeddings. The proposed method applied to existing embeddings achieves new best results on the marked attribute bias test set. See https://github.com/hillary-dawkins/MAB.