WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings

Intersectional bias is a bias caused by an overlap of multiple social factors like gender, sexuality, race, disability, religion, etc. A recent study has shown that word embedding models can be laden with biases against intersectional groups like African American females, etc. The first step towards tackling intersectional biases is to identify them. However, discovering biases against different intersectional groups remains a challenging task. In this work, we present WordBias, an interactive visual tool designed to explore biases against intersectional groups encoded in static word embeddings. Given a pretrained static word embedding, WordBias computes the association of each word along different groups like race, age, etc. and then visualizes them using a novel interactive interface. Using a case study, we demonstrate how WordBias can help uncover biases against intersectional groups like Black Muslim Males, Poor Females, etc. encoded in word embedding. In addition, we also evaluate our tool using qualitative feedback from expert interviews. The source code for this tool can be publicly accessed for reproducibility at github.com/bhavyaghai/WordBias.

[1]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[2]  Orestis Papakyriakopoulos,et al.  Bias in word embeddings , 2020, FAT*.

[3]  David Mimno,et al.  Bad Seeds: Evaluating Lexical Methods for Bias Measurement , 2021, ACL.

[4]  Ryan Cotterell,et al.  Gender Bias in Contextualized Word Embeddings , 2019, NAACL.

[5]  Yu-Ru Lin,et al.  FairSight: Visual Analytics for Fairness in Decision Making , 2019, IEEE Transactions on Visualization and Computer Graphics.

[6]  Alan W Black,et al.  Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings , 2019, NAACL.

[7]  Matt Taddy,et al.  The Geometry of Culture: Analyzing the Meanings of Class through Word Embeddings , 2018, American Sociological Review.

[8]  Aylin Caliskan,et al.  Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases , 2020, AIES.

[9]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[10]  Ryan Cotterell,et al.  Examining Gender Bias in Languages with Grammatical Gender , 2019, EMNLP.

[11]  Alexandra Chouldechova,et al.  Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting , 2019, FAT.

[12]  Noah A. Smith,et al.  Evaluating Gender Bias in Machine Translation , 2019, ACL.

[13]  Goran Glavas,et al.  AraWEAT: Multidimensional Analysis of Biases in Arabic Word Embeddings , 2020, WANLP.

[14]  Hubert Lin,et al.  Silva: Interactively Assessing Machine Learning Fairness Using Causality , 2020, CHI.

[15]  Klaus Mueller,et al.  The Data Context Map: Fusing Data and Attributes into a Unified Display , 2016, IEEE Transactions on Visualization and Computer Graphics.

[16]  Yi Chern Tan,et al.  Assessing Social and Intersectional Biases in Contextualized Word Representations , 2019, NeurIPS.

[17]  K. Crenshaw.  Demarginalizing the Intersection of Race and Sex: A Black Feminist Critique of Antidiscrimination Doctrine, Feminist Theory and Antiracist Politics , 1989 .

[18]  Alfred Inselberg,et al.  Parallel coordinates: a tool for visualizing multi-dimensional geometry , 1990, Proceedings of the First IEEE Conference on Visualization: Visualization `90.

[19]  Timnit Gebru,et al.  Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification , 2018, FAT.

[20]  Tanmoy Chakraborty,et al.  Nurse is Closer to Woman than Surgeon? Mitigating Gender-Biased Proximities in Word Embeddings , 2020, Transactions of the Association for Computational Linguistics.

[21]  Letitia Anne Peplau,et al.  An Intersectional Analysis of Gender and Ethnic Stereotypes , 2013 .

[22]  Ryan Cotterell,et al.  Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation , 2020, EMNLP.

[23]  Adam Tauman Kalai,et al.  Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings , 2016, NIPS.

[24]  Gerasimos Spanakis,et al.  Evaluating Bias In Dutch Word Embeddings , 2020, GEBNLP.

[25]  Jieyu Zhao,et al.  Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods , 2018, NAACL.

[26]  Amir Bakarov,et al.  A Survey of Word Embeddings Evaluation Methods , 2018, ArXiv.

[27]  David Rozado.  Wide range screening of algorithmic bias in word embedding models using large sentiment lexicons reveals underreported bias types , 2020, PloS one.

[28]  Martin Graham,et al.  Using curves to enhance parallel coordinate visualisations , 2003, Proceedings on Seventh International Conference on Information Visualization, 2003. IV 2003..

[29]  Mark Stevenson,et al.  Robustness and Reliability of Gender Bias Assessment in Word Embeddings: The Role of Base Pairs , 2020, AACL.

[30]  Carlos Ortiz,et al.  Intersectional Bias in Hate Speech and Abusive Language Datasets , 2020, ArXiv.

[31]  Daniel Jurafsky,et al.  Word embeddings quantify 100 years of gender and ethnic stereotypes , 2017, Proceedings of the National Academy of Sciences.

[32]  Jeff M. Phillips,et al.  Attenuating Bias in Word Vectors , 2019, AISTATS.

[33]  Martin Wattenberg,et al.  The What-If Tool: Interactive Probing of Machine Learning Models , 2019, IEEE Transactions on Visualization and Computer Graphics.

[34]  Luís C. Lamb,et al.  Assessing gender bias in machine translation: a case study with Google Translate , 2018, Neural Computing and Applications.

[35]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[36]  Martin Wattenberg,et al.  Embedding Projector: Interactive Visualization and Interpretation of Embeddings , 2016, ArXiv.

[37]  Vicente Ordonez,et al.  Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation , 2020, ACL.

[38]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[39]  K. Crenshaw.  Mapping the margins: intersectionality, identity politics, and violence against women of color , 1991 .

[40]  Minsuk Kahng,et al.  FAIRVIS: Visual Analytics for Discovering Intersectional Bias in Machine Learning , 2019, 2019 IEEE Conference on Visual Analytics Science and Technology (VAST).

[41]  Kristina Lerman,et al.  A Survey on Bias and Fairness in Machine Learning , 2019, ACM Comput. Surv..

[42]  Daniel A. Keim,et al.  Visual Analytics: Definition, Process, and Challenges , 2008, Information Visualization.

[43]  Adam Tauman Kalai,et al.  What are the Biases in My Word Embedding? , 2018, AIES.

[44]  Arvind Narayanan,et al.  Semantics derived automatically from language corpora contain human-like biases , 2016, Science.

[45]  Arun K. Pujari,et al.  Debiasing Gender biased Hindi Words with Word-embedding , 2019, Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence.