2022

Re-contextualizing Fairness in NLP: The Case of India

Bhatt, Shaily, Dev, Sunipa, Talukdar, Partha et al.

Understand

Recent research has revealed undesirable biases in NLP data and models.

However, these efforts focus on social disparities in West, and are not directly portable to other geo-cultural contexts.
In this paper, we focus on NLP fair-ness in the context of India.
We start with a brief account of the prominent axes of social disparities in India.

Built on

Racial bias in hate speech and abusive language detection datasets
Original
Thomas Davidson, Debasmita Bhattacharya, and Ingmar Weber. 2019 · 1905
Earlier work this paper cites.
Mitigating gender bias in natural language processing: Literature review
Original
Tony Sun, Andrew Gaut, Shirlyn Tang, Yuxin Huang, Mai ElSherief, Jieyu Zhao, Diba Mirza, Elizabeth Belding, Kai-Wei Chang, and William Yang Wang. 2019 · 1906
Earlier work this paper cites.
Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter
Original
Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019 · 1910
Earlier work this paper cites.
Language and social class
Basil Bernstein. 1960 · 1960
Earlier work this paper cites.
Linguistic stereotypes and social distance
Ramdas Borude. 1966 · 1966
Earlier work this paper cites.
CrowS-pairs: A challenge dataset for measuring social biases in masked language models
Nikita Nangia, Clara Vania, Rasika Bhalerao, and Samuel R. Bowman. 2020 · 1967
Earlier work this paper cites.
Regional and communal stereotypes of bombay university students
Thomas A. de Souza. 1977 · 1977
Earlier work this paper cites.
Toward a theory of social dialect variation
Anthony S Kroch. 1978 · 1978
Earlier work this paper cites.
Sex-role stereotypes in northern india and the united states
Renuka R Sethi and Mary J Allen. 1984 · 1984
Earlier work this paper cites.
Gender advertising in the us and india: Exporting cultural stereotypes
Michael Griffin, K Viswanath, and Dona Schwartz. 1994 · 1994
Earlier work this paper cites.
Homosexuality: some reflections from india
Kuruvilla C Abraham and Ajit K Abraham. 1998 · 1998
Earlier work this paper cites.
Disabled women: An excluded agenda of indian feminism
Anita Ghai. 2002 · 2002
Earlier work this paper cites.
Western civilization, our tradition
James Kurth. 2003 · 2003
Earlier work this paper cites.
Rethinking the digital divide in relation to visual disability in india and the united states: towards a paradigm of information inequity
Vandana Chaudhry and Tom Shipp. 2005 · 2005
Earlier work this paper cites.
AI4Bharat-IndicNLP corpus: Monolingual corpora and word embeddings for Indic languages
Original
Anoop Kunchukuttan, Divyanshu Kakwani, Satish Golla, Avik Bhattacharyya, Mitesh M Khapra, Pratyush Kumar, et al. 2020 · 2005
Earlier work this paper cites.
The cross cultural study concerning gender stereotyping in computing: Comparison between the us and india
Kittipong; Mehta Nikhil; Leingpibul, Thaweephan; Laosethakul and Anju Mehta. 2006 · 2006
Earlier work this paper cites.
Cross-cultural analysis of gender roles: Indian and us advertisements
Durriya HZ Khairullah and Zahid Y Khairullah. 2009 · 2009
Earlier work this paper cites.
Gender role portrayals in indian television ads
Mallika Das. 2011 · 2011
Earlier work this paper cites.
The grammar of caste: Economic discrimination in contemporary India
Ashwini Deshpande. 2011 · 2011
Earlier work this paper cites.
Disability and rehabilitation services in india: Issues and challenges
S. Ganesh Kumar, Gautam Roy, and Sitanshu Sekhar Kar. 2012 · 2012
Earlier work this paper cites.
Northeast migrants in Delhi: Race, refuge and retail
Duncan McDuie-Ra. 2012 · 2012
Earlier work this paper cites.
Recursive deep models for semantic compositionality over a sentiment treebank
Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D Manning, Andrew Y Ng, and Christopher Potts. 2013 · 2013
Earlier work this paper cites.
Annihilation of Caste: The Annotated Critical Edition
BR Ambedkar. 2014 · 2014
Earlier work this paper cites.
Dalit women in india: At the crossroads of gender, class, and caste
Nidhi Sabharwal and Wandana Sonalkar. 2015 · 2015
Earlier work this paper cites.
Attitude towards homosexuality: A survey based study
Pooja V Anand. 2016 · 2016
Earlier work this paper cites.
Man is to computer programmer as woman is to homemaker? debiasing word embeddings
Original
Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, and Adam Kalai. 2016 · 2016
Earlier work this paper cites.

Similar

Interrogating Disability in India
Nandini Ghosh. 2016 · 2016
Cited alongside, same era.
Semantics derived automatically from language corpora contain human-like biases
Aylin Caliskan, Joanna J Bryson, and Arvind Narayanan. 2017 · 2017
Cited alongside, same era.
Disability, culture, and identity in india and usa
Christopher J Johnstone, Sandhya Limaye, and Misa Kayama. 2017 · 2017
Cited alongside, same era.
Men also like shopping: Reducing gender bias amplification using corpus-level constraints
Original
Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. 2017 · 2017
Cited alongside, same era.
Addressing age-related bias in sentiment analysis
Mark Diaz, Isaac Johnson, Amanda Lazar, Anne Marie Piper, and Darren Gergle. 2018 · 2018
Cited alongside, same era.
“untouchable” cellphones? old caste exclusions and new digital divides in peri-urban bangalore
Anant Kamath. 2018 · 2018
Cited alongside, same era.
Examining gender and race bias in two hundred sentiment analysis systems
Svetlana Kiritchenko and Saif Mohammad. 2018 · 2018
Cited alongside, same era.
Caste in the news: a computational analysis of indian newspapers
António Filipe Fonseca, Sohhom Bandyopadhyay, Jorge Louçã, and Jaison A Manjaly. 2019 · 2019
Cited alongside, same era.
Counterfactual fairness in text classification through robustness
Sahaj Garg, Vincent Perot, Nicole Limtiaco, Ankur Taly, Ed H Chi, and Alex Beutel. 2019 · 2019
Cited alongside, same era.
Rethinking disability in India
Anita Ghai. 2019 · 2019
Cited alongside, same era.
Does caste determine farmer access to quality information?
Vijesh V Krishna, Lagesh M Aravalath, and Surjit Vikraman. 2019 · 2019
Cited alongside, same era.
Black is to criminal as caucasian is to police: Detecting and removing multiclass bias in word embeddings
Thomas Manzini, Lim Yao Chong, Alan W Black, and Yulia Tsvetkov. 2019 · 2019
Cited alongside, same era.

Then

IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages
Divyanshu Kakwani, Anoop Kunchukuttan, Satish Golla, Gokul N.C., Avik Bhattacharyya, Mitesh M. Khapra, and Pratyush Kumar. 2020 · 2020
Later among the works it cites.
AraWEAT: Multidimensional analysis of biases in Arabic word embeddings
Anne Lauscher, Rafik Takieddin, Simone Paolo Ponzetto, and Goran Glavaš. 2020 · 2020
Later among the works it cites.
Human-centered approaches to fair and responsible ai
Min Kyung Lee, Nina Grgić-Hlača, Michael Carl Tschantz, Reuben Binns, Adrian Weller, Michelle Carney, and Kori Inkpen. 2020 · 2020
Later among the works it cites.
Stereoset: Measuring stereotypical bias in pretrained language models
Moin Nadeem, Anna Bethke, and Siva Reddy. 2020 · 2020
Later among the works it cites.
Participatory research for low-resourced machine translation: A case study in African languages
Wilhelmina Nekoto, Vukosi Marivate, Tshinondiwa Matsila, Timi Fasubaa, Taiwo Fagbohungbe, Solomon Oluwole Akinola, Shamsuddeen Muhammad, Salomon Kabongo Kabenamualu, Salomey Osei, Freshia Sackey, Rubungo Andre Niyongabo, Ricky Macharm, Perez Ogayo, Orevaoghene Ahia, Musie Meressa Berhe, Mofetoluwa Adeyemi, Masabata Mokgesi-Selinga, Lawrence Okegbemi, Laura Martinus, Kolawole Tajudeen, Kevin Degila, Kelechi Ogueji, Kathleen Siminyu, Julia Kreutzer, Jason Webster, Jamiil Toure Ali, Jade Abbott, Iroro Orife, Ignatius Ezeani, Idris Abdulkadir Dangana, Herman Kamper, Hady Elsahar, Goodness Duru, Ghollah Kioko, Murhabazi Espoir, Elan van Biljon, Daniel Whitenack, Christopher Onyefuluchi, Chris Chinenye Emezue, Bonaventure F. P. Dossou, Blessing Sibanda, Blessing Bassey, Ayodele Olabiyi, Arshath Ramkilowan, Alp Öktem, Adewale Akinfaderin, and Abdallah Bashir. 2020 · 2020
Later among the works it cites.
Can existing methods debias languages other than english? first attempt to analyze and mitigate japanese word embeddings
Masashi Takeshita, Yuki Katsumata, Rafal Rzepka, and Kenji Araki. 2020 · 2020
Later among the works it cites.
Section 377: Challenges and changing perspectives in the indian society
Nisha Tamang. 2020 · 2020
Later among the works it cites.
Measuring and reducing gendered correlations in pre-trained models
Kellie Webster, Xuezhi Wang, Ian Tenney, Alex Beutel, Emily Pitler, Ellie Pavlick, Jilin Chen, Ed Chi, and Slav Petrov. 2020 · 2020
Later among the works it cites.
Persistent anti-muslim bias in large language models
Abubakar Abid, Maheen Farooqi, and James Zou. 2021 · 2021
Later among the works it cites.
Measuring model biases in the absence of ground truth
Osman Aka, Ken Burke, Alex Bauerle, Christina Greer, and Margaret Mitchell. 2021 · 2021
Later among the works it cites.
On the dangers of stochastic parrots: Can language models be too big?
Emily M. Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell. 2021 · 2021
Later among the works it cites.
Learning to recognize dialect features
Dorottya Demszky, Devyani Sharma, Jonathan H Clark, Vinodkumar Prabhakaran, and Jacob Eisenstein. 2021 · 2021
Later among the works it cites.
Documenting large webtext corpora: A case study on the colossal clean crawled corpus
Jesse Dodge, Maarten Sap, Ana Marasović, William Agnew, Gabriel Ilharco, Dirk Groeneveld, Margaret Mitchell, and Matt Gardner. 2021 · 2021
Later among the works it cites.
Detecting cross-geographic biases in toxicity modeling on social media
Original
Sayan Ghosh, Dylan Baker, David Jurgens, and Vinodkumar Prabhakaran. 2021 · 2021
Later among the works it cites.
Evaluating gender bias in hindi-english machine translation
Gauri Gupta, Krithika Ramesh, and Sanjay Singh. 2021 · 2021
Later among the works it cites.
From ‘chinky’ to ‘coronavirus’: racism against northeast indians during the covid-19 pandemic
Thongkholal Haokip. 2021 · 2021
Later among the works it cites.
Muril: Multilingual representations for indian languages
Original
Simran Khanuja, Diksha Bansal, Sarvesh Mehtani, Savya Khosla, Atreyee Dey, Balaji Gopalan, Dilip Kumar Margam, Pooja Aggarwal, Rajiv Teja Nagipogu, Shachi Dave, et al. 2021 · 2021
Later among the works it cites.
Socially aware bias measurements for hindi language representations
Original
Vijit Malik, Sunipa Dev, Akihiro Nishi, Nanyun Peng, and Kai-Wei Chang. 2021 · 2021
Later among the works it cites.
On releasing annotator-level labels and information in datasets
Vinodkumar Prabhakaran, Aida Mostafazadeh Davani, and Mark Diaz. 2021 · 2021
Later among the works it cites.
Re-imagining algorithmic fairness in india and beyond
Nithya Sambasivan, Erin Arnesen, Ben Hutchinson, Tulsee Doshi, and Vinodkumar Prabhakaran. 2021 · 2021
Later among the works it cites.
Societal biases in language generation: Progress and challenges
Original
Emily Sheng, Kai-Wei Chang, Premkumar Natarajan, and Nanyun Peng. 2021 · 2021
Later among the works it cites.
Birds of a caste-how caste hierarchies manifest in retweet behavior of indian politicians
Palashi Vaghela, Ramaravind K Mothilal, and Joyojeet Pal. 2021 · 2021
Later among the works it cites.
Palm: Scaling language modeling with pathways
Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, Parker Schuh, Kensen Shi, Sasha Tsvyashchenko, Joshua Maynez, Abhishek Rao, Parker Barnes, Yi Tay, Noam Shazeer, Vinodkumar Prabhakaran, Emily Reif, Nan Du, Ben Hutchinson, Reiner Pope, James Bradbury, Jacob Austin, Michael Isard, Guy Gur-Ari, Pengcheng Yin, Toju Duke, Anselm Levskaya, Sanjay Ghemawat, Sunipa Dev, Henryk Michalewski, Xavier Garcia, Vedant Misra, Kevin Robinson, Liam Fedus, Denny Zhou, Daphne Ippolito, David Luan, Hyeontaek Lim, Barret Zoph, Alexander Spiridonov, Ryan Sepassi, David Dohan, Shivani Agrawal, Mark Omernick, Andrew M. Dai, Thanumalayan Sankaranarayana Pillai, Marie Pellat, Aitor Lewkowycz, Erica Moreira, Rewon Child, Oleksandr Polozov, Katherine Lee, Zongwei Zhou, Xuezhi Wang, Brennan Saeta, Mark Diaz, Orhan Firat, Michele Catasta, Jason Wei, Kathy Meier-Hellstern, Douglas Eck, Jeff Dean, Slav Petrov, and Noah Fiedel. 2022 · 2022
Closest in time.
Whose language counts as high quality? measuring language ideologies in text data selection
Original
Suchin Gururangan, Dallas Card, Sarah K Drier, Emily K Gade, Leroy Z Wang, Zeyu Wang, Luke Zettlemoyer, and Noah A Smith. 2022 · 2022
Closest in time.
Sex, laws and inequality : comparison between India and the U.S.A
Abhishek Kurian. 2020 · 2022
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…