2021

Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources

Mehrabi, Ninareh, Zhou, Pei, Morstatter, Fred et al.

Understand

Warning: this paper contains content that may be offensive or upsetting.

Numerous natural language processing models have tried injecting commonsense by using the ConceptNet knowledge base to improve performance on different tasks.
ConceptNet, however, is mostly crowdsourced from humans and may reflect human biases such as "lawyers are dishonest." It is important that these biases are not conflated with the notion of commonsense.
We study this missing yet important problem by first defining and quantifying biases in ConceptNet as two types of representational harms: overgeneralization of polarized perceptions and representation disparity.

Built on

Language models are few-shot learners
Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020 · 1901
Earlier work this paper cites.
Commonsense reasoning for natural language understanding: A survey of benchmarks, resources, and approaches
Original
Shane Storks, Qiaozi Gao, and Joyce Y Chai. 2019 · 1904
Earlier work this paper cites.
The handbook of social psychology
Gardner Ed Lindzey and Elliot Ed Aronson. 1968 · 1968
Earlier work this paper cites.
Measuring nominal scale agreement among many raters
Joseph L Fleiss. 1971 · 1971
Earlier work this paper cites.
Wordnet: a lexical database for english
George A Miller. 1995 · 1995
Earlier work this paper cites.
Open mind common sense: Knowledge acquisition from the general public
Push Singh, Thomas Lin, Erik T Mueller, Grace Lim, Travell Perkins, and Wan Li Zhu. 2002 · 2002
Earlier work this paper cites.
Stereoset: Measuring stereotypical bias in pretrained language models
Original
Moin Nadeem, Anna Bethke, and Siva Reddy. 2020 · 2004
Earlier work this paper cites.
Genericskb: A knowledge base of generic statements
Original
Sumithra Bhakthavatsalam, Chloe Anastasiades, and Peter Clark. 2020 · 2005
Earlier work this paper cites.
The psychological meaning of words: Liwc and computerized text analysis methods
Yla R. Tausczik and James W. Pennebaker. 2010 · 2010
Earlier work this paper cites.
Vader: A parsimonious rule-based model for sentiment analysis of social media text
CHE Gilbert and Erric Hutto. 2014 · 2014
Earlier work this paper cites.
Man is to computer programmer as woman is to homemaker? debiasing word embeddings
Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016 · 2016
Earlier work this paper cites.
Empath: Understanding topic signals in large-scale text
Ethan Fast, Binbin Chen, and Michael S. Bernstein. 2016 · 2016
Earlier work this paper cites.
Commonsense knowledge base completion
Xiang Li, Aynaz Taheri, Lifu Tu, and Kevin Gimpel. 2016 · 2016
Earlier work this paper cites.
The problem with bias: Allocative versus representational harms in machine learning
Solon Barocas, Kate Crawford, Aaron Shapiro, and Hanna Wallach. 2017 · 2017
Earlier work this paper cites.

Similar

The trouble with bias
Kate Crawford. 2017 · 2017
Cited alongside, same era.
Conceptnet numberbatch 17.04: better, less-stereotyped word vectors
Robyn Speer. 2017 · 2017
Cited alongside, same era.
Conceptnet 5.5: an open multilingual graph of general knowledge
Robyn Speer, Joshua Chin, and Catherine Havasi. 2017 · 2017
Cited alongside, same era.
Improving language understanding by generative pre-training
Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018 · 2018
Cited alongside, same era.
Gender bias in coreference resolution: Evaluation and debiasing methods
Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. 2018a · 2018
Cited alongside, same era.
Learning gender-neutral word embeddings
Jieyu Zhao, Yichao Zhou, Zeyu Li, Wei Wang, and Kai-Wei Chang. 2018b · 2018
Cited alongside, same era.
Commonsense knowledge aware conversation generation with graph attention
Hao Zhou, Tom Young, Minlie Huang, Haizhou Zhao, Jingfang Xu, and Xiaoyan Zhu. 2018 · 2018
Cited alongside, same era.
Comet: Commonsense transformers for knowledge graph construction
Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, and Yejin Choi. 2019 · 2019
Cited alongside, same era.
Equalizing gender bias in neural machine translation with word embeddings techniques
Joel Escudé Font and Marta R Costa-jussà. 2019 · 2019
Cited alongside, same era.
KagNet: Knowledge-aware graph networks for commonsense reasoning
Bill Yuchen Lin, Xinyue Chen, Jamin Chen, and Xiang Ren. 2019 · 2019
Cited alongside, same era.
Language models are unsupervised multitask learners
Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019 · 2019
Cited alongside, same era.
Atomic: An atlas of machine commonsense for if-then reasoning
Maarten Sap, Ronan Le Bras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A Smith, and Yejin Choi. 2019 · 2019
Cited alongside, same era.

Then

A transparent framework for evaluating unintended demographic bias in word embeddings
Chris Sweeney and Maryam Najafian. 2019 · 2019
Later among the works it cites.
Examining gender bias in languages with grammatical gender
Pei Zhou, Weijia Shi, Jieyu Zhao, Kuan-Hao Huang, Muhao Chen, Ryan Cotterell, and Kai-Wei Chang. 2019 · 2019
Later among the works it cites.
Language (technology) is power: A critical survey of “bias” in NLP
Su Lin Blodgett, Solon Barocas, Hal Daumé III, and Hanna Wallach. 2020 · 2020
Later among the works it cites.
Rˆ3: Reverse, retrieve, and rank for sarcasm generation with commonsense knowledge
Tuhin Chakrabarty, Debanjan Ghosh, Smaranda Muresan, and Nanyun Peng. 2020 · 2020
Later among the works it cites.
Incorporating commonsense knowledge graph in pretrained models for social commonsense tasks
Ting-Yun Chang, Yang Liu, Karthik Gopalakrishnan, Behnam Hedayatnia, Pei Zhou, and Dilek Hakkani-Tur. 2020 · 2020
Later among the works it cites.
A knowledge-enhanced pretraining model for commonsense story generation
Jian Guan, Fei Huang, Zhihao Zhao, Xiaoyan Zhu, and Minlie Huang. 2020 · 2020
Later among the works it cites.
UnQovering stereotyping biases via underspecified questions
Tao Li, Tushar Khot, Daniel Khashabi, Ashish Sabharwal, and Vivek Srikumar. 2020 · 2020
Later among the works it cites.
Man is to person as woman is to location: Measuring gender bias in named entity recognition
Ninareh Mehrabi, Thamme Gowda, Fred Morstatter, Nanyun Peng, and Aram Galstyan. 2020 · 2020
Later among the works it cites.
Towards Controllable Biases in Language Generation
Emily Sheng, Kai-Wei Chang, Prem Natarajan, and Nanyun Peng. 2020 · 2020
Later among the works it cites.
Unsupervised commonsense question answering with self-talk
Vered Shwartz, Peter West, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. 2020 · 2020
Later among the works it cites.
Bold: Dataset and metrics for measuring biases in open-ended language generation
Jwala Dhamala, Tony Sun, Varun Kumar, Satyapriya Krishna, Yada Pruksachatkun, Kai-Wei Chang, and Rahul Gupta. 2021 · 2021
Closest in time.
A survey on bias and fairness in machine learning
Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2021 · 2021
Closest in time.
Commonsense-focused dialogues for response generation: An empirical study
Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia, Seokhwan Kim, Jay Pujara, Xiang Ren, Yang Liu, and Dilek Hakkani-Tur. 2021 · 2021
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…