Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources

Warning: this paper contains content that may be offensive or upsetting. Commonsense knowledge bases (CSKB) are increasingly used for various natural language processing tasks. Since CSKBs are mostly human-generated and may reflect societal biases, it is important to ensure that such biases are not conflated with the notion of commonsense. Here we focus on two widely used CSKBs, ConceptNet and GenericsKB, and establish the presence of bias in the form of two types of representational harms, overgeneralization of polarized perceptions and representation disparity across different demographic groups in both CSKBs. Next, we find similar representational harms for downstream models that use ConceptNet. Finally, we propose a filtering-based approach for mitigating such harms, and observe that our filtered-based approach can reduce the issues in both resources and models but leads to a performance drop, leaving room for future work to build fairer and stronger commonsense models.

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

[2]  Bill Yuchen Lin,et al.  RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms , 2020, EMNLP.

[3]  Bill Yuchen Lin,et al.  CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning , 2020, FINDINGS.

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

[5]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[6]  Catherine Havasi,et al.  ConceptNet 5.5: An Open Multilingual Graph of General Knowledge , 2016, AAAI.

[7]  Dilek Z. Hakkani-Tür,et al.  Commonsense-Focused Dialogues for Response Generation: An Empirical Study , 2021, SIGDIAL.

[8]  Peter Clark,et al.  GenericsKB: A Knowledge Base of Generic Statements , 2020, ArXiv.

[9]  J. Pennebaker,et al.  The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods , 2010 .

[10]  Erik T. Mueller,et al.  Open Mind Common Sense: Knowledge Acquisition from the General Public , 2002, OTM.

[11]  Mai ElSherief,et al.  Mitigating Gender Bias in Natural Language Processing: Literature Review , 2019, ACL.

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

[13]  Marta R. Costa-jussà,et al.  Equalizing Gender Bias in Neural Machine Translation with Word Embeddings Techniques , 2019, Proceedings of the First Workshop on Gender Bias in Natural Language Processing.

[14]  Nanyun Peng,et al.  The Woman Worked as a Babysitter: On Biases in Language Generation , 2019, EMNLP.

[15]  Pedro A. Szekely,et al.  Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering , 2020, FINDINGS.

[16]  Debanjan Ghosh,et al.  R3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge , 2020, ACL.

[17]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[18]  Mark Chen,et al.  Language Models are Few-Shot Learners , 2020, NeurIPS.

[19]  Xiang Ren,et al.  KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning , 2019, EMNLP.

[20]  Nanyun Peng,et al.  Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition , 2019, HT.

[21]  Yejin Choi,et al.  ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning , 2019, AAAI.

[22]  Richard Socher,et al.  Explain Yourself! Leveraging Language Models for Commonsense Reasoning , 2019, ACL.

[23]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[24]  Xiang Li,et al.  Commonsense Knowledge Base Completion , 2016, ACL.

[25]  Ronan Le Bras,et al.  Unsupervised Commonsense Question Answering with Self-Talk , 2020, EMNLP.

[26]  Smaranda Muresan,et al.  Generating similes effortlessly like a Pro: A Style Transfer Approach for Simile Generation , 2020, EMNLP.

[27]  Joyce Yue Chai,et al.  Commonsense Reasoning for Natural Language Understanding: A Survey of Benchmarks, Resources, and Approaches , 2019, ArXiv.

[28]  Zeyu Li,et al.  Learning Gender-Neutral Word Embeddings , 2018, EMNLP.

[29]  Siva Reddy,et al.  StereoSet: Measuring stereotypical bias in pretrained language models , 2020, ACL.

[30]  Eric Gilbert,et al.  VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text , 2014, ICWSM.

[31]  Jonathan Berant,et al.  CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge , 2019, NAACL.

[32]  Xiaoyan Zhu,et al.  Commonsense Knowledge Aware Conversation Generation with Graph Attention , 2018, IJCAI.

[33]  Minlie Huang,et al.  A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation , 2020, TACL.

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

[35]  Alec Radford,et al.  Improving Language Understanding by Generative Pre-Training , 2018 .

[36]  Kai-Wei Chang,et al.  BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation , 2021, FAccT.

[37]  J. Fleiss.  Measuring nominal scale agreement among many raters. , 1971 .

[38]  Sebastian Riedel,et al.  Language Models as Knowledge Bases? , 2019, EMNLP.

[39]  Solon Barocas,et al.  Language (Technology) is Power: A Critical Survey of “Bias” in NLP , 2020, ACL.

[40]  Dimitris Bertsimas,et al.  The Price of Fairness , 2011, Oper. Res..

[41]  Dilek Z. Hakkani-Tür,et al.  Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks , 2020, DEELIO.

[42]  Nanyun Peng,et al.  Towards Controllable Biases in Language Generation , 2020, FINDINGS.

[43]  E. Miller.  Handbook of Social Psychology , 1946, Mental Health.

[44]  Maryam Najafian,et al.  A Transparent Framework for Evaluating Unintended Demographic Bias in Word Embeddings , 2019, ACL.

[45]  Yejin Choi,et al.  COMET: Commonsense Transformers for Knowledge Graph Construction , 2019 .

[46]  Michael S. Bernstein,et al.  Empath: Understanding Topic Signals in Large-Scale Text , 2016, CHI.

[47]  Daniel Khashabi,et al.  UNQOVERing Stereotypical Biases via Underspecified Questions , 2020, FINDINGS.