Towards Understanding Gender Bias in Relation Extraction

Gaut, Andrew W.; Sun, Tony; Tang, Shirlyn; Huang, Yuxin; Jiang, Qian; ElSherief, Mai; Zhao, Jieyu; Mirza, Diba; Belding, Elizabeth; Chang, Kai-Wei; Wang, William Yang

doi:10.48550/arxiv.1911.03642

Cited by 2 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As language technologies and NLP become more widely deployed in various aspects of society, there are concerns about the harms they cause to various demographic groups. The focus of our work was on toxic text classification, but prior work has also revealed bias issues along demographic dimensions like race, sexuality, and gender through identity terms for other NLP tasks including question answering [38], relation extraction [25], occupation prediction [16], autocomplete generation [57], and machine translation [60]. In this section, we provide design recommendations based on our findings.…”

Section: Design Recommendationsmentioning

confidence: 99%

“…Biased metrics or group fairness measures are used to show the differences between demographic groups produced by a model. These NLP tasks include question answering [38], relation extraction [25], text classification [16], autocomplete generation [57] and machine translation [60]. In these tasks, demographic dimensions are an identity axis on which they are evaluated for bias.…”

Section: Ai Fairness and Decision Makingmentioning

confidence: 99%

See 1 more Smart Citation

Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness

Ashktorab

Hoover²,

Agarwal³

et al. 2023

Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Mitigating algorithmic bias is a critical task in the development and deployment of machine learning models. While several toolkits exist to aid machine learning practitioners in addressing fairness issues, little is known about the strategies practitioners employ to evaluate model fairness and what factors influence their assessment, particularly in the context of text classification. Two common approaches of evaluating the fairness of a model are group fairness and individual fairness. We run a study with Machine Learning practitioners (n=24) to understand the strategies used to evaluate models. Metrics presented to practitioners (group vs. individual fairness) impact which models they consider fair. Participants focused on risks associated with underpredicting / overpredicting and model sensitivity relative to identity token manipulations. We discover fairness assessment strategies involving personal experiences or how users form groups of identity tokens to test model fairness. We provide recommendations for interactive tools for evaluating fairness in text classification. CCS CONCEPTS• Human-centered computing → Human computer interaction (HCI).

show abstract

Section: Design Recommendationsmentioning

confidence: 99%

Section: Ai Fairness and Decision Makingmentioning

confidence: 99%

Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness

Ashktorab

Hoover²,

Agarwal³

et al. 2023

Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…For example, of black female names [59]. Gender disparities can occur in neural relation extraction systems when extracting specific links between entities (occupation [32]). As a result, bias…”

Section: Bias Can Be Found In the Data Used To Construct Sw Technologiesmentioning

confidence: 99%

Semantic Web technologies and bias in artificial intelligence: A systematic literature review

Lobo

Daga

Alani

et al. 2023

View full text Add to dashboard Cite

Bias in Artificial Intelligence (AI) is a critical and timely issue due to its sociological, economic and legal impact, as decisions made by biased algorithms could lead to unfair treatment of specific individuals or groups. Multiple surveys have emerged to provide a multidisciplinary view of bias or to review bias in specific areas such as social sciences, business research, criminal justice, or data mining. Given the ability of Semantic Web (SW) technologies to support multiple AI systems, we review the extent to which semantics can be a “tool” to address bias in different algorithmic scenarios. We provide an in-depth categorisation and analysis of bias assessment, representation, and mitigation approaches that use SW technologies. We discuss their potential in dealing with issues such as representing disparities of specific demographics or reducing data drifts, sparsity, and missing values. We find research works on AI bias that apply semantics mainly in information retrieval, recommendation and natural language processing applications and argue through multiple use cases that semantics can help deal with technical, sociological, and psychological challenges.

show abstract

Towards Understanding Gender Bias in Relation Extraction

Cited by 2 publications

References 21 publications

Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness

Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness

Semantic Web technologies and bias in artificial intelligence: A systematic literature review

Contact Info

Product

Resources

About