Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle*

By Yang Trista Cao, Hal Daumé Iii. 2021

63 citations recorded by the source corpus.

Abstract Correctly resolving textual mentions of people fundamentally entails making inferences about those people. Such inferences raise the risk of systematic biases in coreference resolution systems, including biases that can harm binary and non-binary trans and cis stakeholders. To better understand such biases, we foreground nuanced conceptualizations of gender from sociology and sociolinguistics, and investigate where in the machine learning pipeline such biases can enter a coreference resolution system. We inspect many existing data sets for trans-exclusionary biases, and develop two new data sets for interrogating bias in both crowd annotations and in existing coreference resolution systems. Through these studies, conducted on English text, we confirm that without acknowledging and building systems that recognize the complexity of gender, we will build systems that fail for: quality of service, stereotyping, and over- or under-representation, especially for binary and non-binary trans users.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Data Governance in the Age of Large-Scale Data-Driven Language Technology (2022, background): “Unsurprisingly, gendered and racial disparities have been documented in a number of language technologies [37, 79, 141], and processes of creating resources and technologies may further entrench such disparities [25, 38, 144].”
Large Language Model Alignment: A Survey (2023, background): “GICOREF (Cao and III, 2021) focuses on the model’s performance on texts related to non-binary and binary transgender individuals.”
“I’m fully who I am”: Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation (2023, background): “They may be unable to consistently recall them to a subject in text [14].”