Toward Gender-Inclusive Coreference Resolution

By Yang Trista Cao, Hal Daumé Iii. 2019

158 citations recorded by the source corpus.

Correctly resolving textual mentions of people fundamentally entails making inferences about those people. Such inferences raise the risk of systemic 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 develop two new datasets for interrogating bias in 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 build systems that lead to many potential harms.

Subfields: Artificial Intelligence, Natural Language Processing

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

In Natural Language Processing

Citations in the corpus

Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies (2021, neutral): “However, people are conditioned to erroneously believe otherwise, which leads to “societal expectations and stereotypes around gender roles” and the compulsive (mis)gendering of others (Cao and Daumé III, 2020; Serano, 2007).”
Datasheets for datasets (2018, neutral): “Academic researchers have adopted our proposal and released datasets with accompanying datasheets [e.g., 7, 10, 23, 26].”
Queens Are Powerful Too: Mitigating Gender Bias in Dialogue Generation (2019, background): “…focused on exploring gender bias in NLP systems (Sun et al., 2019), uncovering many gender disparities and harmful biases in algorithms and text (Cao and Daum´e III 2020; Chang et al. 2019; Chang and McKeown 2019; Costa-juss ` a 2019; Du et al. 2019; Emami et al. 2019; Garimella et al. 2019;…”
Taxonomy of Risks posed by Language Models (2022, background): “1[33] examines how current literature and models for coreference resolution are designed with binary gender terms, forcing, for example, the resolution of names such as “Max” into either “he” or “she”, not allowing for the resolution into “they” and thereby excluding those who might prefer alternati”
Investigating Gender Bias in Language Models Using Causal Mediation Analysis (2020, methodology): “Neural networks learn to replicate historical, societal biases from training data in various tasks such as natural language inference (Rudinger et al., 2017), coreference resolution (Cao and Daumé III, 2019), and sentiment analysis (Kiritchenko and Mohammad, 2018).”
On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning (2022, background): “Beyond stereotypes, model biases also manifest in a wide range of downstream tasks, like question-answering (QA) (Parrish et al., 2022), toxicity detection (Davidson et al., 2019) and coreference resolution (Zhao et al., 2018; Rudinger et al., 2018; Cao and Daumé III, 2020).”
Theories of “Gender” in NLP Bias Research (2022, background): “aal4230 [7] Yang Trista Cao and Hal Daumé III.”
Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics (2021, background): “…group or for each split of a challenge dataset (Hovy and Søgaard, 2015; Rudinger et al., 2018; Zhao et al., 2018; Garimella et al., 2019; Sap et al., 2019; Bagdasaryan et al., 2019; Stafanoviˇcs et al., 2020; Tan et al., 2020; Mehrabi et al., 2020; Nadeem et al., 2020; Cao and Daumé III, 2020).”
On Measures of Biases and Harms in NLP (2021, methodology): “…entailment (Dev et al., 2019), toxicity prediction (Dixon et al., 2018; Jigsaw, 2019; Sap et al., 2020), coreference resolution (Zhao et al., 2019; Cao and Daumé III, 2020), autocomplete generation (Sheng et al., 2019), dialogue generation (Dinan et al., 2019), machine translation (Stanovsky et…”