Syntactic and cognitive issues in investigating gendered coreference

By Lauren Ackerman. 2019

82 citations recorded by the source corpus.

This paper presents a framework for how the multifaceted nature of "gender" (human and linguistic) interacts with grammatical operations such as coreference dependency formation. It frames the question through the lens of English, in which it focuses on how personal names and referents who identify as nonbinary can provide insight into the conceptual representations of gender. Additional data from a variety of modern languages supports a model of how gender might be cognitively represented such that the observed linguistic patterns are available. A three-tiered model of gender is proposed that unites grammatical, cognitive, social, and biological aspects and describes how implications of this model might be tested in future work.

Subfields: Gender Studies, Language and Linguistics, 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 Gender Studies

In Language and Linguistics

In Natural Language Processing

Citations in the corpus

Toward Gender-Inclusive Coreference Resolution (2019, methodology): “Finally, Ackerman (2019) presents an alternative breakdown of gender than we use (§ 3), and proposes matching criteria for model-”
Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem (2020, neutral): “However, the target languages supported by WinoMT lack widely-accepted non-binary inflection conventions (Ackerman, 2019).”
Investigating Failures of Automatic Translation in the Case of Unambiguous Gender (2021, background): “Our gendered trigger words are largely “unambiguous” modulo costume party examples (Ackerman, 2019), where people dress up contra their gender identity: if a man dresses up as his own grandmother, he can be referred to with so-called “unambiguous” triggers such as grandma or she.”
Detecting Independent Pronoun Bias with Partially-Synthetic Data Generation (2020, background): “Our linguistic understanding of (neo)pronouns and inclusive NLP development are areas of ongoing research (Ackerman, 2019; Bradley et al., 2019; Cao and Daumé III, 2020; Conrod, 2020; Denton et al., 2020; Mitchell et al., 2020).”
Gender and Representation Bias in GPT-3 Generated Stories (2021, background): “Thus, we infer conceptual gender, or gender used by a perceiver, which may differ from the gender experienced internally by an individual being perceived (Ackerman, 2019).”
Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle* (2021, methodology): “Ackerman (2019) analyzes how human cognitively encode gender in resolving coreferences through a Broad Matching Criterion, which posits “matching gender requires at least one level of the mental representation of gender [e.g. the occupation of the person or the environment context, etc.] to be…”
Perturbation Augmentation for Fairer NLP (2022, background): “We grouped the two together because many non-binary examples are ambiguous in referring to either (i) an individual who is known to be non-binary, or (ii) an individual whose gender is not specified, or (iii) a plurality of entities (Ackerman, 2019).”
Theories of “Gender” in NLP Bias Research (2022, background): “[1] Gavin Abercrombie, Amanda Cercas Curry, Mugdha Pandya, and Verena Rieser.”
A Survey on Gender Bias in Natural Language Processing (2021, background): “Definitions of gender used in the linguistics literature vary substantially across subfields and are often implicit [Ackerman 2019]. Depending on the context, the concept of gender refers to a person’s self-determined identity and the way they express it, how they are perceived, and others’ social e”
The practical ethics of bias reduction in machine translation: why domain adaptation is better than data debiasing (2021, background): “…as the IEEE’s Ethically Aligned Design (2016-present) (IEEE 2020), publications such as the European Union’s Ethical Guidelines for Trustworthy AI (2019; from hence-forth ‘ Guidelines ’; HLEGAI 2019), and the self-imposed ‘Principles’ adopted by most leading technology companies to govern their…”