CoChat

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

Open access
Cao, Yang Trista, Daumé, Hal · 2021 · Computational Linguistics

The DOI matches its Crossref record; 329 of the 329 references it cites were found in a registry or an index.

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.

Overview

Integrity signals

Registry

Crossref · 10.1162/coli_a_00413

Cites

329 of 329 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Items 201–329 of 329

Research works printed but not linked: 18

  1. Andrews, 2017, The singular, gender-neutral ‘they’ added to the Associated Press Stylebook
  2. Bagga, 1998, Algorithms for scoring coreference chains, 563
  3. Barocas, 2017, The problem with bias: Allocative versus representational harms in machine learning
  4. Bender, 2019, A typology of ethical risks in language technology with an eye towards where transparent documentation can help, The Future of Artificial Intelligence: Language, Ethics, Technology
  5. Blodgett, 2020, Language (technology) is power: The need to be explicit about NLP harms
  6. Burton, 1883, Kama Sutra, Translation
  7. Conrod, 2018, Changes in singular they
  8. Conrod, 2018, What does it mean to agree? Coreference with singular they
  9. Corbett, 2013, Number of genders
  10. Craig, 1994, Classifier languages, The Encyclopedia of Language and Linguistics, 2, 565
  11. Dryer, 2013, Expression of pronominal subjects
  12. HaNasi, 189, Mishnah bikkurim
  13. Mitchell, 2005, Ace 2004 multilingual training corpus, Linguistic Data Consortium, Philadelphia, 1, 1
  14. Ochs, 1992, Indexing gender, Rethinking Context: Language as an Interactive Phenomenon, 11, 335
  15. Orita, 2015, Why discourse affects speakers’ choice of referring expressions, 10.3115/v1/P15-1158 · DOI
  16. Silverstein, 1979, Language structure and linguistic ideology, The Elements: A Parasession on Linguistic Units and Levels, 193
  17. Stryker, 2008, Transgender History
  18. Weischedel, 2011, OntoNotes: A Large Training Corpus for Enhanced Processing

Cited by

See all 47

Metadata

Authors
Cao, Y. T., & Daumé, H.
Affiliations
  • University of Maryland, College Park (US)
  • Microsoft Research, University of Maryland. me@hal3.name
Corresponding author
  • Cao, Yang Trista
  • Daumé, Hal
Venue
Computational Linguistics
Published
2021-11
Volume
47
Issue
3
Pages
615-661
ISSN
  • 0891-2017 (ISSN-L)
  • 1530-9312
OpenAlex
W3178522238
Cited by
47
References
319
Citations by year
2026: 3 · 2025: 10 · 2024: 7 · 2023: 14 · 2022: 12 · 2021: 1
FWCI
10.64
Type
journal article
Language
en
Open access
Locations
  • Computational Linguistics (publishedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Social Sciences › Gender Studies › Gender Studies in Language
Keywords
coreference resolution, gender bias, trans and non-binary people, stereotyping, machine learning pipelines

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.