Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Queer NLP: A Critical Survey on Literature Gaps, Biases and Trends

Sabine Weber, Angelina Wang, Ankush Gupta, Arjun Subramonian, Dennis Ulmer, Eshaan Tanwar, Geetanjali Aich, Hannah Devinney, Jacob Hobbs, Jennifer Mickel, Joshua Tint, Mae Sosto, Ray Groshan, Simone Astarita, Vagrant Gautam, Verena Blaschke, William Agnew, Wilson Y Lee, Yanan Long

TL;DR

This survey examines NLP research papers that explicitly address the relationship between LGBTQIA+ communities and NLP technologies, and offers an outlook from a queer studies perspective, highlighting understudied topics and gaps in the harms addressed in NLP papers.

Abstract

Natural language processing (NLP) technologies are rapidly reshaping how language is created, processed, and analyzed by humans. With current and potential applications in hiring, law, healthcare, and other areas that impact people's lives, understanding and mitigating harms towards marginalized groups is critical. In this survey, we examine NLP research papers that explicitly address the relationship between LGBTQIA+ communities and NLP technologies. We systematically review all such papers published in the ACL Anthology, to answer the following research questions: (1) What are current research trends? (2) What gaps exist in terms of topics and methods? (3) What areas are open for future work? We find that while the number of papers on queer NLP has grown within the last few years, most papers take a reactive rather than a proactive approach, pointing out bias more often than mitigating it, and focusing on shortcomings of existing systems rather than creating new solutions. Our survey uncovers many opportunities for future work, especially regarding stakeholder involvement, intersectionality, interdisciplinarity, and languages other than English. We also offer an outlook from a queer studies perspective, highlighting understudied topics and gaps in the harms addressed in NLP papers. Beyond being a roadmap of what has been done, this survey is a call to action for work towards more just and inclusive NLP technologies.

Queer NLP: A Critical Survey on Literature Gaps, Biases and Trends

TL;DR

This survey examines NLP research papers that explicitly address the relationship between LGBTQIA+ communities and NLP technologies, and offers an outlook from a queer studies perspective, highlighting understudied topics and gaps in the harms addressed in NLP papers.

Abstract

Natural language processing (NLP) technologies are rapidly reshaping how language is created, processed, and analyzed by humans. With current and potential applications in hiring, law, healthcare, and other areas that impact people's lives, understanding and mitigating harms towards marginalized groups is critical. In this survey, we examine NLP research papers that explicitly address the relationship between LGBTQIA+ communities and NLP technologies. We systematically review all such papers published in the ACL Anthology, to answer the following research questions: (1) What are current research trends? (2) What gaps exist in terms of topics and methods? (3) What areas are open for future work? We find that while the number of papers on queer NLP has grown within the last few years, most papers take a reactive rather than a proactive approach, pointing out bias more often than mitigating it, and focusing on shortcomings of existing systems rather than creating new solutions. Our survey uncovers many opportunities for future work, especially regarding stakeholder involvement, intersectionality, interdisciplinarity, and languages other than English. We also offer an outlook from a queer studies perspective, highlighting understudied topics and gaps in the harms addressed in NLP papers. Beyond being a roadmap of what has been done, this survey is a call to action for work towards more just and inclusive NLP technologies.
Paper Structure (51 sections, 3 figures, 1 table)

This paper contains 51 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Paper Selection
  5. Annotation Process
  6. Survey Findings
  7. Language Models: Evaluation
  8. Template-based methods.
  9. Intrinsic and extrinsic measures.
  10. Language Models: Bias Mitigation
  11. Text Classification
  12. Oversensitivity towards queer language.
  13. Biased datasets.
  14. Non-English hate speech detection.
  15. Information Extraction and Access
  16. ...and 36 more sections

Figures (3)

  • Figure 1: The majority of queer NLP papers published in the ACL Anthology are focused on English, disregard intersectionality and omit stakeholders.
  • Figure 2: Percent breakdown of the 35 languages represented across papers. The 'Other' category aggregates all 20 languages that appeared in only one paper. The total percent is over 100% due to papers on multiple languages. See Appendix \ref{['languages']} for a full list of languages along with paper counts.
  • Figure 3: Comparing paper categories by (a) intersectionality, (b) language diversity, and (c) stakeholder inclusion.