Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies

@article{Dev2021HarmsOG,
  title={Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies},
  author={Sunipa Dev and Masoud Monajatipoor and Anaelia Ovalle and Arjun Subramonian and J. M. Phillips and Kai Wei Chang},
  journal={ArXiv},
  year={2021},
  volume={abs/2108.12084}
}
Gender is widely discussed in the context of language tasks and when examining the stereotypes propagated by language models. However, current discussions primarily treat gender as binary, which can perpetuate harms such as the cyclical erasure of non-binary gender identities. These harms are driven by model and dataset biases, which are consequences of the non-recognition and lack of understanding of non-binary genders in society. In this paper, we explain the complexity of gender and language… 

Theories of “Gender” in NLP Bias Research

The rise of concern around Natural Language Processing (NLP) technologies containing and perpetuating social biases has led to a rich and rapidly growing area of research. Gender bias is one of the

Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender

Trigger warning: This paper contains some examples which might be offensive to some users. The worls of pronouns is changing. From a closed class of words with few members to a much more open set of

Revisiting Queer Minorities in Lexicons

Lexicons play an important role in content moderation often being the first line of defense. However, little or no literature exists in analyzing the representation of queer-related words in them. In

Socially Aware Bias Measurements for Hindi Language Representations

This work investigates the biases present in Hindi language representations such as caste and religion associated biases and demonstrates how biases are unique to specific language representations based on the history and culture of the region they are widely spoken in.

HeteroCorpus: A Corpus for Heteronormative Language Detection

This work proposes and evaluates HeteroCorpus; a corpus created specifically for studying heterononormative language in English, and proposes a baseline set of classification experiments on the corpus, in order to show the performance of the corpus in classification tasks.

You reap what you sow: On the Challenges of Bias Evaluation Under Multilingual Settings

Three dimensions of developing multilingual bias evaluation frameworks are highlighted: increasing transparency through documentation, expanding targets of bias beyond gender, and addressing cultural differences that exist between languages.

Choose Your Lenses: Flaws in Gender Bias Evaluation

Considerable efforts to measure and mitigate gender bias in recent years have led to the introduction of an abundance of tasks, datasets, and metrics used in this vein. In this position paper, we

Handling Bias in Toxic Speech Detection: A Survey

The massive growth of social media usage has witnessed a tsunami of online toxicity in teams of hate speech, abusive posts, cyberbullying, etc. Detecting online toxicity is challenging due to its

Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics

Word embeddings are numeric representations of meaning derived from word co-occurrence statistics in corpora of human-produced texts. The statistical regularities in language corpora encode

How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral Pronouns

Gender-neutral pronouns have recently been introduced in many languages to a) include non-binary people and b) as a generic singular. Recent results from psycholinguistics suggest that gender-neutral

References

SHOWING 1-10 OF 45 REFERENCES

Shirtless and Dangerous: Quantifying Linguistic Signals of Gender Bias in an Online Fiction Writing Community

A technique that combines natural language processing with a crowdsourced lexicon of stereotypes to capture gender biases in fiction finds that male over-representation and traditional gender stereotypes are common throughout nearly every genre in the corpus.

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

It is confirmed that without acknowledging and building systems that recognize the complexity of gender, systems that fail for: quality of service, stereotyping, and over- or under-representation, especially for binary and non-binary trans users.

Revisiting Gendered Web Forms: An Evaluation of Gender Inputs with (Non-)Binary People

This work aims to sensitize designers of (online) gender web forms to the needs and desires of non-binary people and design considerations for improving gender input forms and consequently their underlying gender model in databases.

Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting

A large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives, and the impact on occupation classification of including explicit gender indicators in different semantic representations of online biographies.

Patching Gender: Non-binary Utopias in HCI

It is illustrated the casual violence technologies present to non-binary people, as well as the on-going marginalisations the authors experience as HCI researchers.

For lack of a better word: neo-identities in non-cisgender, non-straight communities on Tumblr

Non-cisgender and non-straight identity language has long been a site of contention and evolution. There has been an increase in new non-cisgender, non-straight identity words since the creation of

Toward Gender-Inclusive Coreference Resolution

Through these studies, conducted on English text, it is confirmed that without acknowledging and building systems that recognize the complexity of gender, the authors build systems that lead to many potential harms.

Demarginalizing the Intersection of Race and Sex: A Black Feminist Critique of Antidiscrimination Doctrine, Feminist Theory and Antiracist Politics

One of the very few Black women's studies books is entitled All the Women Are White; All the Blacks Are Men, But Some of Us are Brave.1 I have chosen this title as a point of departure in my efforts

Whipping Girl: A Transsexual Woman on Sexism and the Scapegoating of Femininity

A provocative manifesto, Whipping Girl tells the powerful story of Julia Serano, a transsexual woman whose supremely intelligent writing reflects her diverse background as a lesbian transgender

Societal Biases in Language Generation: Progress and Challenges

A survey on societal biases in language generation is presented, focusing on how data and techniques contribute to biases and progress towards reducing biases, and the effects of decoding techniques.