ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages [PDF]
International Computing Education Research Workshop, 2023 In this multicultural age, language translation is one of the most performed tasks, and it is becoming increasingly AI-moderated and automated. As a novel AI system, ChatGPT claims to be proficient in machine translation tasks and in this paper, we put ...
Sourojit Ghosh, Aylin Caliskan
semanticscholar +1 more source
MISGENDERED: Limits of Large Language Models in Understanding Pronouns [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Content Warning: This paper contains examples of misgendering and erasure that could be offensive and potentially triggering.Gender bias in language technologies has been widely studied, but research has mostly been restricted to a binary paradigm of ...
Tamanna Hossain +2 more
semanticscholar +1 more source
How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral Pronouns [PDF]
North American Chapter of the Association for Computational Linguistics, 2022 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 pronouns (in Swedish) are not associated with human ...
Stephanie Brandl +2 more
semanticscholar +1 more source
My pronouns are they/them: Talking about pronouns changes how pronouns are understood
Psychonomic Bulletin & Review, 2021 The pronoun “they” can be either plural or singular, perhaps referring to an individual who identifies as nonbinary. How do listeners identify whether “they” has a singular or plural sense?
Jennifer E. Arnold +2 more
semanticscholar +1 more source
Complexity/informativeness trade-off in the domain of indefinite pronouns
Annual Meeting of the Cognitive Science Society, 2021 The vocabulary of human languages has been argued to support efficient communication by optimizing the trade-off between complexity and informativeness (Kemp & Regier 2012).
M. Denic +2 more
semanticscholar +1 more source
On Measuring Gender Bias in Translation of Gender-neutral Pronouns [PDF]
Proceedings of the First Workshop on Gender Bias in Natural Language Processing, 2019 Ethics regarding social bias has recently thrown striking issues in natural language processing. Especially for gender-related topics, the need for a system that reduces the model bias has grown in areas such as image captioning, content recommendation ...
Won Ik Cho +3 more
semanticscholar +1 more source
Resolving Gendered Ambiguous Pronouns with BERT [PDF]
Proceedings of the First Workshop on Gender Bias in Natural Language Processing, 2019 Pronoun resolution is part of coreference resolution, the task of pairing an expression to its referring entity. This is an important task for natural language understanding and a necessary component of machine translation systems, chat bots and ...
Kellie Webster +3 more
semanticscholar +1 more source
Are New Gender-Neutral Pronouns Difficult to Process in Reading? The Case of Hen in SWEDISH
Frontiers in Psychology, 2020 Hen is a Swedish gender-neutral pronoun used for non-binary individuals and as a generic singular pronoun form. Hen was added to the Swedish Academy Glossary (SAOL) in 2015, and opponents of hen have argued that gender-neutral pronouns are difficult to ...
H. Vergoossen +3 more
semanticscholar +1 more source
Vous or tu? Native and non-native speakers of French on a sociolinguistic tightrope [PDF]
, 2004 Sociolinguistic rules governing choice of pronouns of address are notoriously difficult in French, despite the fact that the number of variants is rather limited: the more formal vous versus the more informal tu.
Dewaele, Jean-Marc
core +1 more source
Reflexive pronouns in Spanish Universal Dependencies [PDF]
, 2020 In this paper, we argue that in current Universal Dependencies treebanks, the annotation of Spanish reflexives is an unsolved problem, which clearly affects the accuracy and consistency of current parsers.
Degraeuwe, Jasper, Goethals, Patrick
core +3 more sources