Zum Inhalt springen

Nur-Lesen-Fassung: Das Forschungsinformationssystem (FIS) ist aus Sicherheitsgründen vorübergehend durch diese Nur-Lesen-Fassung ersetzt. Alle öffentlichen Inhalte und Volltexte sind weiterhin abrufbar; Anmeldung, Bearbeitung, Einreichung und Statistiken stehen nicht zur Verfügung. Bei Fragen: fis@uni-bamberg.de

Start › Publikationen › Extending Challenge Sets to Uncover Gender Bias in Machine Translation : Impact of Stereotypical Verbs and Adjectives

Publikation

Extending Challenge Sets to Uncover Gender Bias in Machine Translation : Impact of Stereotypical Verbs and Adjectives

Troles, Jonas-Dario; Schmid, Ute (2021): Extending Challenge Sets to Uncover Gender Bias in Machine Translation : Impact of Stereotypical Verbs and Adjectives, in: Loic Barrault (Hrsg.), Sixth Conference on Machine Translation : proceedings of the conference, Stroudsburg, PA: Association for Computational Linguistics (ACL), S. 531–541.

Details

Fakultät/Lehrstuhl
Autorin(nen)/Autor(en)
Troles, Jonas-Dario
Titel des Sammelwerks
Sixth Conference on Machine Translation : proceedings of the conference
Herausgeberin(nen)/Herausgeber des Sammelwerks
Barrault, Loic
Herausgebende Institution
Association for Computational Linguistics (ACL)
Konferenz
Sixth Conference on Machine Translation, November 10-11, 2021, Punta Cana
Verlagsangabe
Association for Computational Linguistics (ACL) : Stroudsburg, PA
Erscheinungsjahr
2021
ISBN
978-1-954085-94-7
Sprache(n)
Englisch
URL
Abstract

Human gender bias is reflected in language and text production. Because state-of-the-art machine translation (MT) systems are trained on large corpora of text, mostly generated by humans, gender bias can also be found in MT. For instance when occupations are translated from a language like English, which mostly uses gender neutral words, to a language like German, which mostly uses a feminine and a masculine version for an occupation, a decision must be made by the MT System. Recent research showed that MT systems are biased towards stereotypical translation of occupations. In 2019 the first, and so far only, challenge set, explicitly designed to measure the extent of gender bias in MT systems has been published. In this set measurement of gender bias is solely based on the translation of occupations. With our paper we present an extension of this challenge set, called WiBeMT, which adds gender-biased adjectives and sentences with gender-biased verbs. The resulting challenge set consists of over 70, 000 sentences and has been translated with three commercial MT systems: DeepL Translator, Microsoft Translator, and Google Translate. Results show a gender bias for all three MT systems. This gender bias is to a great extent significantly influenced by adjectives and to a lesser extent by verbs.

GND-Schlagwort(e)
Computerunterstützte Übersetzung
Geschlechterrolle
Bias
Freie Schlagwort(e)
Gender Bias
Machine Translation
Challenge Set
DDC-Klassifikation
004 Computer science
300 Sozialwissenschaften, Soziologie, Anthropologie
RVK-Klassifikation
ST 350
Peer Reviewed
ja
Internationale Verbreitung
ja
Open-Access-Zeitschrift
ja
Dokumenttyp
Konferenzveröffentlichung
URI
Datum der Freischaltung
12.12.2022

Permalink: https://fis.uni-bamberg.de/handle/uniba/57197 · Daten als JSON · Zitieren: BibTeX · RIS

Datenstand: 15.11.2026

Eingeschränkter Lesezugriff: Anmeldung, Bearbeitung und Einreichung sind vorübergehend deaktiviert.