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

• URL: http://arxiv.org/abs/2107.11584v1
• Date: Sat, 24 Jul 2021 11:22:10 GMT
• Title: Extending Challenge Sets to Uncover Gender Bias in Machine Translation: Impact of Stereotypical Verbs and Adjectives
• Authors: Jonas-Dario Troles, Ute Schmid
• Abstract summary: State-of-the-art machine translation (MT) systems are trained on large corpora of text, mostly generated by humans. Recent research showed that MT systems are biased towards stereotypical translation of occupations. In this paper we present an extension of this challenge set, called WiBeMT, with gender-biased adjectives and adds sentences with gender-biased verbs.
• Score: 0.45687771576879593
• License: http://creativecommons.org/licenses/by/4.0/
• 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. In this paper we present an extension of this challenge set, called WiBeMT, with gender-biased adjectives and adds 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.

Related papers

• Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words [85.48043537327258]
  Existing machine translation gender bias evaluations are primarily focused on male and female genders. This study presents a benchmark AmbGIMT (Gender-Inclusive Machine Translation with Ambiguous attitude words) We propose a novel process to evaluate gender bias based on the Emotional Attitude Score (EAS), which is used to quantify ambiguous attitude words.
  arXiv  Detail & Related papers  (2024-07-23T08:13:51Z)
• Building Bridges: A Dataset for Evaluating Gender-Fair Machine Translation into German [17.924716793621627]
  We study gender-fair language in English-to-German machine translation (MT) We conduct the first benchmark study involving two commercial systems and six neural MT models. Our findings show that most systems produce mainly masculine forms and rarely gender-neutral variants.
  arXiv  Detail & Related papers  (2024-06-10T09:39:19Z)
• Gender Inflected or Bias Inflicted: On Using Grammatical Gender Cues for Bias Evaluation in Machine Translation [0.0]
  We use Hindi as the source language and construct two sets of gender-specific sentences to evaluate different Hindi-English (HI-EN) NMT systems. Our work highlights the importance of considering the nature of language when designing such extrinsic bias evaluation datasets.
  arXiv  Detail & Related papers  (2023-11-07T07:09:59Z)
• Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation [64.79319733514266]
  Large Language Models (LLMs) can generate biased and toxic responses. We propose a conditional text generation mechanism without the need for predefined gender phrases and stereotypes.
  arXiv  Detail & Related papers  (2023-11-01T05:31:46Z)
• Will the Prince Get True Love's Kiss? On the Model Sensitivity to Gender Perturbation over Fairytale Texts [87.62403265382734]
  Recent studies show that traditional fairytales are rife with harmful gender biases. This work aims to assess learned biases of language models by evaluating their robustness against gender perturbations.
  arXiv  Detail & Related papers  (2023-10-16T22:25:09Z)
• VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution [80.57383975987676]
  VisoGender is a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas. We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes.
  arXiv  Detail & Related papers  (2023-06-21T17:59:51Z)
• Gender, names and other mysteries: Towards the ambiguous for gender-inclusive translation [7.322734499960981]
  This paper explores the case where the source sentence lacks explicit gender markers, but the target sentence contains them due to richer grammatical gender. We find that many name-gender co-occurrences in MT data are not resolvable with 'unambiguous gender' in the source language. We discuss potential steps toward gender-inclusive translation which accepts the ambiguity in both gender and translation.
  arXiv  Detail & Related papers  (2023-06-07T16:21:59Z)
• Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation [64.65911758042914]
  We investigate how seniority impacts the degree of gender bias exhibited in pretrained neural generation models. Our results show that GPT-2 amplifies bias by considering women as junior and men as senior more often than the ground truth in both domains. These results suggest that NLP applications built using GPT-2 may harm women in professional capacities.
  arXiv  Detail & Related papers  (2022-05-19T20:05:02Z)
• Gender Coreference and Bias Evaluation at WMT 2020 [16.814151914000856]
  Gender bias in machine translation can manifest when choosing gender inflections based on spurious gender correlations. Our work presents the largest evidence for the phenomenon in more than 19 systems submitted to the WMT. We find that all systems consistently use spurious correlations in the data rather than meaningful contextual information.
  arXiv  Detail & Related papers  (2020-10-12T20:42:21Z)
• Gender in Danger? Evaluating Speech Translation Technology on the MuST-SHE Corpus [20.766890957411132]
  Translating from languages without productive grammatical gender like English into gender-marked languages is a well-known difficulty for machines. Can audio provide additional information to reduce gender bias? We present the first thorough investigation of gender bias in speech translation, contributing with the release of a benchmark useful for future studies.
  arXiv  Detail & Related papers  (2020-06-10T09:55:38Z)
• Multi-Dimensional Gender Bias Classification [67.65551687580552]
  Machine learning models can inadvertently learn socially undesirable patterns when training on gender biased text. We propose a general framework that decomposes gender bias in text along several pragmatic and semantic dimensions. Using this fine-grained framework, we automatically annotate eight large scale datasets with gender information.
  arXiv  Detail & Related papers  (2020-05-01T21:23:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.