Corpus ID: 222310217

Mitigating Gender Bias in Machine Translation with Target Gender Annotations

@inproceedings{Bergmanis2020MitigatingGB,
  title={Mitigating Gender Bias in Machine Translation with Target Gender Annotations},
  author={Toms Bergmanis and Arturs Stafanovivcs and Marcis Pinnis},
  booktitle={WMT},
  year={2020}
}
When translating The secretary asked for details. to a language with grammatical gender, it might be necessary to determine the gender of the subject secretary. If the sentence does not contain the necessary information, it is not always possible to disambiguate. In such cases, machine translation systems select the most common translation option, which often corresponds to the stereotypical translations, thus potentially exacerbating prejudice and marginalisation of certain groups and people… Expand

Figures and Tables from this paper

The Arabic Parallel Gender Corpus 2.0: Extensions and Analyses
TLDR
A new corpus for gender identification and rewriting in contexts involving one or two target users (I and/or You) – first and second grammatical persons with independent grammatical gender preferences in Arabic, a gender-marking morphologically rich language. Expand
How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation
TLDR
This work considers a model that systematically and disproportionately favours masculine over feminine forms to be biased, as it fails to properly recognize women, and proposes a combined approach that preserves BPE overall translation quality, while leveraging the higher ability of character-based segmentation to properly translate gender. Expand
First the worst: Finding better gender translations during beam search
TLDR
This work focuses on gender bias resulting from systematic errors in grammatical gender translation, which can lead to human referents being misrepresented or misgendered, and experiments with reranking nbest lists using gender features obtained automatically from the source sentence, and applying gender constraints while decoding to improve nbest list gender diversity. Expand
Gender-Aware Reinflection using Linguistically Enhanced Neural Models
In this paper, we present an approach for sentence-level gender reinflection using linguistically enhanced sequence-to-sequence models. Our system takes an Arabic sentence and a given target genderExpand
Contrastive Conditioning for Assessing Disambiguation in MT: A Case Study of Distilled Bias
Lexical disambiguation is a major challenge for machine translation systems, especially if some senses of a word are trained less often than others. Identifying patterns of overgeneralizationExpand
Gender Bias in Machine Translation
TLDR
This work critically review current conceptualizations of bias in machine translation technology in light of theoretical insights from related disciplines and point toward potential directions for future work. Expand
Faithful Target Attribute Prediction in Neural Machine Translation
TLDR
It is argued that predicting the target word and attributes simultaneously is an effective way to ensure that translations are more faithful to the training data distribution with respect to these attributes. Expand
Examining Covert Gender Bias: A Case Study in Turkish and English Machine Translation Models
TLDR
This work introduces a method to investigate asymmetrical gender markings in machine translation models and demonstrates the continued need for language-specific, interdisciplinary methodology in MT model development. Expand
Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation
TLDR
It is observed that gendered noun translation performance degrades at a much faster rate when neural machine translation models are optimized for speed and evaluated on generic test sets using BLEU. Expand
Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics
TLDR
This work unify a broad range of existing metrics under three generalized fairness metrics and demonstrates that the observed differences in bias measurement can be systematically explained via differences in parameter choices for the authors' generalized metrics. Expand
...
1
2
...

References

SHOWING 1-10 OF 49 REFERENCES
Evaluating Gender Bias in Machine Translation
TLDR
An automatic gender bias evaluation method for eight target languages with grammatical gender, based on morphological analysis is devised, which shows that four popular industrial MT systems and two recent state-of-the-art academic MT models are significantly prone to gender-biased translation errors for all tested target languages. Expand
Filling Gender & Number Gaps in Neural Machine Translation with Black-box Context Injection
TLDR
This work proposes a black-box approach for injecting the missing information to a pre-trained neural machine translation system, allowing to control the morphological variations in the generated translations without changing the underlying model or training data. Expand
Getting Gender Right in Neural Machine Translation
TLDR
The experiments show that adding a gender feature to an NMT system significantly improves the translation quality for some language pairs. Expand
Automatic Gender Identification and Reinflection in Arabic
The impressive progress in many Natural Language Processing (NLP) applications has increased the awareness of some of the biases these NLP systems have with regards to gender identities. In thisExpand
Identifying and Reducing Gender Bias in Word-Level Language Models
TLDR
This study proposes a metric to measure gender bias and proposes a regularization loss term for the language model that minimizes the projection of encoder-trained embeddings onto an embedding subspace that encodes gender and finds this regularization method to be effective in reducing gender bias. Expand
Assessing gender bias in machine translation: a case study with Google Translate
TLDR
Experimental evidence is provided that even if one does not expect in principle a 50:50 pronominal gender distribution, Google Translate yields male defaults much more frequently than what would be expected from demographic data alone. Expand
Gender aware spoken language translation applied to English-Arabic
TLDR
It is shown that NMT system can model the speaker/listener gender information to produce gender-aware translation that reduces the bias effect resulting from having training data dominated by particular gender forms. Expand
Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology
TLDR
This work presents a novel approach for converting between masculine-inflected and feminine-inflection sentences in morphologically rich languages and shows that it reduces gender stereotyping by a factor of 2.5 without any sacrifice to grammaticality. Expand
Assessing Social and Intersectional Biases in Contextualized Word Representations
TLDR
Evaluating bias effects at the contextual word level captures biases that are not captured at the sentence level, confirming the need for this novel approach. Expand
Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods
TLDR
A data-augmentation approach is demonstrated that, in combination with existing word-embedding debiasing techniques, removes the bias demonstrated by rule-based, feature-rich, and neural coreference systems in WinoBias without significantly affecting their performance on existing datasets. Expand
...
1
2
3
4
5
...