Neural Machine Translation systems built on top of Transformer-based architectures are routinely improving the state-of-the-art in translation quality according to word-overlap metrics. However, a growing number of studies also highlight the inherent gender bias that these models incorporate during training, which reflects poorly in their translations. In this work, we investigate whether these models can be instructed to fix their bias during inference using targeted, guided instructions as contexts. By translating relevant contextual sentences during inference along with the input, we observe large improvements in reducing the gender bias in translations, across three popular test suites (WinoMT, BUG, SimpleGen). We further propose a nove...
Artificial Intelligence (AI) is increasingly influencing people\u27s opinion and behavior in daily l...
International audienceThis paper is a blueprint of a current study in the making on gender bias in F...
International audienceThis paper is a blueprint of a current study in the making on gender bias in F...
Gender bias negatively impacts many natural language processing applications, including ma-chine tra...
Neural Machine Translation has the power of learning from a large collection of data, which allows i...
The presence of biases in artificial intelligence is arising as a social challenge. In the particula...
Misrepresentation of certain communities in current datasets is causing serious disruptions in artif...
Training data for NLP tasks often exhibits gender bias in that fewer sentences refer to women than t...
Gender bias is a significant issue in machine translation, leading to ongoing research efforts in de...
Multilingual Neural Machine Translation architectures mainly differ in the amount of sharing modules...
Multilingual neural machine translation architectures mainly differ in the number of sharing modules...
Recent years have seen an increased interest in machine translation technologies and applications du...
International audienceThis paper is a blueprint of a current study in the making on gender bias in F...
International audienceThis paper is a blueprint of a current study in the making on gender bias in F...
International audienceThis paper is a blueprint of a current study in the making on gender bias in F...
Artificial Intelligence (AI) is increasingly influencing people\u27s opinion and behavior in daily l...
International audienceThis paper is a blueprint of a current study in the making on gender bias in F...
International audienceThis paper is a blueprint of a current study in the making on gender bias in F...
Gender bias negatively impacts many natural language processing applications, including ma-chine tra...
Neural Machine Translation has the power of learning from a large collection of data, which allows i...
The presence of biases in artificial intelligence is arising as a social challenge. In the particula...
Misrepresentation of certain communities in current datasets is causing serious disruptions in artif...
Training data for NLP tasks often exhibits gender bias in that fewer sentences refer to women than t...
Gender bias is a significant issue in machine translation, leading to ongoing research efforts in de...
Multilingual Neural Machine Translation architectures mainly differ in the amount of sharing modules...
Multilingual neural machine translation architectures mainly differ in the number of sharing modules...
Recent years have seen an increased interest in machine translation technologies and applications du...
International audienceThis paper is a blueprint of a current study in the making on gender bias in F...
International audienceThis paper is a blueprint of a current study in the making on gender bias in F...
International audienceThis paper is a blueprint of a current study in the making on gender bias in F...
Artificial Intelligence (AI) is increasingly influencing people\u27s opinion and behavior in daily l...
International audienceThis paper is a blueprint of a current study in the making on gender bias in F...
International audienceThis paper is a blueprint of a current study in the making on gender bias in F...