Mitigating Gender Bias in Machine Translation with Target Gender Annotations
Mitigating Gender Bias in Machine Translation with Target Gender Annotations
复制标题
使用目标性别注释减轻机器翻译中的性别偏见
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Marcis Pinnis
中科院分区：
文献类型：
--
作者：
Toms Bergmanis;Arturs Stafanovivcs;Marcis Pinnis
翻译时，秘书询问了详细情况。对于一种具有语法性别的语言，可能有必要确定主题秘书的性别。如果句子不包含必要的信息，就不可能总是能够消除歧义。在这种情况下，机器翻译系统选择最常见的翻译选项，这往往对应于刻板印象的翻译，从而可能加剧某些群体和人的偏见和边缘化。我们认为，适当的翻译所需的信息并不总是从被翻译的句子中推断出来的，甚至可能依赖于外部知识。因此，在这项工作中，我们建议将获取必要信息的任务与学习在获得必要信息时正确翻译的任务分离。为此，我们提出了一种训练机器翻译系统使用包含主题性别信息的词级注释的方法。为了准备训练数据，我们用对应的目标语言单词的语法性别信息来标注规则的源语言单词。使用这种数据来培训机器翻译系统，可在有关于受试者性别的信息时减少它们对性别陈规定型观念的依赖。我们在五个语言对上的实验表明，这可以将WinoMT测试集的准确率提高25.8个百分点。
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. We argue that the information necessary for an adequate translation can not always be deduced from the sentence being translated or even might depend on external knowledge. Therefore, in this work, we propose to decouple the task of acquiring the necessary information from the task of learning to translate correctly when such information is available. To that end, we present a method for training machine translation systems to use word-level annotations containing information about subject’s gender. To prepare training data, we annotate regular source language words with grammatical gender information of the corresponding target language words. Using such data to train machine translation systems reduces their reliance on gender stereotypes when information about the subject’s gender is available. Our experiments on five language pairs show that this allows improving accuracy on the WinoMT test set by up to 25.8 percentage points.
DOI：
10.18653/v1/n18-2003
发表时间：
2018-04
期刊：
ArXiv
影响因子：
--
作者：
Jieyu Zhao;Tianlu Wang;Mark Yatskar;Vicente Ordonez;Kai-Wei Chang
通讯作者：
Jieyu Zhao;Tianlu Wang;Mark Yatskar;Vicente Ordonez;Kai-Wei Chang