Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userExamining Covert Gender Bias: A Case Study in Turkish and English Machine Translation Models
فحص البساطة بين الجنسين السرية: دراسة حالة في نماذج الترجمة التركية والإنجليزية
175
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نظرا لأن الترجمة الآلية (MT) أصبحت أكثر قوة بشكل متزايد، والتي يمكن الوصول إليها، واستفادتها، فقد نمت إمكانات إدامة التحيز إلى جانب تقدمها.في حين تمت دراسة المؤشرات العلنية للحيز في الترجمة الآلية، فإننا نجادل بأن التحيزات السرية تعرض مشكلة ترسيخها.من خلال استخدام اللغة المحايدة بين الجنسين اللغة التركية واللغة الجنسية الإنجليزية، ندرس حالات التحيز بين الجنسين العلني والسرية في نماذج MT.على وجه التحديد، نقدم طريقة للتحقيق في العلامات الجنسانية غير المتماثلة.نقوم أيضا بتقييم التحيز في إسناد الشخصية وفحص الصور النمطية المهنية والشخصية من خلال مؤشرات التحيز العلنية في طرازات MT.يستكشف عملنا طبقة أعمق من التحيز في طرازات MT ويوضح الحاجة المستمرة لمنهجية متعددة التخصصات اللغوية في تطوير نموذج MT.
As Machine Translation (MT) has become increasingly more powerful, accessible, and widespread, the potential for the perpetuation of bias has grown alongside its advances. While overt indicators of bias have been studied in machine translation, we argue that covert biases expose a problem that is further entrenched. Through the use of the gender-neutral language Turkish and the gendered language English, we examine cases of both overt and covert gender bias in MT models. Specifically, we introduce a method to investigate asymmetrical gender markings. We also assess bias in the attribution of personhood and examine occupational and personality stereotypes through overt bias indicators in MT models. Our work explores a deeper layer of bias in MT models and demonstrates the continued need for language-specific, interdisciplinary methodology in MT model development.
References used
https://aclanthology.org/
rate research
Read More
With language models being deployed increasingly in the real world, it is essential to address the issue of the fairness of their outputs. The word embedding representations of these language models often implicitly draw unwanted associations that fo
rm a social bias within the model. The nature of gendered languages like Hindi, poses an additional problem to the quantification and mitigation of bias, owing to the change in the form of the words in the sentence, based on the gender of the subject. Additionally, there is sparse work done in the realm of measuring and debiasing systems for Indic languages. In our work, we attempt to evaluate and quantify the gender bias within a Hindi-English machine translation system. We implement a modified version of the existing TGBI metric based on the grammatical considerations for Hindi. We also compare and contrast the resulting bias measurements across multiple metrics for pre-trained embeddings and the ones learned by our machine translation model.
AbstractMachine translation (MT) technology has facilitated our daily tasks by providing accessible shortcuts for gathering, processing, and communicating information. However, it can suffer from biases that harm users and society at large. As a rela
tively new field of inquiry, studies of gender bias in MT still lack cohesion. This advocates for a unified framework to ease future research. To this end, we: i) critically review current conceptualizations of bias in light of theoretical insights from related disciplines, ii) summarize previous analyses aimed at assessing gender bias in MT, iii) discuss the mitigating strategies proposed so far, and iv) point toward potential directions for future work.
In this paper and we explore different techniques of overcoming the challenges of low-resource in Neural Machine Translation (NMT) and specifically focusing on the case of English-Marathi NMT. NMT systems require a large amount of parallel corpora to
obtain good quality translations. We try to mitigate the low-resource problem by augmenting parallel corpora or by using transfer learning. Techniques such as Phrase Table Injection (PTI) and back-translation and mixing of language corpora are used for enhancing the parallel data; whereas pivoting and multilingual embeddings are used to leverage transfer learning. For pivoting and Hindi comes in as assisting language for English-Marathi translation. Compared to baseline transformer model and a significant improvement trend in BLEU score is observed across various techniques. We have done extensive manual and automatic and qualitative evaluation of our systems. Since the trend in Machine Translation (MT) today is post-editing and measuring of Human Effort Reduction (HER) and we have given our preliminary observations on Translation Edit Rate (TER) vs. BLEU score study and where TER is regarded as a measure of HER.
Gender bias in word embeddings gradually becomes a vivid research field in recent years. Most studies in this field aim at measurement and debiasing methods with English as the target language. This paper investigates gender bias in static word embed
dings from a unique perspective, Chinese adjectives. By training word representations with different models, the gender bias behind the vectors of adjectives is assessed. Through a comparison between the produced results and a human scored data set, we demonstrate how gender bias encoded in word embeddings differentiates from people's attitudes.
In this work we explore the effect of incorporating demographic metadata in a text classifier trained on top of a pre-trained transformer language model. More specifically, we add information about the gender of critics and book authors when classify
ing the polarity of book reviews, and the polarity of the reviews when classifying the genders of authors and critics. We use an existing data set of Norwegian book reviews with ratings by professional critics, which has also been augmented with gender information, and train a document-level sentiment classifier on top of a recently released Norwegian BERT-model. We show that gender-informed models obtain substantially higher accuracy, and that polarity-informed models obtain higher accuracy when classifying the genders of book authors. For this particular data set, we take this result as a confirmation of the gender bias in the underlying label distribution, but in other settings we believe a similar approach can be used for mitigating bias in the model.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
