Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userUsing Gender- and Polarity-Informed Models to Investigate Bias
باستخدام النماذج المستنيرة بين الجنسين وقطبية للتحقيق في التحيز
457
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذا العمل، نستكشف تأثير دمج البيانات الوصفية الديموغرافية في نصوص نصية مدربة على رأس نموذج لغة محول مدرب مسبقا. وبشكل أكثر تحديدا، نضيف معلومات حول جنس النقاد ومؤلفي الكتاب عند تصنيف قطبية مراجعات الكتب، وقطبية الاستعراضات عند تصنيف الجنسين من المؤلفين والنقاد. نحن نستخدم مجموعة بيانات موجودة من مراجعات الكتاب النرويجية من خلال تقييمات من قبل النقاد المحترفين، والتي عززت أيضا مع المعلومات الجنسانية، وتدريب مصنف معنويات على مستوى المستند أعلى نموذج برت النرويجي الذي تم إصداره مؤخرا. نظهر أن النماذج المستنيرة بين الجنسين تحصل على دقة أعلى إلى حد كبير، وأن النماذج المستنيرة بالقطبية تحصل على دقة أعلى عند تصنيف جندات مؤلفي الكتاب. بالنسبة إلى مجموعة البيانات الخاصة بهذه الطريقة، نأخذ هذه النتيجة تأكيدا بتحيز بين الجنسين في توزيع الملصقات الأساسية، ولكن في أوائل أخرى نعتقد أنه يمكن استخدام نهج مماثل لتخفيف التحيز في النموذج.
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 classifying 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.
References used
https://aclanthology.org/
rate research
Read More
Gender inequality represents a considerable loss of human potential and perpetuates a culture of violence, higher gender wage gaps, and a lack of representation of women in higher and leadership positions. Applications powered by Artificial Intellige
nce (AI) are increasingly being used in the real world to provide critical decisions about who is going to be hired, granted a loan, admitted to college, etc. However, the main pillars of AI, Natural Language Processing (NLP) and Machine Learning (ML) have been shown to reflect and even amplify gender biases and stereotypes, which are mainly inherited from historical training data. In an effort to facilitate the identification and mitigation of gender bias in English text, we develop a comprehensive taxonomy that relies on the following gender bias types: Generic Pronouns, Sexism, Occupational Bias, Exclusionary Bias, and Semantics. We also provide a bottom-up overview of gender bias, from its societal origin to its spillover onto language. Finally, we link the societal implications of gender bias to their corresponding type(s) in the proposed taxonomy. The underlying motivation of our work is to help enable the technical community to identify and mitigate relevant biases from training corpora for improved fairness in NLP systems.
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.
Natural Language Processing (NLP) systems are at the heart of many critical automated decision-making systems making crucial recommendations about our future world. Gender bias in NLP has been well studied in English, but has been less studied in oth
er languages. In this paper, a team including speakers of 9 languages - Chinese, Spanish, English, Arabic, German, French, Farsi, Urdu, and Wolof - reports and analyzes measurements of gender bias in the Wikipedia corpora for these 9 languages. We develop extensions to profession-level and corpus-level gender bias metric calculations originally designed for English and apply them to 8 other languages, including languages that have grammatically gendered nouns including different feminine, masculine, and neuter profession words. We discuss future work that would benefit immensely from a computational linguistics perspective.
Internet search affects people's cognition of the world, so mitigating biases in search results and learning fair models is imperative for social good. We study a unique gender bias in image search in this work: the search images are often gender-imb
alanced for gender-neutral natural language queries. We diagnose two typical image search models, the specialized model trained on in-domain datasets and the generalized representation model pre-trained on massive image and text data across the internet. Both models suffer from severe gender bias. Therefore, we introduce two novel debiasing approaches: an in-processing fair sampling method to address the gender imbalance issue for training models, and a post-processing feature clipping method base on mutual information to debias multimodal representations of pre-trained models. Extensive experiments on MS-COCO and Flickr30K benchmarks show that our methods significantly reduce the gender bias in image search models.
Potential gender biases existing in Wikipedia's content can contribute to biased behaviors in a variety of downstream NLP systems. Yet, efforts in understanding what inequalities in portraying women and men occur in Wikipedia focused so far only on *
biographies*, leaving open the question of how often such harmful patterns occur in other topics. In this paper, we investigate gender-related asymmetries in Wikipedia titles from *all domains*. We assess that for only half of gender-related articles, i.e., articles with words such as *women* or *male* in their titles, symmetrical counterparts describing the same concept for the other gender (and clearly stating it in their titles) exist. Among the remaining imbalanced cases, the vast majority of articles concern sports- and social-related issues. We provide insights on how such asymmetries can influence other Wikipedia components and propose steps towards reducing the frequency of observed patterns.
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
