Справедливость
Related Papers
Finding the Middle Ground - A Model for Planning Satisficing Answers
To establish sophisticated dialogue sys- tems, text planning needs to cope with congruent as well as incongruent inter- locutor interests as given in everyday di- alogues. Little attention has been …...
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
AbstractThe ability to control for the kinds of information encoded in neural representation has a variety of use cases, especially in light of the challenge of interpreting these models. We …...
Constructing a Psychometric Testbed for Fair Natural Language Processing
AbstractPsychometric measures of ability, attitudes, perceptions, and beliefs are crucial for understanding user behavior in various contexts including health, security, e-commerce, and finance. Traditionally, psychometric dimensions have been measured and …...
Measuring Fairness of Text Classifiers via Prediction Sensitivity
AbstractWith the rapid growth in language processing applications, fairness has emerged as an important consideration in data-driven solutions. Although various fairness definitions have been explored in the recent literature, there …...
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models
AbstractLanguage models (LMs) are pretrained on diverse data sources—news, discussion forums, books, online encyclopedias. A significant portion of this data includes facts and opinions which, on one hand, celebrate democracy …...
Learning to Generate Equitable Text in Dialogue from Biased Training Data
AbstractThe ingrained principles of fairness in a dialogue system’s decision-making process and generated responses are crucial for user engagement, satisfaction, and task achievement. Absence of equitable and inclusive principles can …...
LEXPLAIN: Improving Model Explanations via Lexicon Supervision
AbstractModel explanations that shed light on the model’s predictions are becoming a desired additional output of NLP models, alongside their predictions. Challenges in creating these explanations include making them trustworthy …...