Fairness in machine learning is of considerable interest in recent years
owing to the propensity of algorithms trained on historical data to amplify and
perpetuate historical biases. In this paper, we argue for a formal
reconstruction of fairness definitions, not so much to replace existing
definitions but to ground their application in an epistemic setting and allow
for rich environmental modelling. Consequently we look into three notions:
fairness through unawareness, demographic parity and counterfactual fairness,
and formalise these in the epistemic situation calculus.

本文主要论述机器学习中公平性问题，提出三种公平模型：无意识公平、人口统计学公平和反事实公平，并在认识情境演算中进行了形式化的定义。

公平和偏见的逻辑理论

Toward A Logical Theory Of Fairness and Bias

Data-driven analyses of biases in historical texts can help illuminate the
origin and development of biases prevailing in modern society.
However, digitised historical documents pose a challenge for NLP
practitioners as these corpora suffer from errors introduced by optical
character recognition (OCR) and are written in an archaic language. In this
paper, we investigate the continuities and transformations of bias in
historical newspapers published in the Caribbean during the colonial era (18th
to 19th centuries). Our analyses are performed along the axes of gender, race,
and their intersection. We examine these biases by conducting a temporal study
in which we measure the development of lexical associations using
distributional semantics models and word embeddings. Further, we evaluate the
effectiveness of techniques designed to process OCR-generated data and assess
their stability when trained on and applied to the noisy historical newspapers.
We find that there is a trade-off between the stability of the word embeddings
and their compatibility with the historical dataset. We provide evidence that
gender and racial biases are interdependent, and their intersection triggers
distinct effects. These findings align with the theory of intersectionality,
which stresses that biases affecting people with multiple marginalised
identities compound to more than the sum of their constituents.

本文通过时间序列的词汇联想分析，以及针对 OCR 错误引入噪音的技术处理，研究了加勒比地区殖民时期（18 世纪到 19 世纪）历史报纸中性别、种族偏见的连续性和转化。研究结果表明，种族和性别偏见是相互依存的，两者的交叉触发了不同效应，这与交叉性理论一致。