相关论文: Bias in Machine Learning -- What is it Good for?

The blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning…

Social bias in language - towards genders, ethnicities, ages, and other social groups - poses a problem with ethical impact for many NLP applications. Recent research has shown that machine learning models trained on respective data may not…

Machine learning systems have been shown to propagate the societal errors of the past. In light of this, a wealth of research focuses on designing solutions that are "fair." Even with this abundance of work, there is no singular definition…

Machine translation (MT) technology has facilitated our daily tasks by providing accessible shortcuts for gathering, elaborating and communicating information. However, it can suffer from biases that harm users and society at large. As a…

Discrimination can occur when the underlying unbiased labels are overwritten by an agent with potential bias, resulting in biased datasets that unfairly harm specific groups and cause classifiers to inherit these biases. In this paper, we…

Recent studies in the field of Machine Translation (MT) and Natural Language Processing (NLP) have shown that existing models amplify biases observed in the training data. The amplification of biases in language technology has mainly been…

In this work, we analyze papers that are classified as primary hep-lat to study whether there is any race or gender bias in the journal-publication process. We implement machine learning to predict the race and gender of authors based on…

Word embeddings are a fixed, distributional representation of the context of words in a corpus learned from word co-occurrences. Despite their proven utility in machine learning tasks, word embedding models may capture uneven semantic and…

With the widespread and pervasive use of Artificial Intelligence (AI) for automated decision-making systems, AI bias is becoming more apparent and problematic. One of its negative consequences is discrimination: the unfair, or unequal…

As different research works report and daily life experiences confirm, learning models can result in biased outcomes. The biased learned models usually replicate historical discrimination in society and typically negatively affect the less…

Algorithms learned from data are increasingly used for deciding many aspects in our life: from movies we see, to prices we pay, or medicine we get. Yet there is growing evidence that decision making by inappropriately trained algorithms may…

Machine learning models built on datasets containing discriminative instances attributed to various underlying factors result in biased and unfair outcomes. It's a well founded and intuitive fact that existing bias mitigation strategies…

Given a supervised machine learning problem where the training set has been subject to a known sampling bias, how can a model be trained to fit the original dataset? We achieve this through the Bayesian inference framework by altering the…

Causal machine learning methods which flexibly generate heterogeneous treatment effect estimates could be very useful tools for governments trying to make and implement policy. However, as the critical artificial intelligence literature has…

Positional bias - where models overemphasize certain positions regardless of content - has been shown to negatively impact model performance across various tasks. While recent research has extensively examined positional bias in text…

Fairness in machine learning has attained significant focus due to the widespread application in high-stake decision-making tasks. Unregulated machine learning classifiers can exhibit bias towards certain demographic groups in data, thus…

This paper describes an experimental comparison of seven different learning algorithms on the problem of learning to disambiguate the meaning of a word from context. The algorithms tested include statistical, neural-network, decision-tree,…

This paper clarifies why bias cannot be completely mitigated in Machine Learning (ML) and proposes an end-to-end methodology to translate the ethical principle of justice and fairness into the practice of ML development as an ongoing…

As an intrinsic and fundamental property of big data, data heterogeneity exists in a variety of real-world applications, such as precision medicine, autonomous driving, financial applications, etc. For machine learning algorithms, the…

We present a large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives. We analyze the potential allocation harms that can result from semantic…