相关论文: Gender Stereotype Reinforcement: Measuring the Gen…

Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these…

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…

Studies have shown that some Natural Language Processing (NLP) systems encode and replicate harmful biases with potential adverse ethical effects in our society. In this article, we propose an approach for identifying gender and racial…

Concerns regarding the footprint of societal biases in information retrieval (IR) systems have been raised in several previous studies. In this work, we examine various recent IR models from the perspective of the degree of gender bias in…

Humans have entered the age of algorithms. Each minute, algorithms shape countless preferences from suggesting a product to a potential life partner. In the marketplace algorithms are trained to learn consumer preferences from customer…

Various measures have been proposed to quantify human-like social biases in word embeddings. However, bias scores based on these measures can suffer from measurement error. One indication of measurement quality is reliability, concerning…

It has been shown that word embeddings can exhibit gender bias, and various methods have been proposed to quantify this. However, the extent to which the methods are capturing social stereotypes inherited from the data has been debated.…

Neural machine translation has significantly pushed forward the quality of the field. However, there are remaining big issues with the output translations and one of them is fairness. Neural models are trained on large text corpora which…

Word embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the down-stream NLP applications that use those word embeddings.…

Gender bias is highly impacting natural language processing applications. Word embeddings have clearly been proven both to keep and amplify gender biases that are present in current data sources. Recently, contextualized word embeddings…

Word embeddings carry stereotypical connotations from the text they are trained on, which can lead to invalid inferences in downstream models that rely on them. We use this observation to design a mechanism for measuring stereotypes using…

Multi-modal search engines have experienced significant growth and widespread use in recent years, making them the second most common internet use. While search engine systems offer a range of services, the image search field has recently…

Word embeddings are often criticized for capturing undesirable word associations such as gender stereotypes. However, methods for measuring and removing such biases remain poorly understood. We show that for any embedding model that…

The provided contents by information retrieval (IR) systems can reflect the existing societal biases and stereotypes. Such biases in retrieval results can lead to further establishing and strengthening stereotypes in society and also in the…

This work investigates the effect of gender-stereotypical biases in the content of retrieved results on the relevance judgement of users/annotators. In particular, since relevance in information retrieval (IR) is a multi-dimensional…

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent…

The Word Embedding Association Test shows that GloVe and word2vec word embeddings exhibit human-like implicit biases based on gender, race, and other social constructs (Caliskan et al., 2017). Meanwhile, research on learning reusable text…

Biases in culture, gender, ethnicity, etc. have existed for decades and have affected many areas of human social interaction. These biases have been shown to impact machine learning (ML) models, and for natural language processing (NLP),…

Non-contextual word embedding models have been shown to inherit human-like stereotypical biases of gender, race and religion from the training corpora. To counter this issue, a large body of research has emerged which aims to mitigate these…

Many studies have revealed that word embeddings, language models, and models for specific downstream tasks in NLP are prone to social biases, especially gender bias. Recently these techniques have been gradually applied to automatic…