Related papers: Gender Bias in Neural Natural Language Processing
Language can be used as a means of reproducing and enforcing harmful stereotypes and biases and has been analysed as such in numerous research. In this paper, we present a survey of 304 papers on gender bias in natural language processing.…
Word embedding has become essential for natural language processing as it boosts empirical performances of various tasks. However, recent research discovers that gender bias is incorporated in neural word embeddings, and downstream tasks…
Gender bias exists in natural language datasets which neural language models tend to learn, resulting in biased text generation. In this research, we propose a debiasing approach based on the loss function modification. We introduce a new…
Machine learning models are trained to find patterns in data. NLP models can inadvertently learn socially undesirable patterns when training on gender biased text. In this work, we propose a general framework that decomposes gender bias in…
Many text corpora exhibit socially problematic biases, which can be propagated or amplified in the models trained on such data. For example, doctor cooccurs more frequently with male pronouns than female pronouns. In this study we (i)…
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…
Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…
Large Language Models (LLMs) exhibit socio-economic biases that can propagate into downstream tasks. While prior studies have questioned whether intrinsic bias in LLMs affects fairness at the downstream task level, this work empirically…
Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society. Gender bias has been identified in the context of employment advertising and recruitment tools, due…
Recent advances in large language models (LLMs) have substantially improved natural language processing (NLP) applications. However, these models often inherit and amplify biases present in their training data. Although several datasets…
Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attracted attention to developing techniques that mitigate such biases. In this work, we perform an…
Natural Language Processing (NLP) models have been found discriminative against groups of different social identities such as gender and race. With the negative consequences of these undesired biases, researchers have responded with…
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…
Pretrained Language Models (PLMs) are widely used in NLP for various tasks. Recent studies have identified various biases that such models exhibit and have proposed methods to correct these biases. However, most of the works address a…
Word embeddings are extensively used in various NLP problems as a state-of-the-art semantic feature vector representation. Despite their success on various tasks and domains, they might exhibit an undesired bias for stereotypical categories…
Recent works have found evidence of gender bias in models of machine translation and coreference resolution using mostly synthetic diagnostic datasets. While these quantify bias in a controlled experiment, they often do so on a small scale…
Critical scholarship has elevated the problem of gender bias in data sets used to train virtual assistants (VAs). Most work has focused on explicit biases in language, especially against women, girls, femme-identifying people, and…
Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on…
The gender bias present in the data on which language models are pre-trained gets reflected in the systems that use these models. The model's intrinsic gender bias shows an outdated and unequal view of women in our culture and encourages…
Gender-bias stereotypes have recently raised significant ethical concerns in natural language processing. However, progress in detection and evaluation of gender bias in natural language understanding through inference is limited and…