Related papers: ValNorm Quantifies Semantics to Reveal Consistent …

Language models are trained on large-scale corpora that embed implicit biases documented in psychology. Valence associations (pleasantness/unpleasantness) of social groups determine the biased attitudes towards groups and concepts in social…

Does the grammatical gender of a language interfere when measuring the semantic gender information captured by its word embeddings? A number of anomalous gender bias measurements in the embeddings of gendered languages suggest this…

The statistical regularities in language corpora encode well-known social biases into word embeddings. Here, we focus on gender to provide a comprehensive analysis of group-based biases in widely-used static English word embeddings trained…

Word embeddings have recently been shown to reflect many of the pronounced societal biases (e.g., gender bias or racial bias). Existing studies are, however, limited in scope and do not investigate the consistency of biases across relevant…

VAST, the Valence-Assessing Semantics Test, is a novel intrinsic evaluation task for contextualized word embeddings (CWEs). VAST uses valence, the association of a word with pleasantness, to measure the correspondence of word-level LM…

Word embeddings capture semantic relationships based on contextual information and are the basis for a wide variety of natural language processing applications. Notably these relationships are solely learned from the data and subsequently…

Recent studies have shown that word embeddings exhibit gender bias inherited from the training corpora. However, most studies to date have focused on quantifying and mitigating such bias only in English. These analyses cannot be directly…

Static word embeddings are ubiquitous in computational social science applications and contribute to practical decision-making in a variety of fields including law and healthcare. However, assessing the statistical uncertainty in downstream…

Language carries implicit human biases, functioning both as a reflection and a perpetuation of stereotypes that people carry with them. Recently, ML-based NLP methods such as word embeddings have been shown to learn such language biases…

Word embeddings use vectors to represent words such that the geometry between vectors captures semantic relationship between the words. In this paper, we develop a framework to demonstrate how the temporal dynamics of the embedding can be…

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…

The number of senses of a given word, or polysemy, is a very subjective notion, which varies widely across annotators and resources. We propose a novel method to estimate polysemy, based on simple geometry in the contextual embedding space.…

Factor analysis studies have shown that the primary dimensions of word meaning are Valence (V), Arousal (A), and Dominance (D) (also referred to in social cognition research as Competence (C)). These dimensions impact various aspects of our…

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…

Social biases are encoded in word embeddings. This presents a unique opportunity to study society historically and at scale, and a unique danger when embeddings are used in downstream applications. Here, we investigate the extent to which…

Modern models for common NLP tasks often employ machine learning techniques and train on journalistic, social media, or other culturally-derived text. These have recently been scrutinized for racial and gender biases, rooting from inherent…

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…

Societal biases in the usage of words, including harmful stereotypes, are frequently learned by common word embedding methods. These biases manifest not only between a word and an explicit marker of its stereotype, but also between words…

Human biases are ubiquitous but not uniform: disparities exist across linguistic, cultural, and societal borders. As large amounts of recent literature suggest, language models (LMs) trained on human data can reflect and often amplify the…

We demonstrate the utility of a new methodological tool, neural-network word embedding models, for large-scale text analysis, revealing how these models produce richer insights into cultural associations and categories than possible with…