Related papers: Visualization for interactively adjusting the de-b…
Recent research in Natural Language Processing has revealed that word embeddings can encode social biases present in the training data which can affect minorities in real world applications. This paper explores the gender bias implicit in…
Bias in word embeddings such as Word2Vec has been widely investigated, and many efforts made to remove such bias. We show how to use conceptors debiasing to post-process both traditional and contextualized word embeddings. Our conceptor…
This paper presents an algorithm for enumerating biases in word embeddings. The algorithm exposes a large number of offensive associations related to sensitive features such as race and gender on publicly available embeddings, including 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 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…
Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into…
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…
Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members of various racial and gender identities. VLMs are being…
Neural network based models are a very powerful tool for creating word embeddings, the objective of these models is to group similar words together. These embeddings have been used as features to improve results in various applications such…
Machine learning models have been shown to inherit biases from their training datasets. This can be particularly problematic for vision-language foundation models trained on uncurated datasets scraped from the internet. The biases can be…
Recent research demonstrates that word embeddings, trained on the human-generated corpus, have strong gender biases in embedding spaces, and these biases can result in the discriminative results from the various downstream tasks. Whereas…
Humans show language-biased image recognition for a word-embedded image, known as picture-word interference. Such interference depends on hierarchical semantic categories and reflects that human language processing highly interacts with…
Word vector representations are well developed tools for various NLP and Machine Learning tasks and are known to retain significant semantic and syntactic structure of languages. But they are prone to carrying and amplifying bias which can…
Word embeddings have been shown to produce remarkable results in tackling a vast majority of NLP related tasks. Unfortunately, word embeddings also capture the stereotypical biases that are prevalent in society, affecting the predictive…
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…
It has been shown that word embeddings derived from large corpora tend to incorporate biases present in their training data. Various methods for mitigating these biases have been proposed, but recent work has demonstrated that these methods…
Many words have evolved in meaning as a result of cultural and social change. Understanding such changes is crucial for modelling language and cultural evolution. Low-dimensional embedding methods have shown promise in detecting words'…
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,…
Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising process guided by text embeddings extracted from pretrained vision-language models such as…
Word embeddings are useful for a wide variety of tasks, but they lack interpretability. By rotating word spaces, interpretable dimensions can be identified while preserving the information contained in the embeddings without any loss. In…