English
Related papers

Related papers: Effect of dimensionality change on the bias of wor…

200 papers

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…

Computation and Language · Computer Science 2019-04-19 Christine Basta , Marta R. Costa-jussà , Noe Casas

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…

Computation and Language · Computer Science 2020-01-15 Stephanie Brandl , David Lassner , Maximilian Alber

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…

Computation and Language · Computer Science 2019-04-30 Anne Lauscher , Goran Glavaš

Word embeddings have become the basic building blocks for several natural language processing and information retrieval tasks. Pre-trained word embeddings are used in several downstream applications as well as for constructing…

Computation and Language · Computer Science 2017-11-22 Vikas Raunak

As a fundamental task in natural language processing, word embedding converts each word into a representation in a vector space. A challenge with word embedding is that as the vocabulary grows, the vector space's dimension increases, which…

Computation and Language · Computer Science 2024-11-05 Jintang Xue , Yun-Cheng Wang , Chengwei Wei , C. -C. Jay Kuo

In this paper, we provide a theoretical understanding of word embedding and its dimensionality. Motivated by the unitary-invariance of word embedding, we propose the Pairwise Inner Product (PIP) loss, a novel metric on the dissimilarity…

Machine Learning · Computer Science 2018-12-12 Zi Yin , Yuanyuan Shen

Static word embedding is still useful, particularly for context-unavailable tasks, because in the case of no context available, pre-trained language models often perform worse than static word embeddings. Although dimension is a key factor…

Computation and Language · Computer Science 2023-05-16 Lingfeng Shen , Haiyun Jiang , Lemao Liu , Ying Chen

The versatility of word embeddings for various applications is attracting researchers from various fields. However, the impact of hyper-parameters when training embedding model is often poorly understood. How much do hyper-parameters such…

Computation and Language · Computer Science 2018-04-13 Maryam Fanaeepour , Adam Makarucha , Jey Han Lau

How does word frequency in pre-training data affect the behavior of similarity metrics in contextualized BERT embeddings? Are there systematic ways in which some word relationships are exaggerated or understated? In this work, we explore…

Computation and Language · Computer Science 2021-04-20 Kaitlyn Zhou , Kawin Ethayarajh , Dan Jurafsky

The power of machine learning systems not only promises great technical progress, but risks societal harm. As a recent example, researchers have shown that popular word embedding algorithms exhibit stereotypical biases, such as gender bias.…

Machine Learning · Computer Science 2019-06-11 Marc-Etienne Brunet , Colleen Alkalay-Houlihan , Ashton Anderson , Richard Zemel

A representation learning method is considered stable if it consistently generates similar representation of the given data across multiple runs. Word Embedding Methods (WEMs) are a class of representation learning methods that generate…

Computation and Language · Computer Science 2024-06-13 Angana Borah , Manash Pratim Barman , Amit Awekar

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…

Computation and Language · Computer Science 2022-12-16 Gizem Sogancioglu , Heysem Kaya

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…

Computation and Language · Computer Science 2020-04-28 Kenneth Joseph , Jonathan H. Morgan

Word embeddings and convolutional neural networks (CNN) have attracted extensive attention in various classification tasks for Twitter, e.g. sentiment classification. However, the effect of the configuration used to train and generate the…

Information Retrieval · Computer Science 2017-03-23 Xiao Yang , Craig Macdonald , Iadh Ounis

Word embedding spaces are powerful tools for capturing latent semantic relationships between terms in corpora, and have become widely popular for building state-of-the-art natural language processing algorithms. However, studies have shown…

Computation and Language · Computer Science 2019-06-21 Inom Mirzaev , Anthony Schulte , Michael Conover , Sam Shah

In recent years, word embeddings have been widely used to measure biases in texts. Even if they have proven to be effective in detecting a wide variety of biases, metrics based on word embeddings lack transparency and interpretability. We…

Computation and Language · Computer Science 2023-07-19 Francisco Valentini , Germán Rosati , Damián Blasi , Diego Fernandez Slezak , Edgar Altszyler

Recent research has shown that static word embeddings can encode word frequency information. However, little has been studied about this phenomenon and its effects on downstream tasks. In the present work, we systematically study the…

Computation and Language · Computer Science 2023-10-23 Francisco Valentini , Juan Cruz Sosa , Diego Fernandez Slezak , Edgar Altszyler

We investigate the effect of various dependency-based word embeddings on distinguishing between functional and domain similarity, word similarity rankings, and two downstream tasks in English. Variations include word embeddings trained…

Computation and Language · Computer Science 2018-04-18 Sean MacAvaney , Amir Zeldes

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…

Computation and Language · Computer Science 2020-11-05 Rodrigo Alejandro Chávez Mulsa , Gerasimos Spanakis

Embedding spaces contain interpretable dimensions indicating gender, formality in style, or even object properties. This has been observed multiple times. Such interpretable dimensions are becoming valuable tools in different areas of…

Computation and Language · Computer Science 2024-04-04 Katrin Erk , Marianna Apidianaki
‹ Prev 1 2 3 10 Next ›