English
Related papers

Related papers: Debiasing Sentence Embedders through Contrastive W…

200 papers

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…

Computation and Language · Computer Science 2023-06-27 Hailey Joren , David Alvarez-Melis

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Computation and Language · Computer Science 2025-03-13 Liu Yu , Ludie Guo , Ping Kuang , Fan Zhou

In this paper, we advance the current state-of-the-art method for debiasing monolingual word embeddings so as to generalize well in a multilingual setting. We consider different methods to quantify bias and different debiasing approaches…

Computation and Language · Computer Science 2021-07-23 Srijan Bansal , Vishal Garimella , Ayush Suhane , Animesh Mukherjee

Deep learning models continuously break new records across different NLP tasks. At the same time, their success exposes weaknesses of model evaluation. Here, we compile several key pitfalls of evaluation of sentence embeddings, a currently…

Computation and Language · Computer Science 2019-06-05 Steffen Eger , Andreas Rücklé , Iryna Gurevych

Word embeddings derived from human-generated corpora inherit strong gender bias which can be further amplified by downstream models. Some commonly adopted debiasing approaches, including the seminal Hard Debias algorithm, apply…

Computation and Language · Computer Science 2020-05-05 Tianlu Wang , Xi Victoria Lin , Nazneen Fatema Rajani , Bryan McCann , Vicente Ordonez , Caiming Xiong

Natural Language Processing (NLP) systems learn harmful societal biases that cause them to amplify inequality as they are deployed in more and more situations. To guide efforts at debiasing these systems, the NLP community relies on a…

Computation and Language · Computer Science 2021-06-09 Seraphina Goldfarb-Tarrant , Rebecca Marchant , Ricardo Muñoz Sanchez , Mugdha Pandya , Adam Lopez

Sentence embeddings are an important component of many natural language processing (NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such…

Computation and Language · Computer Science 2021-05-28 John Giorgi , Osvald Nitski , Bo Wang , Gary Bader

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…

Computation and Language · Computer Science 2022-04-13 Sean Matthews , John Hudzina , Dawn Sepehr

As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their age,…

Machine Learning · Computer Science 2021-05-03 Maarten Buyl , Tijl De Bie

Mitigation of gender bias in NLP has a long history tied to debiasing static word embeddings. More recently, attention has shifted to debiasing pre-trained language models. We study to what extent the simplest projective debiasing methods,…

Computation and Language · Computer Science 2024-05-27 Hillary Dawkins , Isar Nejadgholi , Daniel Gillis , Judi McCuaig

Embedding-based similarity metrics between text sequences can be influenced not just by the content dimensions we most care about, but can also be biased by spurious attributes like the text's source or language. These document confounders…

Computation and Language · Computer Science 2025-09-25 Yu Fan , Yang Tian , Shauli Ravfogel , Mrinmaya Sachan , Elliott Ash , Alexander Hoyle

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…

Computation and Language · Computer Science 2019-11-26 Zekun Yang , Juan Feng

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…

Computation and Language · Computer Science 2022-01-26 Xavier Ferrer-Aran , Tom van Nuenen , Natalia Criado , Jose M. Such

Mitigating biases in machine learning models has become an increasing concern in Natural Language Processing (NLP), particularly in developing fair text embeddings, which are crucial yet challenging for real-world applications like search…

Computation and Language · Computer Science 2024-06-25 Wenlong Deng , Blair Chen , Beidi Zhao , Chiyu Zhang , Xiaoxiao Li , Christos Thrampoulidis

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…

Computation and Language · Computer Science 2019-06-05 Yusu Qian , Urwa Muaz , Ben Zhang , Jae Won Hyun

Following the recent success of word embeddings, it has been argued that there is no such thing as an ideal representation for words, as different models tend to capture divergent and often mutually incompatible aspects like…

Computation and Language · Computer Science 2021-12-28 Mikel Artetxe , Gorka Labaka , Iñigo Lopez-Gazpio , Eneko Agirre

Sentence embedding methods using natural language inference (NLI) datasets have been successfully applied to various tasks. However, these methods are only available for limited languages due to relying heavily on the large NLI datasets. In…

Computation and Language · Computer Science 2021-06-10 Hayato Tsukagoshi , Ryohei Sasano , Koichi Takeda

Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring…

Computation and Language · Computer Science 2021-09-10 Michael Mendelson , Yonatan Belinkov

Distributed word embeddings have shown superior performances in numerous Natural Language Processing (NLP) tasks. However, their performances vary significantly across different tasks, implying that the word embeddings learnt by those…

Computation and Language · Computer Science 2017-09-21 Danushka Bollegala , Kohei Hayashi , Ken-ichi Kawarabayashi

Distributional word vectors have recently been shown to encode many of the human biases, most notably gender and racial biases, and models for attenuating such biases have consequently been proposed. However, existing models and studies (1)…

Computation and Language · Computer Science 2020-01-06 Anne Lauscher , Goran Glavaš , Simone Paolo Ponzetto , Ivan Vulić