paper-with-me

Papers

An Empirical Study on the Fairness of Pre-trained Word Embeddings

2022-07-01 · NAACL (GeBNLP) 2022 7 · Emeralda Sesari, Max Hort, Federica Sarro

Pre-trained word embedding models are easily distributed and applied, as they alleviate users from the effort to train models themselves. With widely distributed models, it is important to ensure that they do not exhibit undesired behaviour, such as biases against population groups. For this purpose, we carry out an empirical study on evaluating the bias of 15 publicly available, pre-trained word embeddings model based on three training algorithms (GloVe, word2vec, and fastText) with regard to four bias metrics (WEAT, SEMBIAS,DIRECT BIAS, and ECT). The choice of word embedding models and bias metrics is motivated by a literature survey over 37 publications which quantified bias on pre-trained word embeddings. Our results indicate that fastText is the least biased model (in 8 out of 12 cases) and small vector lengths lead to a higher bias.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

FairnessWord Embeddings

Similar Papers 제목 키워드 기반

Impact of Gender Debiased Word Embeddings in Language Modeling

2021-05-03 · Christine Basta, Marta R. Costa-jussà

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data an…

FairnessLanguage ModelingLanguage ModellingWord Embeddings

Towards Fair and Explainable AI using a Human-Centered AI Approach

2023-06-12 · Bhavya Ghai

The rise of machine learning (ML) is accompanied by several high-profile cases that have stressed the need for fairness, accountability, explainability and trust in ML systems. The existing literature has largely focused…

FairnessWord Embeddings

An Empirical Study of the Downstream Reliability of Pre-Trained Word Embeddings

2020-12-01 · COLING 2020 8 · Anthony Rios, Brandon Lwowski

While pre-trained word embeddings have been shown to improve the performance of downstream tasks, many questions remain regarding their reliability: Do the same pre-trained word embeddings result in the best performance …

ImputationWord Embeddings

Addressing Biases in the Texts using an End-to-End Pipeline Approach

2023-03-13 · Shaina Raza, Syed Raza Bashir, Sneha, Urooj Qamar

The concept of fairness is gaining popularity in academia and industry. Social media is especially vulnerable to media biases and toxic language and comments. We propose a fair ML pipeline that takes a text as input and …

FairnessWord Embeddings

Blind signal decomposition of various word embeddings based on join and individual variance explained

2020-11-30 · Yikai Wang, Weijian Li

In recent years, natural language processing (NLP) has become one of the most important areas with various applications in human's life. As the most fundamental task, the field of word embedding still requires more atten…

Dimensionality ReductionSentiment AnalysisWord Embeddings