Skip to main content

BibTeX

@inProceedings{goldfarbtarrant-etal-2021-intrinsic-312616,
	title        = {Intrinsic Bias Metrics Do Not Correlate with Application Bias},
	abstract     = {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 variety of metrics that quantify bias in models. Some of these metrics are intrinsic, measuring bias in word embedding spaces, and some are extrinsic, measuring bias in downstream tasks that the word embeddings enable. Do these intrinsic and extrinsic metrics correlate with each other? We compare intrinsic and extrinsic metrics across hundreds of trained models covering different tasks and experimental conditions. Our results show no reliable correlation between these metrics that holds in all scenarios across tasks and languages. We urge researchers working on debiasing to focus on extrinsic measures of bias, and to make using these measures more feasible via creation of new challenge sets and annotated test data. To aid this effort, we release code, a new intrinsic metric, and an annotated test set focused on gender bias in hate speech.},
	booktitle    = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), August 2021, Online},
	author       = {Goldfarb-Tarrant, Seraphina and Marchant, Rebecca and Muñoz Sánchez, Ricardo and Pandya, Mugdha and Lopez, Adam},
	year         = {2021},
	publisher    = {Association for Computational Linguistics},
	ISBN         = {978-1-954085-52-7 },
}

@inProceedings{munozsanchez-etal-2022-first-320225,
	title        = {A First Attempt at Unreliable News Detection in Swedish},
	abstract     = {Throughout the COVID-19 pandemic, a parallel infodemic has also been going on such that the information has been spreading faster than the virus itself. During this time, every individual needs to access accurate news in order to take corresponding protective measures, regardless of their country of origin or the language they speak, as misinformation can cause significant loss to not only individuals but also society. In this paper we train several machine learning models (ranging from traditional machine learning to deep learning) to try to determine whether news articles come from either a reliable or an unreliable source, using just the body of the article. Moreover, we use a previously introduced corpus of news in Swedish related to the COVID-19 pandemic for the classification task. Given that our dataset is both unbalanced and small, we use subsampling and easy data augmentation (EDA) to try to solve these issues. In the end, we realize that, due to the small size of our dataset, using traditional machine learning along with data augmentation yields results that rival those of transformer models such as BERT.},
	booktitle    = {Proceedings of the Second International Workshop on Resources and Techniques for User Information in Abusive Language Analysis, Marseille, 20-25 June, 2022 / Editors: Johanna Monti, Valerio Basile, Maria Pia Di Buono, Raffaele Manna, Antonio Pascucci, Sara Tonell},
	author       = {Muñoz Sánchez, Ricardo and Johansson, Eric and Tayefeh, Shakila and Kad, Shreyash},
	year         = {2022},
	publisher    = {European Language Resources Association (ELRA)},
	address      = {Paris},
	ISBN         = {979-10-95546-99-3},
}