A Survey on Bias in Deep NLP

Deep neural networks are hegemonic approaches to many machine learning areas, including natural language processing (NLP). Thanks to the availability of large corpora collections and the capability of deep architectures to shape internal language mechanisms in self-supervised learning processes (als...

Descripción completa

Detalles Bibliográficos
Autores: Garrido-Muñoz, Ismael, Montejo-Ráez, Arturo, Martínez-Santiago, Fernando, Ureña-López, L. Alfonso
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:España
Institución:Universidad de Jaén
Repositorio:RUJA. Repositorio Institucional de la Producción Científica de la Universidad de Jaén
OAI Identifier:oai:ruja.ujaen.es:10953/1991
Acceso en línea:https://doi.org/10.3390/app11073184
https://www.mdpi.com/2076-3417/11/7/3184
https://hdl.handle.net/10953/1991
Access Level:acceso abierto
Palabra clave:natural language processing
deep learning
biased models
Descripción
Sumario:Deep neural networks are hegemonic approaches to many machine learning areas, including natural language processing (NLP). Thanks to the availability of large corpora collections and the capability of deep architectures to shape internal language mechanisms in self-supervised learning processes (also known as “pre-training”), versatile and performing models are released continuously for every new network design. These networks, somehow, learn a probability distribution of words and relations across the training collection used, inheriting the potential flaws, inconsistencies and biases contained in such a collection. As pre-trained models have been found to be very useful approaches to transfer learning, dealing with bias has become a relevant issue in this new scenario. We introduce bias in a formal way and explore how it has been treated in several networks, in terms of detection and correction. In addition, available resources are identified and a strategy to deal with bias in deep NLP is proposed.