Cargando…

Compressed models for co-reference resolution: enhancing efficiency with debiased word embeddings

This work presents a comprehensive approach to reduce bias in word embedding vectors and evaluate the impact on various Natural Language Processing (NLP) tasks. Two GloVe variations (840B and 50) are debiased by identifying the gender direction in the word embedding space and then removing or reduci...

Descripción completa

Detalles Bibliográficos
Autores principales: Ioannides, Georgios, Jadhav, Aishwarya, Sharma, Aditi, Navali, Samarth, Black, Alan W.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10613201/
https://www.ncbi.nlm.nih.gov/pubmed/37898713
http://dx.doi.org/10.1038/s41598-023-45677-0