Exploration and mitigation of gender bias in word embeddings from transformer-based language models

Exploration and mitigation of gender bias in word embeddings from transformer-based language models

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.

Bibliografski detalji
Glavni autori: Hossain, Ariyan, Haque, Rakinul, Hannan, Khondokar Mohammad Ahanaf, Rafa, Nowreen Tarannum, Musarrat, Humayra
Daljnji autori: Sadeque, Farig Yousuf
Format: Disertacija
Jezik:English
Izdano: Brac University 2024
Teme:
Natural Llnguage processing
Gender bias
Debiasing
Continued pretraining
Natural language processing (Computer science)
Online pristup:http://hdl.handle.net/10361/23457

Internet

http://hdl.handle.net/10361/23457

Similar Items