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.

Podrobná bibliografie
Hlavní autoři: Hossain, Ariyan, Haque, Rakinul, Hannan, Khondokar Mohammad Ahanaf, Rafa, Nowreen Tarannum, Musarrat, Humayra
Další autoři: Sadeque, Farig Yousuf
Médium: Diplomová práce
Jazyk:English
Vydáno: Brac University 2024
Témata:
Natural Llnguage processing
Gender bias
Debiasing
Continued pretraining
Natural language processing (Computer science)
On-line přístup:http://hdl.handle.net/10361/23457

Internet

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

Podobné jednotky