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.

Bibliografiska uppgifter
Huvudupphovsmän: Hossain, Ariyan, Haque, Rakinul, Hannan, Khondokar Mohammad Ahanaf, Rafa, Nowreen Tarannum, Musarrat, Humayra
Övriga upphovsmän: Sadeque, Farig Yousuf
Materialtyp: Lärdomsprov
Språk:English
Publicerad: Brac University 2024
Ämnen:
Natural Llnguage processing
Gender bias
Debiasing
Continued pretraining
Natural language processing (Computer science)
Länkar:http://hdl.handle.net/10361/23457

Internet

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

Liknande verk