Browsing by Subject "Continued pretraining"
Now showing items 1-1 of 1
-
Exploration and mitigation of gender bias in word embeddings from transformer-based language models
(Brac University, 2023-09)Machine learning has the potential to uncover data biases resulting from human error when it’s implemented without proper restraint. However, this complexity arises from word embedding, which is a prominent technique for ...
