Generative Pseudo Labeling

AI & ML interests

GPL is an unsupervised domain adaptation method for training dense retrievers. It is based on query generation and pseudo labeling with powerful cross-encoders. To train a domain-adapted model, it needs only the unlabeled target corpus and can achieve significant improvement over zero-shot models.

Recent Activity

kwang2049  updated a model over 2 years ago

GPL/README

kwang2049  updated a model over 2 years ago

GPL/robust04-tsdae-msmarco-distilbert-margin-mse

kwang2049  updated a model over 2 years ago

GPL/cqadupstack-tsdae-msmarco-distilbert-margin-mse

View all activity

Team members 2