Асимметричное взаимное обучение
method
ID: asymmetricmutuallearning
Related Papers
Asymmetric Mutual Learning for Multi-source Unsupervised Sentiment Adaptation with Dynamic Feature Network
AbstractRecently, fine-tuning the pre-trained language model (PrLM) on labeled sentiment datasets demonstrates impressive performance. However, collecting labeled sentiment dataset is time-consuming, and fine-tuning the whole PrLM brings about much computation …...