Meta-learning algorithm trains the model to adapt to another domain by utilizing only a small amount of training data . Model surpasses transfer learning-based approach by up to 2-4 BLEUscores . We assume that domain-general knowledge is a significant factor in handling data-scarceomains. Our proposed algorithm ispertinent for fast adaptation and consistently outperforms other baselinemodels. Extensive experimental results show that our proposed algorithm . Our model surpasses a transfer learning . based approach by . up to two-four scores .

Author(s) : Yunwon Tae, Cheonbok Park, Taehee Kim, Soyoung Yang, Mohammad Azam Khan, Eunjeong Park, Tao Qin, Jaegul Choo

Links : PDF - Abstract

Code :


Keywords : learning - algorithm - model - data - approach -

Leave a Reply

Your email address will not be published. Required fields are marked *