13 citations · 44 across the 7 of their papers we have counts for
7 papers
Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering
Juan Zha, Zheng Li, Ying Wei +1
Few-Shot Text Classification (FSTC) imitates humans to learn a new text classifier efficiently with only few examples, by leveraging prior knowledge from historical tasks. However,…
Frustratingly Easy Transferability Estimation
Long-Kai Huang, Ying Wei, Yu Rong +2
Transferability estimation has been an essential tool in selecting a pre-trained model and the layers in it for transfer learning, to transfer, so as to maximize the performance on…
Fisher Deep Domain Adaptation
Yinghua Zhang, Yu Zhang, Ying Wei +3
Deep domain adaptation models learn a neural network in an unlabeled target domain by leveraging the knowledge from a labeled source domain. This can be achieved by learning a doma…
Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning
Zheng Li, Xin Li, Ying Wei +3
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem. However, such formulation hinders the effectiveness of supervised methods d…
Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification
Zheng Li, Ying Wei, Yu Zhang +3
Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or…
Learning to Multitask
Yu Zhang, Ying Wei, Qiang Yang
Multitask learning has shown promising performance in many applications and many multitask models have been proposed. In order to identify an effective multitask model for a given…