3 papers
cs.CL2022
A Robust Contrastive Alignment Method For Multi-Domain Text Classification
Xuefeng Li, Hao Lei, Liwen Wang +5
Multi-domain text classification can automatically classify texts in various scenarios. Due to the diversity of human languages, texts with the same label in different domains may…
cs.CL2021
Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling
Liwen Wang, Xuefeng Li, Jiachi Liu +3
Zero-shot cross-domain slot filling alleviates the data dependence in the case of data scarcity in the target domain, which has aroused extensive research. However, as most of the…
cs.AI2018
Orthogonal Policy Gradient and Autonomous Driving Application
Mincong Luo, Yin Tong, Jiachi Liu
One less addressed issue of deep reinforcement learning is the lack of generalization capability based on new state and new target, for complex tasks, it is necessary to give the c…