Weakly-Supervised Deep Learning for Domain Invariant Sentiment Classification
Kayal, Pratik, Singh, Mayank, Goyal, Pawan
The task of learning a sentiment classification model that adapts well to any target domain, different from the source domain, is a challenging problem. Majority of the existing approaches focus on learning a common representation by leveraging both source and target data during training. In this paper, we introduce a two-stage training procedure that leverages weakly supervised datasets for developing simple lift-and-shift-based predictive models without being exposed to the target domain during the training phase. Experimental results show that transfer with weak supervision from a source domain to various target domains provides performance very close to that obtained via supervised training on the target domain itself.
Oct-29-2019
- Country:
- North America > United States
- Oregon > Multnomah County
- Portland (0.04)
- New York > New York County
- New York City (0.04)
- Oregon > Multnomah County
- Asia
- Vietnam > Long An Province
- Tân An (0.04)
- India
- Telangana > Hyderabad (0.05)
- Gujarat > Gandhinagar (0.04)
- West Bengal > Kharagpur (0.04)
- Vietnam > Long An Province
- North America > United States
- Genre:
- Research Report > New Finding (0.34)
- Technology: