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.
@article{arxiv.1910.13425,
title = {Weakly-Supervised Deep Learning for Domain Invariant Sentiment Classification},
author = {Pratik Kayal and Mayank Singh and Pawan Goyal},
journal= {arXiv preprint arXiv:1910.13425},
year = {2019}
}