Weakly-Supervised Deep Learning for Domain Invariant Sentiment Classification

Show simple item record

dc.contributor.author Kayal, Pratik
dc.contributor.author Singh, Mayank
dc.contributor.author Goyal, Pawan
dc.date.accessioned 2019-11-19T11:29:01Z
dc.date.available 2019-11-19T11:29:01Z
dc.date.issued 2019-10
dc.identifier.citation Kayal, Pratik; Singh, Mayank and Goyal, Pawan, "Weakly-supervised deep learning for domain invariant sentiment classification", arXiv, Cornell University Library, DOI: arXiv:1910.13425, Oct. 2019. en_US
dc.identifier.uri https://arxiv.org/abs/1910.13425
dc.identifier.uri https://repository.iitgn.ac.in/handle/123456789/4942
dc.description.abstract 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.
dc.description.statementofresponsibility by Pratik Kayal, Mayank Singh and Pawan Goyal
dc.language.iso en_US en_US
dc.publisher Cornell University Library en_US
dc.subject Machine Learning (cs.LG) en_US
dc.subject Computation and Language (cs.CL) en_US
dc.subject Information Retrieval (cs.IR) en_US
dc.subject Machine Learning (stat.ML) en_US
dc.title Weakly-Supervised Deep Learning for Domain Invariant Sentiment Classification en_US
dc.type Pre-Print en_US
dc.relation.journal arXiv

Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


My Account