Using Psuedolabels for training Sentiment Classifiers makes the model generalize better across datasets

TL;DR

This paper demonstrates that using pseudolabels generated from a small annotated dataset on large unannotated, multi-domain data improves the generalization of sentiment classifiers across different datasets.

Contribution

The work introduces a pseudolabeling approach that enhances cross-domain sentiment classification without extensive annotations from multiple domains.

Findings

Pseudolabel-based training improves cross-dataset performance

Method reduces need for extensive domain-specific annotations

Model generalizes better across diverse sentiment datasets

Abstract

The problem statement addressed in this work is : For a public sentiment classification API, how can we set up a classifier that works well on different types of data, having limited ability to annotate data from across domains. We show that given a large amount of unannotated data from across different domains and pseudolabels on this dataset generated by a classifier trained on a small annotated dataset from one domain, we can train a sentiment classifier that generalizes better across different datasets.