In this paper, we present an overview of generalized expectation criteria (GE), a simple, robust, scalable method for semi-supervised training using weakly-labeled data. GE fits m...
Many data mining applications have a large amount of data but labeling data is often difficult, expensive, or time consuming, as it requires human experts for annotation. Semi-supe...
Graph-based semi-supervised learning has recently emerged as a promising approach to data-sparse learning problems in natural language processing. All graph-based algorithms rely ...
We introduce a novel machine learning framework based on recursive autoencoders for sentence-level prediction of sentiment label distributions. Our method learns vector space repr...
Richard Socher, Jeffrey Pennington, Eric H. Huang,...