2010 · 109 citations · 18 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningNatural Language ProcessingActive LearningDeep LearningNeural NetworksSemi-supervised LearningSentiment AnalysisUnsupervised LearningActive Learning For ClassificationActive Learning With Deep Neural NetworksExponential LossRestricted Boltzmann MachinesSemi-supervised Active LearningSemi-supervised ClassificationSemi-supervised ModelsSentiment Classification
This paper presents a novel semi-supervised learning algorithm called Ac-tive Deep Networks (ADN), to address the semi-supervised sentiment classifica-tion problem with active learning. First, we propose the semi-supervised learning method of ADN. ADN is constructed by Restricted Boltzmann Machines (RBM) with unsupervised learning using labeled data and abundant of unlabeled data. Then the constructed structure is fine-tuned by gradient-descent based super-vised learning with an exponential loss function. Second, we apply active learn-ing in the semi-supervised learning framework to identify reviews that should be labeled as training data. Then ADN architecture is trained by the se-lected labeled data and all unlabeled data. Experiments on five sentiment classifica-tion datasets show that ADN outper-forms the semi-supervised learning algo-rithm and deep learning techniques ap-plied for sentiment classification. 1
18
A Fast Learning Algorithm for Deep Belief Nets
Geoffrey E. Hinton, Simon Osindero, Yee‐Whye Teh · Neural Computation · 2006 · 16.4K citations
Bo Pang, Lillian Lee, Shivakumar Vaithyanathan · 2002 · 7K citations · Full text
Semi-Supervised Learning Literature Survey
Xiaojin Zhu · Minds at UW (University of Wisconsin) · 2005 · 3.9K citations · Full text
Bo Pang, Lillian Lee · 2004 · 3.3K citations · Full text