2018 · 51 citations · 40 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingGenerative ModelingLatent Variable ModelsMulti-task LearningSemi-supervised LearningSequence LabelingWord EmbeddingsConditional Probability ModelsGenerative Semi-supervised LearningHierarchical Latent Variable ModelsHierarchical Variational ModelsLatent Space ExplorationMultitask LearningSemi-supervised LabelingSemi-supervised Sequence Labeling
We introduce a family of multitask variational methods for semi-supervised sequence labeling. Our model family consists of a latentvariable generative model and a discriminative labeler. The generative models use latent variables to define the conditional probability of a word given its context, drawing inspiration from word prediction objectives commonly used in learning word embeddings. The labeler helps inject discriminative information into the latent space. We explore several latent variable configurations, including ones with hierarchical structure, which enables the model to account for both label-specific and word-specific information. Our models consistently outperform standard sequential baselines on 8 sequence labeling datasets, and improve further with unlabeled data.
40
Laurens van der Maaten, Geoffrey E. Hinton · Journal of Machine Learning Research · 2008 · 35.7K citations
Auto-Encoding Variational Bayes
Diederik P. Kingma, Max Welling · UvA-DARE (University of Amsterdam) · 2013 · 15.6K citations · Full text