2018 · 11 citations · 27 references
ComputingComputer ScienceLinguisticsComputational LinguisticsMorphologyNatural Language ProcessingInflectional MorphologyLanguage ModelingMachine TranslationMorphological VariationVariational InferenceLanguage Model PretrainingMorphological LearningPosterior InferenceSemi-supervised Morphological AnalysisSemi-supervised Representation LearningStructured Variational InferenceVariational Bayesian Inference
Statistical morphological inflectors are typically trained on fully supervised, type-level data. One remaining open research question is the following: How can we effectively exploit raw, token-level data to improve their performance? To this end, we introduce a novel generative latent-variable model for the semi-supervised learning of inflection generation. To enable posterior inference over the latent variables, we derive an efficient variational inference procedure based on the wake-sleep algorithm. We experiment on 23 languages, using the Universal Dependencies corpora in a simulated low-resource setting, and find improvements of over 10% absolute accuracy in some cases.
27
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
Auto-Encoding Variational Bayes
Diederik P. Kingma, Max Welling · UvA-DARE (University of Amsterdam) · 2013 · 15.6K citations · Full text
Sequence to Sequence Learning with Neural Networks
Ilya Sutskever, Oriol Vinyals, Quoc V. Le · arXiv (Cornell University) · 2014 · 13.4K citations · Full text
Computing, Computer Science, French +14