Better Exploiting Latent Variables in Text Modeling
We show that sampling latent variables multiple times at a gradient step helps in improving a variational autoencoder and propose a simple and effective method to better exploit these latent variables through hidden state averaging. Consistent gains in performance on two different datasets, Penn Treebank and Yahoo, indicate the generalizability of our method.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Hierarchical Bayesian image analysis: from low-level modeling to robust supervised learning
Within a supervised classification framework, labeled data are used to learn classifier parameters. Prior to that, it is generally required to perform dimensionality reduction via feature extraction. These preprocessing …
ClassificationClusteringDimensionality ReductionGeneral ClassificationA Hierarchical Latent Structure for Variational Conversation Modeling
Variational autoencoders (VAE) combined with hierarchical RNNs have emerged as a powerful framework for conversation modeling. However, they suffer from the notorious degeneration problem, where the decoders learn to ign…
Stock Movement Prediction from Tweets and Historical Prices
Stock movement prediction is a challenging problem: the market is highly stochastic, and we make temporally-dependent predictions from chaotic data. We treat these three complexities and present a novel deep generative m…
Feature EngineeringPredictionStock Market PredictionStock Trend Prediction+2Expanding variational autoencoders for learning and exploiting latent representations in search distributions
In the past, evolutionary algorithms (EAs) that use probabilistic modeling of the best solutions incorporated latent or hidden vari- ables to the models as a more accurate way to represent the search distributions. Recen…
Evolutionary AlgorithmsInducing Constituency Trees through Neural Machine Translation
Latent tree learning(LTL) methods learn to parse sentences using only indirect supervision from a downstream task. Recent advances in latent tree learning have made it possible to recover moderately high quality tree str…
Language ModelingLanguage ModellingMachine TranslationTranslation