Shared Logistic Normal Distributions for Soft Parameter Tying in Unsupervised Grammar Induction
We present a family of priors over probabilistic grammar weights, called the shared logistic normal distribution. This family extends the partitioned logistic normal distribution, enabling factored covariance between the probabilities of different derivation events in the probabilistic grammar, providing a new way to encode prior knowledge about an unknown grammar. We describe a variational EM algorithm for learning a probabilistic grammar based on this family of priors. We then experiment with unsupervised dependency grammar induction and show significant improvements using our model for both monolingual learning and bilingual learning with a non-parallel, multilingual corpus.
Code (0)
등록된 구현이 없습니다.
Tasks
Dependency Grammar InductionUnsupervised Dependency ParsingSimilar Papers 제목 키워드 기반
An approximate closed formula for European Mortgage Options
The aim of this paper is to investigate the use of close formula approximation for pricing European mortgage options. Under the assumption of logistic duration and normal mortgage rates the underlying price at the option…
Bias and Coverage Properties of the WENDy-IRLS Algorithm
The Weak form Estimation of Nonlinear Dynamics (WENDy) method is a recently proposed class of parameter estimation algorithms that exhibits notable noise robustness and computational efficiency. This work examines the co…
Computational EfficiencyReducing normalizing flow complexity for MCMC preconditioning
Preconditioning is a key component of MCMC algorithms that improves sampling efficiency by facilitating exploration of geometrically complex target distributions through an invertible map. While linear preconditioners ar…
Stable Training of Normalizing Flows for High-dimensional Variational Inference
Variational inference with normalizing flows (NFs) is an increasingly popular alternative to MCMC methods. In particular, NFs based on coupling layers (Real NVPs) are frequently used due to their good empirical performan…
Variational InferenceA method to integrate and classify normal distributions
Univariate and multivariate normal probability distributions are widely used when modeling decisions under uncertainty. Computing the performance of such models requires integrating these distributions over specific doma…
Dimensionality Reduction