Bayesian Inference for PCFGs via Markov Chain Monte Carlo
نویسندگان
چکیده
This paper presents two Markov chain Monte Carlo (MCMC) algorithms for Bayesian inference of probabilistic context free grammars (PCFGs) from terminal strings, providing an alternative to maximum-likelihood estimation using the Inside-Outside algorithm. We illustrate these methods by estimating a sparse grammar describing the morphology of the Bantu language Sesotho, demonstrating that with suitable priors Bayesian techniques can infer linguistic structure in situations where maximum likelihood methods such as the Inside-Outside algorithm only produce a trivial grammar.
منابع مشابه
Collapsed Variational Bayesian Inference for PCFGs
This paper presents a collapsed variational Bayesian inference algorithm for PCFGs that has the advantages of two dominant Bayesian training algorithms for PCFGs, namely variational Bayesian inference and Markov chain Monte Carlo. In three kinds of experiments, we illustrate that our algorithm achieves close performance to the Hastings sampling algorithm while using an order of magnitude less t...
متن کاملBayesian inference for statistical abduction using Markov chain Monte Carlo
Abduction is one of the basic logical inferences (deduction, induction and abduction) and derives the best explanations for our observation. Statistical abduction attempts to define a probability distribution over explanations and to evaluate them by their probabilities. The framework of statistical abduction is general since many well-known probabilistic models, i.e., BNs, HMMs and PCFGs, are ...
متن کاملA General MCMC Method for Bayesian Inference in Logic-Based Probabilistic Modeling
We propose a general MCMC method for Bayesian inference in logic-based probabilistic modeling. It covers a broad class of generative models including Bayesian networks and PCFGs. The idea is to generalize an MCMC method for PCFGs to the one for a Turing-complete probabilistic modeling language PRISM in the context of statistical abduction where parse trees are replaced with explanations. We des...
متن کاملRecent Advances in Semiparametric Bayesian Function Estimation
Common nonparametric curve tting methods such as spline smooth ing local polynomial regression and basis function approaches are now well devel oped and widely applied More recently Bayesian function estimation has become a useful supplementary or alternative tool for practical data analysis mainly due to breakthroughs in computerintensive inference via Markov chain Monte Carlo simulation This ...
متن کاملBayesian Markov Regime-Switching Models for Cointegration
This paper introduces a Bayesian Markov regime-switching model that allows the cointegration relationship between two time series to be switched on and off over time. Unlike classical approaches for testing and modeling cointegration, the Bayesian Markov switching method allows for estimation of the regime-specific model parameters via Markov Chain Monte Carlo and generates more reliable estima...
متن کامل