Statistical user simulation with a hidden agenda

Recent work in the area of probabilistic user simulation for training statistical dialogue managers has investigated a new agenda-based user model and presented preliminary experiments with a handcrafted model parameter set. Training the model on dialogue data is an important next step, but non-trivial since the user agenda states are not observable in data and the space of possible states and state transitions is intractably large. This paper presents a summary-space mapping which greatly reduces the number of state transitions and introduces a tree-based method for representing the space of possible agenda state sequences. Treating the user agenda as a hidden variable, the forward/backward algorithm can then be successfully applied to iteratively estimate the model parameters on dialogue data. © 2007 Association for Computational Linguistics.

Statistical parametric speech synthesis based on speaker and language factorization

An increasingly common scenario in building speech synthesis and recognition systems is training on inhomogeneous data. This paper proposes a new framework for estimating hidden Markov models on data containing both multiple speakers and multiple languages. The proposed framework, speaker and language factorization, attempts to factorize speaker-/language-specific characteristics in the data and then model them using separate transforms. Language-specific factors in the data are represented by transforms based on cluster mean interpolation with cluster-dependent decision trees. Acoustic variations caused by speaker characteristics are handled by transforms based on constrained maximum-likelihood linear regression. Experimental results on statistical parametric speech synthesis show that the proposed framework enables data from multiple speakers in different languages to be used to: train a synthesis system; synthesize speech in a language using speaker characteristics estimated in a different language; and adapt to a new language. © 2012 IEEE.

An ngram-based statistical machine translation decoder

In this paper we describe MARIE, an Ngram-based statistical machine translation decoder. It is implemented using a beam search strategy, with distortion (or reordering) capabilities. The underlying translation model is based on an Ngram approach, extended to introduce reordering at the phrase level. The search graph structure is designed to perform very accurate comparisons, what allows for a high level of pruning, improving the decoder efficiency. We report several techniques for efficiently prune out the search space. The combinatory explosion of the search space derived from the search graph structure is reduced by limiting the number of reorderings a given translation is allowed to perform, and also the maximum distance a word (or a phrase) is allowed to be reordered. We finally report translation accuracy results on three different translation tasks.

Phrase linguistic classification and generalization for improving statistical machine translation

In this paper a method to incorporate linguistic information regarding single-word and compound verbs is proposed, as a first step towards an SMT model based on linguistically-classified phrases. By substituting these verb structures by the base form of the head verb, we achieve a better statistical word alignment performance, and are able to better estimate the translation model and generalize to unseen verb forms during translation. Preliminary experiments for the English - Spanish language pair are performed, and future research lines are detailed. © 2005 Association for Computational Linguistics.

A probabilistic energy model for non-domestic building sectors applied to analysis of school buildings in greater London

The diversity of non-domestic buildings at urban scale poses a number of difficulties to develop models for large scale analysis of the stock. This research proposes a probabilistic, engineering-based, bottom-up model to address these issues. In a recent study we classified London's non-domestic buildings based on the service they provide, such as offices, retail premise, and schools, and proposed the creation of one probabilistic representational model per building type. This paper investigates techniques for the development of such models. The representational model is a statistical surrogate of a dynamic energy simulation (ES) model. We first identify the main parameters affecting energy consumption in a particular building sector/type by using sampling-based global sensitivity analysis methods, and then generate statistical surrogate models of the dynamic ES model within the dominant model parameters. Given a sample of actual energy consumption for that sector, we use the surrogate model to infer the distribution of model parameters by inverse analysis. The inferred distributions of input parameters are able to quantify the relative benefits of alternative energy saving measures on an entire building sector with requisite quantification of uncertainties. Secondary school buildings are used for illustrating the application of this probabilistic method. © 2012 Elsevier B.V. All rights reserved.

A Stochastic Model for Electron Multiplication Charge-Coupled Devices - From Theory to Practice

Electron multiplication charge-coupled devices (EMCCD) are widely used for photon counting experiments and measurements of low intensity light sources, and are extensively employed in biological fluorescence imaging applications. These devices have a complex statistical behaviour that is often not fully considered in the analysis of EMCCD data. Robust and optimal analysis of EMCCD images requires an understanding of their noise properties, in particular to exploit fully the advantages of Bayesian and maximum-likelihood analysis techniques, whose value is increasingly recognised in biological imaging for obtaining robust quantitative measurements from challenging data. To improve our own EMCCD analysis and as an effort to aid that of the wider bioimaging community, we present, explain and discuss a detailed physical model for EMCCD noise properties, giving a likelihood function for image counts in each pixel for a given incident intensity, and we explain how to measure the parameters for this model from various calibration images. © 2013 Hirsch et al.

Statistical inference for single- and multi-band probabilistic amplitude demodulation.

Amplitude demodulation is an ill-posed problem and so it is natural to treat it from a Bayesian viewpoint, inferring the most likely carrier and envelope under probabilistic constraints. One such treatment is Probabilistic Amplitude Demodulation (PAD), which, whilst computationally more intensive than traditional approaches, offers several advantages. Here we provide methods for estimating the uncertainty in the PAD-derived envelopes and carriers, and for learning free-parameters like the time-scale of the envelope. We show how the probabilistic approach can naturally handle noisy and missing data. Finally, we indicate how to extend the model to signals which contain multiple modulators and carriers.

POMDP-based statistical spoken dialog systems: A review

Statistical dialog systems (SDSs) are motivated by the need for a data-driven framework that reduces the cost of laboriously handcrafting complex dialog managers and that provides robustness against the errors created by speech recognizers operating in noisy environments. By including an explicit Bayesian model of uncertainty and by optimizing the policy via a reward-driven process, partially observable Markov decision processes (POMDPs) provide such a framework. However, exact model representation and optimization is computationally intractable. Hence, the practical application of POMDP-based systems requires efficient algorithms and carefully constructed approximations. This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems. © 1963-2012 IEEE.

Active learning of model evidence using Bayesian quadrature

Numerical integration is a key component of many problems in scientific computing, statistical modelling, and machine learning. Bayesian Quadrature is a modelbased method for numerical integration which, relative to standard Monte Carlo methods, offers increased sample efficiency and a more robust estimate of the uncertainty in the estimated integral. We propose a novel Bayesian Quadrature approach for numerical integration when the integrand is non-negative, such as the case of computing the marginal likelihood, predictive distribution, or normalising constant of a probabilistic model. Our approach approximately marginalises the quadrature model's hyperparameters in closed form, and introduces an active learning scheme to optimally select function evaluations, as opposed to using Monte Carlo samples. We demonstrate our method on both a number of synthetic benchmarks and a real scientific problem from astronomy.

Classical two-site fidelity and quantum phase transitions in the Ising model and the extended Hubbard model

In this Letter, the classical two-site-ground-state fidelity (CTGF) is exploited to identify quantum phase transitions (QPTs) for the transverse field Ising model (TFIM) and the one-dimensional extended Hubbard model (EHM). Our results show that the CTGF exhibits an abrupt change around the regions of criticality and can be used to identify QPTs in spin and fermionic systems. The method is especially convenient when it is connected with the density-matrix renormalization group (DMRG) algorithm. (C) 2008 Elsevier B.V. All rights reserved.

A geometrical model of GaN morphology in initial growth stage

Based on morphology observed by atomic force microscopy, a geometrical model was proposed in order to explain the statistical results obtained from morphology observation on GaN in initial growth stage. Four parameters were introduced to describe the morphology characteristics in this model. Least-square fitting of height distribution was performed. The height distribution derived from the model agreed well with that obtained from experimental records. It was also found that the model should be further advanced to understand the growth of GaN in initial growth stage. (C) 2002 Elsevier Science BY. All rights reserved.

Biomimetic (topological) pattern recognition - A new model of pattern recognition theory and its application

A new theoretical model of Pattern Recognition principles was proposed, which is based on "matter cognition" instead of "matter classification" in traditional statistical Pattern Recognition. This new model is closer to the function of human being, rather than traditional statistical Pattern Recognition using "optimal separating" as its main principle. So the new model of Pattern Recognition is called the Biomimetic Pattern Recognition (BPR)(1). Its mathematical basis is placed on topological analysis of the sample set in the high dimensional feature space. Therefore, it is also called the Topological Pattern Recognition (TPR). The fundamental idea of this model is based on the fact of the continuity in the feature space of any one of the certain kinds of samples. We experimented with the Biomimetic Pattern Recognition (BPR) by using artificial neural networks, which act through covering the high dimensional geometrical distribution of the sample set in the feature space. Onmidirectionally cognitive tests were done on various kinds of animal and vehicle models of rather similar shapes. For the total 8800 tests, the correct recognition rate is 99.87%. The rejection rate is 0.13% and on the condition of zero error rates, the correct rate of BPR was much better than that of RBF-SVM.

Excitation and dissociation of tungsten hexacarbonyl W(CO)(6): Statistical and nonstatistical dissociation processes

We have studied the excitation and dissociation processes of the molecule W(CO)(6) in collisions with low kinetic energy (3 keV) protons, monocharged fluorine, and chlorine ions using double charge transfer spectroscopy. By analyzing the kinetic energy loss of the projectile anions, we measured the excitation energy distribution of the produced transient dications W(CO)(6)(2+). By coincidence measurements between the anions and the stable or fragments of W(CO)(6)(2+), we determined the energy distribution for each dissociation channel. Based on the experimental data, the emission of the first CO was tentatively attributed to a nonstatistical direct dissociation process and the emission of the second or more CO ligands was attributed to the statistical dissociation processes. The dissociation energies for the successive breaking of the W-CO bond were estimated using a cascade model. The ratio between charge separation and evaporation (by the loss of CO+ and CO, respectively) channels was estimated to be 6% in the case of Cl+ impact. (C) 2011 American Institute of Physics. [doi: 10.1063/1.3523347]