Information extraction (IE) is the technique for transforming unstructured textual data into structured representation that can be understood by machines. The exponential growth of the Web generates an exceptional quantity of data for which automatic knowledge capture is essential. This work describes the methodology for web scale information extraction in the LODIE project (linked open data information extraction) and highlights results from the early experiments carried out in the initial phase of the project. LODIE aims to develop information extraction techniques able to scale at web level and adapt to user information needs. The core idea behind LODIE is the usage of linked open data, a very large-scale information resource, as a ground-breaking solution for IE, which provides invaluable annotated data on a growing number of domains. This article has two objectives. First, describing the LODIE project as a whole and depicting its general challenges and directions. Second, describing some initial steps taken towards the general solution, focusing on a specific IE subtask, wrapper induction.

We discuss the nature of big data and address the role of semantics in analyzing and processing big data that arises in the context of physical-cyber-social systems. To handle volume, we advocate semantic perception that can convert low-level observational data to higher-level abstractions more suitable for decision-making. To handle variety, we resort to semantic models and annotations of data so that intelligent processing can be done independent of heterogeneity of data formats and media. To handle velocity, we seek to use continuous semantics capability to dynamically create event or situation specific models and recognize relevant new concepts, entities and facts. To handle veracity, we explore trust models and approaches to glean trustworthiness. These four v's of big data are harnessed by the semantics-empowered analytics to derive value to support applications transcending physical-cyber-social continuum.

While catchphrases such as big data, smart data, data-intensive science, or smart dust highlight different aspects, they share a common theme: Namely, a shift towards a data-centric perspective in which the synthesis and analysis of data at an ever-increasing spatial, temporal, and thematic resolution promises new insights, while, at the same time, reducing the need for strong domain theories as starting points. In terms of the envisioned methodologies, those catchphrases tend to emphasize the role of predictive analytics, that is, statistical techniques including data mining and machine learning, as well as supercomputing. Interestingly, however, while this perspective takes the availability of data as a given, it does not answer the question how one would discover the required data in today’s chaotic information universe, how one would understand which datasets can be meaningfully integrated, and how to communicate the results to humans and machines alike. The semantic web addresses these questions. In the following, we argue why the data train needs semantic rails. We point out that making sense of data and gaining new insights works best if inductive and deductive techniques go hand-in-hand instead of competing over the prerogative of interpretation.

Call Detail Records (CDRs) are data recorded by telecommunications companies, consisting of basic informations related to several dimensions of the calls made through the network: the source, destination, date and time of calls. CDRs data analysis has received much attention in the recent years since it might reveal valuable information about human behavior. It has shown high added value in many application domains like e.g., communities analysis or network planning. In this paper, we suggest a generic methodology for summarizing information contained in CDRs data. The method is based on a parameter-free estimation of the joint distribution of the variables that describe the calls. We also suggest several well-founded criteria that allows one to browse the summary at various granularities and to explore the summary by means of insightful visualizations. The method handles network graph data, temporal sequence data as well as user mobility data stemming from original CDRs data. We show the relevance of our methodology for various case studies on real-world CDRs data from Ivory Coast.

This work deals with parallel optimization of expensive objective functions which are modeled as sample realizations of Gaussian processes. The study is formalized as a Bayesian optimization problem, or continuous multi-armed bandit problem, where a batch of q \textgreater{} 0 arms is pulled in parallel at each iteration. Several algorithms have been developed for choosing batches by trading off exploitation and exploration. As of today, the maximum Expected Improvement (EI) and Upper Confidence Bound (UCB) selection rules appear as the most prominent approaches for batch selection. Here, we build upon recent work on the multipoint Expected Improvement criterion, for which an analytic expansion relying on Tallis' formula was recently established. The computational burden of this selection rule being still an issue in application, we derive a closed-form expression for the gradient of the multipoint Expected Improvement, which aims at facilitating its maximization using gradient-based ascent algorithms. Substantial computational savings are shown in application. In addition, our algorithms are tested numerically and compared to state-of-the-art UCB-based batch-sequential algorithms. Combining starting designs relying on UCB with gradient-based EI local optimization finally appears as a sound option for batch design in distributed Gaussian Process optimization.

Estimation of response functions is an important task in dynamic medical imaging. This task arises for example in dynamic renal scintigraphy, where impulse response or retention functions are estimated, or in functional magnetic resonance imaging where hemodynamic response functions are required. These functions can not be observed directly and their estimation is complicated because the recorded images are subject to superposition of underlying signals. Therefore, the response functions are estimated via blind source separation and deconvolution. Performance of this algorithm heavily depends on the used models of the response functions. Response functions in real image sequences are rather complicated and finding a suitable parametric form is problematic. In this paper, we study estimation of the response functions using non-parametric Bayesian priors. These priors were designed to favor desirable properties of the functions, such as sparsity or smoothness. These assumptions are used within hierarchical priors of the blind source separation and deconvolution algorithm. Comparison of the resulting algorithms with these priors is performed on synthetic dataset as well as on real datasets from dynamic renal scintigraphy. It is shown that flexible non-parametric priors improve estimation of response functions in both cases. MATLAB implementation of the resulting algorithms is freely available for download.

This paper presents a novel approach to speaker subspace modelling based on Gaussian-Binary Restricted Boltzmann Machines (GRBM). The proposed model is based on the idea of shared factors as in the Probabilistic Linear Discriminant Analysis (PLDA). GRBM hidden layer is divided into speaker and channel factors, herein the speaker factor is shared over all vectors of the speaker. Then Maximum Likelihood Parameter Estimation (MLE) for proposed model is introduced. Various new scoring techniques for speaker verification using GRBM are proposed. The results for NIST i-vector Challenge 2014 dataset are presented.

This works extends the Random Embedding Bayesian Optimization approach by integrating a warping of the high dimensional subspace within the covariance kernel. The proposed warping, that relies on elementary geometric considerations, allows mitigating the drawbacks of the high extrinsic dimensionality while avoiding the algorithm to evaluate points giving redundant information. It also alleviates constraints on bound selection for the embedded domain, thus improving the robustness, as illustrated with a test case with 25 variables and intrinsic dimension 6.

In many sequential decision-making problems we may want to manage risk by minimizing some measure of variability in rewards in addition to maximizing a standard criterion. Variance related risk measures are among the most common risk-sensitive criteria in finance and operations research. However, optimizing many such criteria is known to be a hard problem. In this paper, we consider both discounted and average reward Markov decision processes. For each formulation, we first define a measure of variability for a policy, which in turn gives us a set of risk-sensitive criteria to optimize. For each of these criteria, we derive a formula for computing its gradient. We then devise actor-critic algorithms that operate on three timescales - a TD critic on the fastest timescale, a policy gradient (actor) on the intermediate timescale, and a dual ascent for Lagrange multipliers on the slowest timescale. In the discounted setting, we point out the difficulty in estimating the gradient of the variance of the return and incorporate simultaneous perturbation approaches to alleviate this. The average setting, on the other hand, allows for an actor update using compatible features to estimate the gradient of the variance. We establish the convergence of our algorithms to locally risk-sensitive optimal policies. Finally, we demonstrate the usefulness of our algorithms in a traffic signal control application.

Complex operational environments require improved tactical mission command capabilities with a high level of interoperability among coalition control and command (C2) systems. This paper focuses on two areas of interest: decision support based on automated planning and Service Oriented Architecture (SOA) for rapid service development. Previous experiments were performed bilaterally by US, France and Germany to focus on collaborative mission planning using Web Services (WSs). The results reported herein were obtained from a unified experiment performed by US, France and Germany involving a common scenario. The operational benefit from the experimentation has been to improve mutual understanding among allied forces, to dynamically plan for assistance among ground support troops (logistics, MEDE- VAC, and other areas) as well as to improve their coordination. The effort addressed system design, and integration within an experimental framework. It enabled the evolution of the CERDEC Mission Command Gateway (MCG) architecture as well as a constraint based planner ”ORTAC”, developed by French DGA and Sagem. It takes into account near real-time multimodal Situation Awareness and readiness status from tactical edge units. The trilateral experiment, entitled From Data to Decision included Net-Centric manned and unmanned assets from all three nations (France - Germany - US) operating as a cohesive coalition force while preserving command and support relationships as required through their respective chains of command.