The paper describes a method of relation extraction, which is based on parsing the input text using a combination of a generic HPSG-based grammar and a highly focused domain- and relation-specific lexicon. We also show a method of unsupervised acquisition of such a lexicon from a large unlabeled corpus. Together, the methods introduce a novel approach to the “Open IE” task, which is superior in accuracy and in quality of relation identification to the existing approaches.

The paper describes a method of relation extraction, which is based on parsing the input text using a combination of a generic HPSG-based grammar and a highly focused domain- and relation-specific lexicon. We also show a method of unsupervised acquisition of such a lexicon from a large unlabeled corpus. Together, the methods introduce a novel approach to the “Open IE” task, which is superior in accuracy and in quality of relation identification to the existing approaches.

The paper describes a method of relation extraction, which is based on parsing the input text using a combination of a generic HPSG-based grammar and a highly focused domain- and relation-specific lexicon. We also show a method of unsupervised acquisition of such a lexicon from a large unlabeled corpus. Together, the methods introduce a novel approach to the “Open IE” task, which is superior in accuracy and in quality of relation identification to the existing approaches.

The paper describes a method of relation extraction, which is based on parsing the input text using a combination of a generic HPSG-based grammar and a highly focused domain- and relation-specific lexicon. We also show a method of unsupervised acquisition of such a lexicon from a large unlabeled corpus. Together, the methods introduce a novel approach to the “Open IE” task, which is superior in accuracy and in quality of relation identification to the existing approaches.

With the availability of the huge amounts of data produced by current and future large multi-band photometric surveys, photometric redshifts have become a crucial tool for extragalactic astronomy and cosmology. In this paper we present a novel method, called Weak Gated Experts (WGE), which allows to derive photometric redshifts through a combination of data mining techniques. \noindent The WGE, like many other machine learning techniques, is based on the exploitation of a spectroscopic knowledge base composed by sources for which a spectroscopic value of the redshift is available. This method achieves a variance \sigma^2(\Delta z)=2.3x10^{-4} (\sigma^2(\Delta z) =0.08), where \Delta z = z_{phot} - z_{spec}) for the reconstruction of the photometric redshifts for the optical galaxies from the SDSS and for the optical quasars respectively, while the Root Mean Square (RMS) of the \Delta z variable distributions for the two experiments is respectively equal to 0.021 and 0.35. The WGE provides also a mechanism for the estimation of the accuracy of each photometric redshift. We also present and discuss the catalogs obtained for the optical SDSS galaxies, for the optical candidate quasars extracted from the DR7 SDSS photometric dataset {The sample of SDSS sources on which the accuracy of the reconstruction has been assessed is composed of bright sources, for a subset of which spectroscopic redshifts have been measured.}, and for optical SDSS candidate quasars observed by GALEX in the UV range. The WGE method exploits the new technological paradigm provided by the Virtual Observatory and the emerging field of Astroinformatics.

In this paper we develop a randomized block-coordinate descent method for minimizing the sum of a smooth and a simple nonsmooth block-separable convex function and prove that it obtains an $\epsilon$-accurate solution with probability at least $1-\rho$ in at most $O(\tfrac{n}{\epsilon} \log \tfrac{1}{\rho})$ iterations, where $n$ is the number of blocks. For strongly convex functions the method converges linearly. This extends recent results of Nesterov [Efficiency of coordinate descent methods on huge-scale optimization problems, CORE Discussion Paper #2010/2], which cover the smooth case, to composite minimization, while at the same time improving the complexity by the factor of 4 and removing $\epsilon$ from the logarithmic term. More importantly, in contrast with the aforementioned work in which the author achieves the results by applying the method to a regularized version of the objective function with an unknown scaling factor, we show that this is not necessary, thus achieving true iteration complexity bounds. In the smooth case we also allow for arbitrary probability vectors and non-Euclidean norms. Finally, we demonstrate numerically that the algorithm is able to solve huge-scale $\ell_1$-regularized least squares and support vector machine problems with a billion variables.

In this paper, we give a new sharp generalization bound of lp-MKL which is a generalized framework of multiple kernel learning (MKL) and imposes lp-mixed-norm regularization instead of l1-mixed-norm regularization. We utilize localization techniques to obtain the sharp learning rate. The bound is characterized by the decay rate of the eigenvalues of the associated kernels. A larger decay rate gives a faster convergence rate. Furthermore, we give the minimax learning rate on the ball characterized by lp-mixed-norm in the product space. Then we show that our derived learning rate of lp-MKL achieves the minimax optimal rate on the lp-mixed-norm ball.

We investigate the learning rate of multiple kernel leaning (MKL) with elastic-net regularization, which consists of an $\ell_1$-regularizer for inducing the sparsity and an $\ell_2$-regularizer for controlling the smoothness. We focus on a sparse setting where the total number of kernels is large but the number of non-zero components of the ground truth is relatively small, and prove that elastic-net MKL achieves the minimax learning rate on the $\ell_2$-mixed-norm ball. Our bound is sharper than the convergence rates ever shown, and has a property that the smoother the truth is, the faster the convergence rate is.

Purely data driven approaches for machine learning present difficulties when data is scarce relative to the complexity of the model or when the model is forced to extrapolate. On the other hand, purely mechanistic approaches need to identify and specify all the interactions in the problem at hand (which may not be feasible) and still leave the issue of how to parameterize the system. In this paper, we present a hybrid approach using Gaussian processes and differential equations to combine data driven modelling with a physical model of the system. We show how different, physically-inspired, kernel functions can be developed through sensible, simple, mechanistic assumptions about the underlying system. The versatility of our approach is illustrated with three case studies from motion capture, computational biology and geostatistics.

We investigate and evaluate methods for the characterization of social relations from textual communication context, using e-mail as an example. Social relations are intrinsically characterized by the Cartesian product of weights on various axes (we employ valuation and intensity as examples). The prediction of these characteristics is performed by application of unsupervised learning algorithms on meta-data, communication statistics, and the results of deep linguistic analysis of the message body. Classification of sentiment polarity is chosen as the means of linguistic analysis. We find that prediction accuracy can be improved by introducing limited amounts of additional information.