Paper Group ANR 250
Readability-based Sentence Ranking for Evaluating Text Simplification. Fast and Effective Algorithms for Symmetric Nonnegative Matrix Factorization. Effective Multi-step Temporal-Difference Learning for Non-Linear Function Approximation. Texture analysis using deterministic partially self-avoiding walk with thresholds. TF.Learn: TensorFlow’s High-l …
Readability-based Sentence Ranking for Evaluating Text Simplification
| Title | Readability-based Sentence Ranking for Evaluating Text Simplification |
| Authors | Sowmya Vajjala, Detmar Meurers |
| Abstract | We propose a new method for evaluating the readability of simplified sentences through pair-wise ranking. The validity of the method is established through in-corpus and cross-corpus evaluation experiments. The approach correctly identifies the ranking of simplified and unsimplified sentences in terms of their reading level with an accuracy of over 80%, significantly outperforming previous results. To gain qualitative insights into the nature of simplification at the sentence level, we studied the impact of specific linguistic features. We empirically confirm that both word-level and syntactic features play a role in comparing the degree of simplification of authentic data. To carry out this research, we created a new sentence-aligned corpus from professionally simplified news articles. The new corpus resource enriches the empirical basis of sentence-level simplification research, which so far relied on a single resource. Most importantly, it facilitates cross-corpus evaluation for simplification, a key step towards generalizable results. |
| Tasks | Text Simplification |
| Published | 2016-03-18 |
| URL | http://arxiv.org/abs/1603.06009v1 |
| http://arxiv.org/pdf/1603.06009v1.pdf | |
| PWC | https://paperswithcode.com/paper/readability-based-sentence-ranking-for |
| Repo | |
| Framework | |
Fast and Effective Algorithms for Symmetric Nonnegative Matrix Factorization
| Title | Fast and Effective Algorithms for Symmetric Nonnegative Matrix Factorization |
| Authors | Reza Borhani, Jeremy Watt, Aggelos Katsaggelos |
| Abstract | Symmetric Nonnegative Matrix Factorization (SNMF) models arise naturally as simple reformulations of many standard clustering algorithms including the popular spectral clustering method. Recent work has demonstrated that an elementary instance of SNMF provides superior clustering quality compared to many classic clustering algorithms on a variety of synthetic and real world data sets. In this work, we present novel reformulations of this instance of SNMF based on the notion of variable splitting and produce two fast and effective algorithms for its optimization using i) the provably convergent Accelerated Proximal Gradient (APG) procedure and ii) a heuristic version of the Alternating Direction Method of Multipliers (ADMM) framework. Our two algorithms present an interesting tradeoff between computational speed and mathematical convergence guarantee: while the former method is provably convergent it is considerably slower than the latter approach, for which we also provide significant but less stringent mathematical proof regarding its convergence. Through extensive experiments we show not only that the efficacy of these approaches is equal to that of the state of the art SNMF algorithm, but also that the latter of our algorithms is extremely fast being one to two orders of magnitude faster in terms of total computation time than the state of the art approach, outperforming even spectral clustering in terms of computation time on large data sets. |
| Tasks | |
| Published | 2016-09-17 |
| URL | http://arxiv.org/abs/1609.05342v1 |
| http://arxiv.org/pdf/1609.05342v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-effective-algorithms-for-symmetric |
| Repo | |
| Framework | |
Effective Multi-step Temporal-Difference Learning for Non-Linear Function Approximation
| Title | Effective Multi-step Temporal-Difference Learning for Non-Linear Function Approximation |
| Authors | Harm van Seijen |
| Abstract | Multi-step temporal-difference (TD) learning, where the update targets contain information from multiple time steps ahead, is one of the most popular forms of TD learning for linear function approximation. The reason is that multi-step methods often yield substantially better performance than their single-step counter-parts, due to a lower bias of the update targets. For non-linear function approximation, however, single-step methods appear to be the norm. Part of the reason could be that on many domains the popular multi-step methods TD($\lambda$) and Sarsa($\lambda$) do not perform well when combined with non-linear function approximation. In particular, they are very susceptible to divergence of value estimates. In this paper, we identify the reason behind this. Furthermore, based on our analysis, we propose a new multi-step TD method for non-linear function approximation that addresses this issue. We confirm the effectiveness of our method using two benchmark tasks with neural networks as function approximation. |
| Tasks | |
| Published | 2016-08-18 |
| URL | http://arxiv.org/abs/1608.05151v1 |
| http://arxiv.org/pdf/1608.05151v1.pdf | |
| PWC | https://paperswithcode.com/paper/effective-multi-step-temporal-difference |
| Repo | |
| Framework | |
Texture analysis using deterministic partially self-avoiding walk with thresholds
| Title | Texture analysis using deterministic partially self-avoiding walk with thresholds |
| Authors | Lucas Correia Ribas, Wesley Nunes Gonçalves, Odemir Martinez Bruno |
| Abstract | In this paper, we propose a new texture analysis method using the deterministic partially self-avoiding walk performed on maps modified with thresholds. In this method, two pixels of the map are neighbors if the Euclidean distance between them is less than $\sqrt{2}$ and the weight (difference between its intensities) is less than a given threshold. The maps obtained by using different thresholds highlight several properties of the image that are extracted by the deterministic walk. To compose the feature vector, deterministic walks are performed with different thresholds and its statistics are concatenated. Thus, this approach can be considered as a multi-scale analysis. We validate our method on the Brodatz database, which is very well known public image database and widely used by texture analysis methods. Experimental results indicate that the proposed method presents a good texture discrimination, overcoming traditional texture methods. |
| Tasks | Texture Classification |
| Published | 2016-11-25 |
| URL | http://arxiv.org/abs/1611.08629v1 |
| http://arxiv.org/pdf/1611.08629v1.pdf | |
| PWC | https://paperswithcode.com/paper/texture-analysis-using-deterministic |
| Repo | |
| Framework | |
TF.Learn: TensorFlow’s High-level Module for Distributed Machine Learning
| Title | TF.Learn: TensorFlow’s High-level Module for Distributed Machine Learning |
| Authors | Yuan Tang |
| Abstract | TF.Learn is a high-level Python module for distributed machine learning inside TensorFlow. It provides an easy-to-use Scikit-learn style interface to simplify the process of creating, configuring, training, evaluating, and experimenting a machine learning model. TF.Learn integrates a wide range of state-of-art machine learning algorithms built on top of TensorFlow’s low level APIs for small to large-scale supervised and unsupervised problems. This module focuses on bringing machine learning to non-specialists using a general-purpose high-level language as well as researchers who want to implement, benchmark, and compare their new methods in a structured environment. Emphasis is put on ease of use, performance, documentation, and API consistency. |
| Tasks | |
| Published | 2016-12-13 |
| URL | http://arxiv.org/abs/1612.04251v1 |
| http://arxiv.org/pdf/1612.04251v1.pdf | |
| PWC | https://paperswithcode.com/paper/tflearn-tensorflows-high-level-module-for |
| Repo | |
| Framework | |
Global analysis of Expectation Maximization for mixtures of two Gaussians
| Title | Global analysis of Expectation Maximization for mixtures of two Gaussians |
| Authors | Ji Xu, Daniel Hsu, Arian Maleki |
| Abstract | Expectation Maximization (EM) is among the most popular algorithms for estimating parameters of statistical models. However, EM, which is an iterative algorithm based on the maximum likelihood principle, is generally only guaranteed to find stationary points of the likelihood objective, and these points may be far from any maximizer. This article addresses this disconnect between the statistical principles behind EM and its algorithmic properties. Specifically, it provides a global analysis of EM for specific models in which the observations comprise an i.i.d. sample from a mixture of two Gaussians. This is achieved by (i) studying the sequence of parameters from idealized execution of EM in the infinite sample limit, and fully characterizing the limit points of the sequence in terms of the initial parameters; and then (ii) based on this convergence analysis, establishing statistical consistency (or lack thereof) for the actual sequence of parameters produced by EM. |
| Tasks | |
| Published | 2016-08-26 |
| URL | http://arxiv.org/abs/1608.07630v1 |
| http://arxiv.org/pdf/1608.07630v1.pdf | |
| PWC | https://paperswithcode.com/paper/global-analysis-of-expectation-maximization |
| Repo | |
| Framework | |
Discrete Schroedinger Transform For Texture Recognition
| Title | Discrete Schroedinger Transform For Texture Recognition |
| Authors | João B. Florindo, Odemir M. Bruno |
| Abstract | This work presents a new procedure to extract features of grey-level texture images based on the discrete Schroedinger transform. This is a non-linear transform where the image is mapped as the initial probability distribution of a wave function and such distribution evolves in time following the Schroedinger equation from Quantum Mechanics. The features are provided by statistical moments of the distribution measured at different times. The proposed method is applied to the classification of three databases of textures used for benchmark and compared to other well-known texture descriptors in the literature, such as textons, local binary patterns, multifractals, among others. All of them are outperformed by the proposed method in terms of percentage of images correctly classified. The proposal is also applied to the identification of plant species using scanned images of leaves and again it outperforms other texture methods. A test with images affected by Gaussian and “salt & pepper” noise is also carried out, also with the best performance achieved by the Schroedinger descriptors. |
| Tasks | |
| Published | 2016-12-08 |
| URL | http://arxiv.org/abs/1612.02498v1 |
| http://arxiv.org/pdf/1612.02498v1.pdf | |
| PWC | https://paperswithcode.com/paper/discrete-schroedinger-transform-for-texture |
| Repo | |
| Framework | |
Greedy Criterion in Orthogonal Greedy Learning
| Title | Greedy Criterion in Orthogonal Greedy Learning |
| Authors | Lin Xu, Shaobo Lin, Jinshan Zeng, Xia Liu, Zongben Xu |
| Abstract | Orthogonal greedy learning (OGL) is a stepwise learning scheme that starts with selecting a new atom from a specified dictionary via the steepest gradient descent (SGD) and then builds the estimator through orthogonal projection. In this paper, we find that SGD is not the unique greedy criterion and introduce a new greedy criterion, called “$\delta$-greedy threshold” for learning. Based on the new greedy criterion, we derive an adaptive termination rule for OGL. Our theoretical study shows that the new learning scheme can achieve the existing (almost) optimal learning rate of OGL. Plenty of numerical experiments are provided to support that the new scheme can achieve almost optimal generalization performance, while requiring less computation than OGL. |
| Tasks | |
| Published | 2016-04-20 |
| URL | http://arxiv.org/abs/1604.05993v1 |
| http://arxiv.org/pdf/1604.05993v1.pdf | |
| PWC | https://paperswithcode.com/paper/greedy-criterion-in-orthogonal-greedy |
| Repo | |
| Framework | |
Constrained Maximum Correntropy Adaptive Filtering
| Title | Constrained Maximum Correntropy Adaptive Filtering |
| Authors | Siyuan Peng, Badong Chen, Lei Sun, Zhiping Lin, Wee Ser |
| Abstract | Constrained adaptive filtering algorithms inculding constrained least mean square (CLMS), constrained affine projection (CAP) and constrained recursive least squares (CRLS) have been extensively studied in many applications. Most existing constrained adaptive filtering algorithms are developed under mean square error (MSE) criterion, which is an ideal optimality criterion under Gaussian noises. This assumption however fails to model the behavior of non-Gaussian noises found in practice. Motivated by the robustness and simplicity of maximum correntropy criterion (MCC) in non-Gaussian impulsive noises, this paper proposes a new adaptive filtering algorithm called constrained maximum correntropy criterion (CMCC). Specifically, CMCC incorporates a linear constraint into a MCC filter to solve a constrained optimization problem explicitly. The proposed adaptive filtering algorithm is easy to implement and has low computational complexity, and in terms of convergence accuracy (say lower mean square deviation) and stability, can significantly outperform those MSE based constrained adaptive algorithms in presence of heavy-tailed impulsive noises. Additionally, the mean square convergence behaviors are studied under energy conservation relation, and a sufficient condition to ensure the mean square convergence and the steady-state mean square deviation (MSD) of the proposed algorithm are obtained. Simulation results confirm the theoretical predictions under both Gaussian and non- Gaussian noises, and demonstrate the excellent performance of the novel algorithm by comparing it with other conventional methods. |
| Tasks | |
| Published | 2016-10-06 |
| URL | http://arxiv.org/abs/1610.01766v2 |
| http://arxiv.org/pdf/1610.01766v2.pdf | |
| PWC | https://paperswithcode.com/paper/constrained-maximum-correntropy-adaptive |
| Repo | |
| Framework | |
Fixed-point Factorized Networks
| Title | Fixed-point Factorized Networks |
| Authors | Peisong Wang, Jian Cheng |
| Abstract | In recent years, Deep Neural Networks (DNN) based methods have achieved remarkable performance in a wide range of tasks and have been among the most powerful and widely used techniques in computer vision. However, DNN-based methods are both computational-intensive and resource-consuming, which hinders the application of these methods on embedded systems like smart phones. To alleviate this problem, we introduce a novel Fixed-point Factorized Networks (FFN) for pretrained models to reduce the computational complexity as well as the storage requirement of networks. The resulting networks have only weights of -1, 0 and 1, which significantly eliminates the most resource-consuming multiply-accumulate operations (MACs). Extensive experiments on large-scale ImageNet classification task show the proposed FFN only requires one-thousandth of multiply operations with comparable accuracy. |
| Tasks | |
| Published | 2016-11-07 |
| URL | http://arxiv.org/abs/1611.01972v2 |
| http://arxiv.org/pdf/1611.01972v2.pdf | |
| PWC | https://paperswithcode.com/paper/fixed-point-factorized-networks |
| Repo | |
| Framework | |
Exclusivity Regularized Machine
| Title | Exclusivity Regularized Machine |
| Authors | Xiaojie Guo |
| Abstract | It has been recognized that the diversity of base learners is of utmost importance to a good ensemble. This paper defines a novel measurement of diversity, termed as exclusivity. With the designed exclusivity, we further propose an ensemble model, namely Exclusivity Regularized Machine (ERM), to jointly suppress the training error of ensemble and enhance the diversity between bases. Moreover, an Augmented Lagrange Multiplier based algorithm is customized to effectively and efficiently seek the optimal solution of ERM. Theoretical analysis on convergence and global optimality of the proposed algorithm, as well as experiments are provided to reveal the efficacy of our method and show its superiority over state-of-the-art alternatives in terms of accuracy and efficiency. |
| Tasks | |
| Published | 2016-03-28 |
| URL | http://arxiv.org/abs/1603.08318v2 |
| http://arxiv.org/pdf/1603.08318v2.pdf | |
| PWC | https://paperswithcode.com/paper/exclusivity-regularized-machine |
| Repo | |
| Framework | |
ASP for Minimal Entailment in a Rational Extension of SROEL
| Title | ASP for Minimal Entailment in a Rational Extension of SROEL |
| Authors | Laura Giordano, Daniele Theseider Dupré |
| Abstract | In this paper we exploit Answer Set Programming (ASP) for reasoning in a rational extension SROEL-R-T of the low complexity description logic SROEL, which underlies the OWL EL ontology language. In the extended language, a typicality operator T is allowed to define concepts T(C) (typical C’s) under a rational semantics. It has been proven that instance checking under rational entailment has a polynomial complexity. To strengthen rational entailment, in this paper we consider a minimal model semantics. We show that, for arbitrary SROEL-R-T knowledge bases, instance checking under minimal entailment is \Pi^P_2-complete. Relying on a Small Model result, where models correspond to answer sets of a suitable ASP encoding, we exploit Answer Set Preferences (and, in particular, the asprin framework) for reasoning under minimal entailment. The paper is under consideration for acceptance in Theory and Practice of Logic Programming. |
| Tasks | |
| Published | 2016-08-08 |
| URL | http://arxiv.org/abs/1608.02450v1 |
| http://arxiv.org/pdf/1608.02450v1.pdf | |
| PWC | https://paperswithcode.com/paper/asp-for-minimal-entailment-in-a-rational |
| Repo | |
| Framework | |
Fully-Trainable Deep Matching
| Title | Fully-Trainable Deep Matching |
| Authors | James Thewlis, Shuai Zheng, Philip H. S. Torr, Andrea Vedaldi |
| Abstract | Deep Matching (DM) is a popular high-quality method for quasi-dense image matching. Despite its name, however, the original DM formulation does not yield a deep neural network that can be trained end-to-end via backpropagation. In this paper, we remove this limitation by rewriting the complete DM algorithm as a convolutional neural network. This results in a novel deep architecture for image matching that involves a number of new layer types and that, similar to recent networks for image segmentation, has a U-topology. We demonstrate the utility of the approach by improving the performance of DM by learning it end-to-end on an image matching task. |
| Tasks | Semantic Segmentation |
| Published | 2016-09-12 |
| URL | http://arxiv.org/abs/1609.03532v1 |
| http://arxiv.org/pdf/1609.03532v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-trainable-deep-matching |
| Repo | |
| Framework | |
La representación de la variación contextual mediante definiciones terminológicas flexibles
| Title | La representación de la variación contextual mediante definiciones terminológicas flexibles |
| Authors | Antonio San Martín |
| Abstract | In this doctoral thesis, we apply premises of cognitive linguistics to terminological definitions and present a proposal called the flexible terminological definition. This consists of a set of definitions of the same concept made up of a general definition (in this case, one encompassing the entire environmental domain) along with additional definitions describing the concept from the perspective of the subdomains in which it is relevant. Since context is a determining factor in the construction of the meaning of lexical units (including terms), we assume that terminological definitions can, and should, reflect the effects of context, even though definitions have traditionally been treated as the expression of meaning void of any contextual effect. The main objective of this thesis is to analyze the effects of contextual variation on specialized environmental concepts with a view to their representation in terminological definitions. Specifically, we focused on contextual variation based on thematic restrictions. To accomplish the objectives of this doctoral thesis, we conducted an empirical study consisting of the analysis of a set of contextually variable concepts and the creation of a flexible definition for two of them. As a result of the first part of our empirical study, we divided our notion of domain-dependent contextual variation into three different phenomena: modulation, perspectivization and subconceptualization. These phenomena are additive in that all concepts experience modulation, some concepts also undergo perspectivization, and finally, a small number of concepts are additionally subjected to subconceptualization. In the second part, we applied these notions to terminological definitions and we presented we presented guidelines on how to build flexible definitions, from the extraction of knowledge to the actual writing of the definition. |
| Tasks | |
| Published | 2016-06-01 |
| URL | http://arxiv.org/abs/1607.06330v1 |
| http://arxiv.org/pdf/1607.06330v1.pdf | |
| PWC | https://paperswithcode.com/paper/la-representacion-de-la-variacion-contextual |
| Repo | |
| Framework | |
Learning Action Maps of Large Environments via First-Person Vision
| Title | Learning Action Maps of Large Environments via First-Person Vision |
| Authors | Nicholas Rhinehart, Kris M. Kitani |
| Abstract | When people observe and interact with physical spaces, they are able to associate functionality to regions in the environment. Our goal is to automate dense functional understanding of large spaces by leveraging sparse activity demonstrations recorded from an ego-centric viewpoint. The method we describe enables functionality estimation in large scenes where people have behaved, as well as novel scenes where no behaviors are observed. Our method learns and predicts “Action Maps”, which encode the ability for a user to perform activities at various locations. With the usage of an egocentric camera to observe human activities, our method scales with the size of the scene without the need for mounting multiple static surveillance cameras and is well-suited to the task of observing activities up-close. We demonstrate that by capturing appearance-based attributes of the environment and associating these attributes with activity demonstrations, our proposed mathematical framework allows for the prediction of Action Maps in new environments. Additionally, we offer a preliminary glance of the applicability of Action Maps by demonstrating a proof-of-concept application in which they are used in concert with activity detections to perform localization. |
| Tasks | |
| Published | 2016-05-05 |
| URL | http://arxiv.org/abs/1605.01679v1 |
| http://arxiv.org/pdf/1605.01679v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-action-maps-of-large-environments |
| Repo | |
| Framework | |
