May 6, 2019

2785 words 14 mins read

Paper Group ANR 208

Coalition Formability Semantics with Conflict-Eliminable Sets of Arguments. The discriminative Kalman filter for nonlinear and non-Gaussian sequential Bayesian filtering. Counting Answer Sets via Dynamic Programming. A Character-Word Compositional Neural Language Model for Finnish. Multi-document abstractive summarization using ILP based multi-sent …

Coalition Formability Semantics with Conflict-Eliminable Sets of Arguments


Title	Coalition Formability Semantics with Conflict-Eliminable Sets of Arguments
Authors	Ryuta Arisaka, Ken Satoh
Abstract	We consider abstract-argumentation-theoretic coalition formability in this work. Taking a model from political alliance among political parties, we will contemplate profitability, and then formability, of a coalition. As is commonly understood, a group forms a coalition with another group for a greater good, the goodness measured against some criteria. As is also commonly understood, however, a coalition may deliver benefits to a group X at the sacrifice of something that X was able to do before coalition formation, which X may be no longer able to do under the coalition. Use of the typical conflict-free sets of arguments is not very fitting for accommodating this aspect of coalition, which prompts us to turn to a weaker notion, conflict-eliminability, as a property that a set of arguments should primarily satisfy. We require numerical quantification of attack strengths as well as of argument strengths for its characterisation. We will first analyse semantics of profitability of a given conflict-eliminable set forming a coalition with another conflict-eliminable set, and will then provide four coalition formability semantics, each of which formalises certain utility postulate(s) taking the coalition profitability into account.
Tasks	Abstract Argumentation
Published	2016-05-02
URL	http://arxiv.org/abs/1605.00495v2
PDF	http://arxiv.org/pdf/1605.00495v2.pdf
PWC	https://paperswithcode.com/paper/coalition-formability-semantics-with-conflict
Repo
Framework

The discriminative Kalman filter for nonlinear and non-Gaussian sequential Bayesian filtering


Title	The discriminative Kalman filter for nonlinear and non-Gaussian sequential Bayesian filtering
Authors	Michael C. Burkhart, David M. Brandman, Carlos E. Vargas-Irwin, Matthew T. Harrison
Abstract	The Kalman filter (KF) is used in a variety of applications for computing the posterior distribution of latent states in a state space model. The model requires a linear relationship between states and observations. Extensions to the Kalman filter have been proposed that incorporate linear approximations to nonlinear models, such as the extended Kalman filter (EKF) and the unscented Kalman filter (UKF). However, we argue that in cases where the dimensionality of observed variables greatly exceeds the dimensionality of state variables, a model for $p(\text{state}\text{observation})$ proves both easier to learn and more accurate for latent space estimation. We derive and validate what we call the discriminative Kalman filter (DKF): a closed-form discriminative version of Bayesian filtering that readily incorporates off-the-shelf discriminative learning techniques. Further, we demonstrate that given mild assumptions, highly non-linear models for $p(\text{state}\text{observation})$ can be specified. We motivate and validate on synthetic datasets and in neural decoding from non-human primates, showing substantial increases in decoding performance versus the standard Kalman filter.
Tasks
Published	2016-08-23
URL	http://arxiv.org/abs/1608.06622v2
PDF	http://arxiv.org/pdf/1608.06622v2.pdf
PWC	https://paperswithcode.com/paper/the-discriminative-kalman-filter-for
Repo
Framework

Counting Answer Sets via Dynamic Programming


Title	Counting Answer Sets via Dynamic Programming
Authors	Johannes Fichte, Markus Hecher, Michael Morak, Stefan Woltran
Abstract	While the solution counting problem for propositional satisfiability (#SAT) has received renewed attention in recent years, this research trend has not affected other AI solving paradigms like answer set programming (ASP). Although ASP solvers are designed to enumerate all solutions, and counting can therefore be easily done, the involved materialization of all solutions is a clear bottleneck for the counting problem of ASP (#ASP). In this paper we propose dynamic programming-based #ASP algorithms that exploit the structure of the underlying (ground) ASP program. Experimental results for a prototype implementation show promise when compared to existing solvers.
Tasks
Published	2016-12-22
URL	http://arxiv.org/abs/1612.07601v1
PDF	http://arxiv.org/pdf/1612.07601v1.pdf
PWC	https://paperswithcode.com/paper/counting-answer-sets-via-dynamic-programming
Repo
Framework

A Character-Word Compositional Neural Language Model for Finnish


Title	A Character-Word Compositional Neural Language Model for Finnish
Authors	Matti Lankinen, Hannes Heikinheimo, Pyry Takala, Tapani Raiko, Juha Karhunen
Abstract	Inspired by recent research, we explore ways to model the highly morphological Finnish language at the level of characters while maintaining the performance of word-level models. We propose a new Character-to-Word-to-Character (C2W2C) compositional language model that uses characters as input and output while still internally processing word level embeddings. Our preliminary experiments, using the Finnish Europarl V7 corpus, indicate that C2W2C can respond well to the challenges of morphologically rich languages such as high out of vocabulary rates, the prediction of novel words, and growing vocabulary size. Notably, the model is able to correctly score inflectional forms that are not present in the training data and sample grammatically and semantically correct Finnish sentences character by character.
Tasks	Language Modelling
Published	2016-12-10
URL	http://arxiv.org/abs/1612.03266v1
PDF	http://arxiv.org/pdf/1612.03266v1.pdf
PWC	https://paperswithcode.com/paper/a-character-word-compositional-neural
Repo
Framework

Multi-document abstractive summarization using ILP based multi-sentence compression


Title	Multi-document abstractive summarization using ILP based multi-sentence compression
Authors	Siddhartha Banerjee, Prasenjit Mitra, Kazunari Sugiyama
Abstract	Abstractive summarization is an ideal form of summarization since it can synthesize information from multiple documents to create concise informative summaries. In this work, we aim at developing an abstractive summarizer. First, our proposed approach identifies the most important document in the multi-document set. The sentences in the most important document are aligned to sentences in other documents to generate clusters of similar sentences. Second, we generate K-shortest paths from the sentences in each cluster using a word-graph structure. Finally, we select sentences from the set of shortest paths generated from all the clusters employing a novel integer linear programming (ILP) model with the objective of maximizing information content and readability of the final summary. Our ILP model represents the shortest paths as binary variables and considers the length of the path, information score and linguistic quality score in the objective function. Experimental results on the DUC 2004 and 2005 multi-document summarization datasets show that our proposed approach outperforms all the baselines and state-of-the-art extractive summarizers as measured by the ROUGE scores. Our method also outperforms a recent abstractive summarization technique. In manual evaluation, our approach also achieves promising results on informativeness and readability.
Tasks	Abstractive Text Summarization, Document Summarization, Multi-Document Summarization, Sentence Compression
Published	2016-09-22
URL	http://arxiv.org/abs/1609.07034v1
PDF	http://arxiv.org/pdf/1609.07034v1.pdf
PWC	https://paperswithcode.com/paper/multi-document-abstractive-summarization
Repo
Framework

Semi-Supervised Prediction of Gene Regulatory Networks Using Machine Learning Algorithms


Title	Semi-Supervised Prediction of Gene Regulatory Networks Using Machine Learning Algorithms
Authors	Nihir Patel, Jason T. L. Wang
Abstract	Use of computational methods to predict gene regulatory networks (GRNs) from gene expression data is a challenging task. Many studies have been conducted using unsupervised methods to fulfill the task; however, such methods usually yield low prediction accuracies due to the lack of training data. In this article, we propose semi-supervised methods for GRN prediction by utilizing two machine learning algorithms, namely support vector machines (SVM) and random forests (RF). The semi-supervised methods make use of unlabeled data for training. We investigate inductive and transductive learning approaches, both of which adopt an iterative procedure to obtain reliable negative training data from the unlabeled data. We then apply our semi-supervised methods to gene expression data of Escherichia coli and Saccharomyces cerevisiae, and evaluate the performance of our methods using the expression data. Our analysis indicated that the transductive learning approach outperformed the inductive learning approach for both organisms. However, there was no conclusive difference identified in the performance of SVM and RF. Experimental results also showed that the proposed semi-supervised methods performed better than existing supervised methods for both organisms.
Tasks
Published	2016-08-11
URL	http://arxiv.org/abs/1608.03530v1
PDF	http://arxiv.org/pdf/1608.03530v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-prediction-of-gene-regulatory
Repo
Framework

Subsampled online matrix factorization with convergence guarantees


Title	Subsampled online matrix factorization with convergence guarantees
Authors	Arthur Mensch, Julien Mairal, Gaël Varoquaux, Bertrand Thirion
Abstract	We present a matrix factorization algorithm that scales to input matrices that are large in both dimensions (i.e., that contains morethan 1TB of data). The algorithm streams the matrix columns while subsampling them, resulting in low complexity per iteration andreasonable memory footprint. In contrast to previous online matrix factorization methods, our approach relies on low-dimensional statistics from past iterates to control the extra variance introduced by subsampling. We present a convergence analysis that guarantees us to reach a stationary point of the problem. Large speed-ups can be obtained compared to previous online algorithms that do not perform subsampling, thanks to the feature redundancy that often exists in high-dimensional settings.
Tasks
Published	2016-11-30
URL	http://arxiv.org/abs/1611.10041v1
PDF	http://arxiv.org/pdf/1611.10041v1.pdf
PWC	https://paperswithcode.com/paper/subsampled-online-matrix-factorization-with
Repo
Framework

Depth Estimation Through a Generative Model of Light Field Synthesis


Title	Depth Estimation Through a Generative Model of Light Field Synthesis
Authors	Mehdi S. M. Sajjadi, Rolf Köhler, Bernhard Schölkopf, Michael Hirsch
Abstract	Light field photography captures rich structural information that may facilitate a number of traditional image processing and computer vision tasks. A crucial ingredient in such endeavors is accurate depth recovery. We present a novel framework that allows the recovery of a high quality continuous depth map from light field data. To this end we propose a generative model of a light field that is fully parametrized by its corresponding depth map. The model allows for the integration of powerful regularization techniques such as a non-local means prior, facilitating accurate depth map estimation.
Tasks	Depth Estimation
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01499v1
PDF	http://arxiv.org/pdf/1609.01499v1.pdf
PWC	https://paperswithcode.com/paper/depth-estimation-through-a-generative-model
Repo
Framework

Improving the Robustness of Deep Neural Networks via Stability Training


Title	Improving the Robustness of Deep Neural Networks via Stability Training
Authors	Stephan Zheng, Yang Song, Thomas Leung, Ian Goodfellow
Abstract	In this paper we address the issue of output instability of deep neural networks: small perturbations in the visual input can significantly distort the feature embeddings and output of a neural network. Such instability affects many deep architectures with state-of-the-art performance on a wide range of computer vision tasks. We present a general stability training method to stabilize deep networks against small input distortions that result from various types of common image processing, such as compression, rescaling, and cropping. We validate our method by stabilizing the state-of-the-art Inception architecture against these types of distortions. In addition, we demonstrate that our stabilized model gives robust state-of-the-art performance on large-scale near-duplicate detection, similar-image ranking, and classification on noisy datasets.
Tasks
Published	2016-04-15
URL	http://arxiv.org/abs/1604.04326v1
PDF	http://arxiv.org/pdf/1604.04326v1.pdf
PWC	https://paperswithcode.com/paper/improving-the-robustness-of-deep-neural
Repo
Framework

Learning Image Matching by Simply Watching Video


Title	Learning Image Matching by Simply Watching Video
Authors	Gucan Long, Laurent Kneip, Jose M. Alvarez, Hongdong Li
Abstract	This work presents an unsupervised learning based approach to the ubiquitous computer vision problem of image matching. We start from the insight that the problem of frame-interpolation implicitly solves for inter-frame correspondences. This permits the application of analysis-by-synthesis: we firstly train and apply a Convolutional Neural Network for frame-interpolation, then obtain correspondences by inverting the learned CNN. The key benefit behind this strategy is that the CNN for frame-interpolation can be trained in an unsupervised manner by exploiting the temporal coherency that is naturally contained in real-world video sequences. The present model therefore learns image matching by simply watching videos. Besides a promise to be more generally applicable, the presented approach achieves surprising performance comparable to traditional empirically designed methods.
Tasks
Published	2016-03-19
URL	http://arxiv.org/abs/1603.06041v2
PDF	http://arxiv.org/pdf/1603.06041v2.pdf
PWC	https://paperswithcode.com/paper/learning-image-matching-by-simply-watching
Repo
Framework

Controlling Search in Very large Commonsense Knowledge Bases: A Machine Learning Approach


Title	Controlling Search in Very large Commonsense Knowledge Bases: A Machine Learning Approach
Authors	Abhishek Sharma, Michael Witbrock, Keith Goolsbey
Abstract	Very large commonsense knowledge bases (KBs) often have thousands to millions of axioms, of which relatively few are relevant for answering any given query. A large number of irrelevant axioms can easily overwhelm resolution-based theorem provers. Therefore, methods that help the reasoner identify useful inference paths form an essential part of large-scale reasoning systems. In this paper, we describe two ordering heuristics for optimization of reasoning in such systems. First, we discuss how decision trees can be used to select inference steps that are more likely to succeed. Second, we identify a small set of problem instance features that suffice to guide searches away from intractable regions of the search space. We show the efficacy of these techniques via experiments on thousands of queries from the Cyc KB. Results show that these methods lead to an order of magnitude reduction in inference time.
Tasks
Published	2016-03-14
URL	http://arxiv.org/abs/1603.04402v1
PDF	http://arxiv.org/pdf/1603.04402v1.pdf
PWC	https://paperswithcode.com/paper/controlling-search-in-very-large-commonsense
Repo
Framework

Impossibility in Belief Merging


Title	Impossibility in Belief Merging
Authors	Amílcar Mata Díaz, Ramón Pino Pérez
Abstract	With the aim of studying social properties of belief merging and having a better understanding of impossibility, we extend in three ways the framework of logic-based merging introduced by Konieczny and Pino P'erez. First, at the level of representation of the information, we pass from belief bases to complex epistemic states. Second, the profiles are represented as functions of finite societies to the set of epistemic states (a sort of vectors) and not as multisets of epistemic states. Third, we extend the set of rational postulates in order to consider the epistemic versions of the classical postulates of Social Choice Theory: Standard Domain, Pareto Property, Independence of Irrelevant Alternatives and Absence of Dictator. These epistemic versions of social postulates are given, essentially, in terms of the finite propositional logic. We state some representation theorems for these operators. These extensions and representation theorems allow us to establish an epistemic and very general version of Arrow’s Impossibility Theorem. One of the interesting features of our result, is that it holds for different representations of epistemic states; for instance conditionals, Ordinal Conditional functions and, of course, total preorders.
Tasks
Published	2016-06-14
URL	http://arxiv.org/abs/1606.04589v1
PDF	http://arxiv.org/pdf/1606.04589v1.pdf
PWC	https://paperswithcode.com/paper/impossibility-in-belief-merging
Repo
Framework

Anomaly Detection Using the Knowledge-based Temporal Abstraction Method


Title	Anomaly Detection Using the Knowledge-based Temporal Abstraction Method
Authors	Asaf Shabtai
Abstract	The rapid growth in stored time-oriented data necessitates the development of new methods for handling, processing, and interpreting large amounts of temporal data. One important example of such processing is detecting anomalies in time-oriented data. The Knowledge-Based Temporal Abstraction method was previously proposed for intelligent interpretation of temporal data based on predefined domain knowledge. In this study we propose a framework that integrates the KBTA method with a temporal pattern mining process for anomaly detection. According to the proposed method a temporal pattern mining process is applied on a dataset of basic temporal abstraction database in order to extract patterns representing normal behavior. These patterns are then analyzed in order to identify abnormal time periods characterized by a significantly small number of normal patterns. The proposed approach was demonstrated using a dataset collected from a real server.
Tasks	Anomaly Detection
Published	2016-12-14
URL	http://arxiv.org/abs/1612.04804v1
PDF	http://arxiv.org/pdf/1612.04804v1.pdf
PWC	https://paperswithcode.com/paper/anomaly-detection-using-the-knowledge-based
Repo
Framework

Probing the Intra-Component Correlations within Fisher Vector for Material Classification


Title	Probing the Intra-Component Correlations within Fisher Vector for Material Classification
Authors	Xiaopeng Hong, Xianbiao Qi, Guoying Zhao, Matti Pietikäinen
Abstract	Fisher vector (FV) has become a popular image representation. One notable underlying assumption of the FV framework is that local descriptors are well decorrelated within each cluster so that the covariance matrix for each Gaussian can be simplified to be diagonal. Though the FV usually relies on the Principal Component Analysis (PCA) to decorrelate local features, the PCA is applied to the entire training data and hence it only diagonalizes the \textit{universal} covariance matrix, rather than those w.r.t. the local components. As a result, the local decorrelation assumption is usually not supported in practice. To relax this assumption, this paper proposes a completed model of the Fisher vector, which is termed as the Completed Fisher vector (CFV). The CFV is a more general framework of the FV, since it encodes not only the variances but also the correlations of the whitened local descriptors. The CFV thus leads to improved discriminative power. We take the task of material categorization as an example and experimentally show that: 1) the CFV outperforms the FV under all parameter settings; 2) the CFV is robust to the changes in the number of components in the mixture; 3) even with a relatively small visual vocabulary the CFV still works well on two challenging datasets.
Tasks	Material Classification
Published	2016-04-15
URL	http://arxiv.org/abs/1604.04473v1
PDF	http://arxiv.org/pdf/1604.04473v1.pdf
PWC	https://paperswithcode.com/paper/probing-the-intra-component-correlations
Repo
Framework

Learning Executable Semantic Parsers for Natural Language Understanding


Title	Learning Executable Semantic Parsers for Natural Language Understanding
Authors	Percy Liang
Abstract	For building question answering systems and natural language interfaces, semantic parsing has emerged as an important and powerful paradigm. Semantic parsers map natural language into logical forms, the classic representation for many important linguistic phenomena. The modern twist is that we are interested in learning semantic parsers from data, which introduces a new layer of statistical and computational issues. This article lays out the components of a statistical semantic parser, highlighting the key challenges. We will see that semantic parsing is a rich fusion of the logical and the statistical world, and that this fusion will play an integral role in the future of natural language understanding systems.
Tasks	Question Answering, Semantic Parsing
Published	2016-03-22
URL	http://arxiv.org/abs/1603.06677v1
PDF	http://arxiv.org/pdf/1603.06677v1.pdf
PWC	https://paperswithcode.com/paper/learning-executable-semantic-parsers-for
Repo
Framework