May 6, 2019

3018 words 15 mins read

Paper Group ANR 350

#HashtagWars: Learning a Sense of Humor. World Knowledge as Indirect Supervision for Document Clustering. A symbolic algebra for the computation of expected utilities in multiplicative influence diagrams. Image Decomposition Using a Robust Regression Approach. Learning Joint Representations of Videos and Sentences with Web Image Search. Neural Beli …

#HashtagWars: Learning a Sense of Humor


Title	#HashtagWars: Learning a Sense of Humor
Authors	Peter Potash, Alexey Romanov, Anna Rumshisky
Abstract	In this work, we present a new dataset for computational humor, specifically comparative humor ranking, which attempts to eschew the ubiquitous binary approach to humor detection. The dataset consists of tweets that are humorous responses to a given hashtag. We describe the motivation for this new dataset, as well as the collection process, which includes a description of our semi-automated system for data collection. We also present initial experiments for this dataset using both unsupervised and supervised approaches. Our best supervised system achieved 63.7% accuracy, suggesting that this task is much more difficult than comparable humor detection tasks. Initial experiments indicate that a character-level model is more suitable for this task than a token-level model, likely due to a large amount of puns that can be captured by a character-level model.
Tasks	Humor Detection
Published	2016-12-09
URL	http://arxiv.org/abs/1612.03216v2
PDF	http://arxiv.org/pdf/1612.03216v2.pdf
PWC	https://paperswithcode.com/paper/hashtagwars-learning-a-sense-of-humor
Repo
Framework

World Knowledge as Indirect Supervision for Document Clustering


Title	World Knowledge as Indirect Supervision for Document Clustering
Authors	Chenguang Wang, Yangqiu Song, Dan Roth, Ming Zhang, Jiawei Han
Abstract	One of the key obstacles in making learning protocols realistic in applications is the need to supervise them, a costly process that often requires hiring domain experts. We consider the framework to use the world knowledge as indirect supervision. World knowledge is general-purpose knowledge, which is not designed for any specific domain. Then the key challenges are how to adapt the world knowledge to domains and how to represent it for learning. In this paper, we provide an example of using world knowledge for domain dependent document clustering. We provide three ways to specify the world knowledge to domains by resolving the ambiguity of the entities and their types, and represent the data with world knowledge as a heterogeneous information network. Then we propose a clustering algorithm that can cluster multiple types and incorporate the sub-type information as constraints. In the experiments, we use two existing knowledge bases as our sources of world knowledge. One is Freebase, which is collaboratively collected knowledge about entities and their organizations. The other is YAGO2, a knowledge base automatically extracted from Wikipedia and maps knowledge to the linguistic knowledge base, WordNet. Experimental results on two text benchmark datasets (20newsgroups and RCV1) show that incorporating world knowledge as indirect supervision can significantly outperform the state-of-the-art clustering algorithms as well as clustering algorithms enhanced with world knowledge features.
Tasks
Published	2016-07-30
URL	http://arxiv.org/abs/1608.00104v1
PDF	http://arxiv.org/pdf/1608.00104v1.pdf
PWC	https://paperswithcode.com/paper/world-knowledge-as-indirect-supervision-for
Repo
Framework

A symbolic algebra for the computation of expected utilities in multiplicative influence diagrams


Title	A symbolic algebra for the computation of expected utilities in multiplicative influence diagrams
Authors	Manuele Leonelli, Eva Riccomagno, Jim Q. Smith
Abstract	Influence diagrams provide a compact graphical representation of decision problems. Several algorithms for the quick computation of their associated expected utilities are available in the literature. However, often they rely on a full quantification of both probabilistic uncertainties and utility values. For problems where all random variables and decision spaces are finite and discrete, here we develop a symbolic way to calculate the expected utilities of influence diagrams that does not require a full numerical representation. Within this approach expected utilities correspond to families of polynomials. After characterizing their polynomial structure, we develop an efficient symbolic algorithm for the propagation of expected utilities through the diagram and provide an implementation of this algorithm using a computer algebra system. We then characterize many of the standard manipulations of influence diagrams as transformations of polynomials. We also generalize the decision analytic framework of these diagrams by defining asymmetries as operations over the expected utility polynomials.
Tasks
Published	2016-07-28
URL	http://arxiv.org/abs/1607.08485v2
PDF	http://arxiv.org/pdf/1607.08485v2.pdf
PWC	https://paperswithcode.com/paper/a-symbolic-algebra-for-the-computation-of
Repo
Framework

Image Decomposition Using a Robust Regression Approach


Title	Image Decomposition Using a Robust Regression Approach
Authors	Shervin Minaee, Yao Wang
Abstract	This paper considers how to separate text and/or graphics from smooth background in screen content and mixed content images and proposes an algorithm to perform this segmentation task. The proposed methods make use of the fact that the background in each block is usually smoothly varying and can be modeled well by a linear combination of a few smoothly varying basis functions, while the foreground text and graphics create sharp discontinuity. This algorithm separates the background and foreground pixels by trying to fit pixel values in the block into a smooth function using a robust regression method. The inlier pixels that can be well represented with the smooth model will be considered as background, while remaining outlier pixels will be considered foreground. We have also created a dataset of screen content images extracted from HEVC standard test sequences for screen content coding with their ground truth segmentation result which can be used for this task. The proposed algorithm has been tested on the dataset mentioned above and is shown to have superior performance over other methods, such as the hierarchical k-means clustering algorithm, shape primitive extraction and coding, and the least absolute deviation fitting scheme for foreground segmentation.
Tasks
Published	2016-09-13
URL	http://arxiv.org/abs/1609.03874v2
PDF	http://arxiv.org/pdf/1609.03874v2.pdf
PWC	https://paperswithcode.com/paper/image-decomposition-using-a-robust-regression
Repo
Framework

Learning Joint Representations of Videos and Sentences with Web Image Search


Title	Learning Joint Representations of Videos and Sentences with Web Image Search
Authors	Mayu Otani, Yuta Nakashima, Esa Rahtu, Janne Heikkilä, Naokazu Yokoya
Abstract	Our objective is video retrieval based on natural language queries. In addition, we consider the analogous problem of retrieving sentences or generating descriptions given an input video. Recent work has addressed the problem by embedding visual and textual inputs into a common space where semantic similarities correlate to distances. We also adopt the embedding approach, and make the following contributions: First, we utilize web image search in sentence embedding process to disambiguate fine-grained visual concepts. Second, we propose embedding models for sentence, image, and video inputs whose parameters are learned simultaneously. Finally, we show how the proposed model can be applied to description generation. Overall, we observe a clear improvement over the state-of-the-art methods in the video and sentence retrieval tasks. In description generation, the performance level is comparable to the current state-of-the-art, although our embeddings were trained for the retrieval tasks.
Tasks	Image Retrieval, Sentence Embedding, Video Retrieval
Published	2016-08-08
URL	http://arxiv.org/abs/1608.02367v1
PDF	http://arxiv.org/pdf/1608.02367v1.pdf
PWC	https://paperswithcode.com/paper/learning-joint-representations-of-videos-and
Repo
Framework

Neural Belief Tracker: Data-Driven Dialogue State Tracking


Title	Neural Belief Tracker: Data-Driven Dialogue State Tracking
Authors	Nikola Mrkšić, Diarmuid Ó Séaghdha, Tsung-Hsien Wen, Blaise Thomson, Steve Young
Abstract	One of the core components of modern spoken dialogue systems is the belief tracker, which estimates the user’s goal at every step of the dialogue. However, most current approaches have difficulty scaling to larger, more complex dialogue domains. This is due to their dependency on either: a) Spoken Language Understanding models that require large amounts of annotated training data; or b) hand-crafted lexicons for capturing some of the linguistic variation in users’ language. We propose a novel Neural Belief Tracking (NBT) framework which overcomes these problems by building on recent advances in representation learning. NBT models reason over pre-trained word vectors, learning to compose them into distributed representations of user utterances and dialogue context. Our evaluation on two datasets shows that this approach surpasses past limitations, matching the performance of state-of-the-art models which rely on hand-crafted semantic lexicons and outperforming them when such lexicons are not provided.
Tasks	Dialogue State Tracking, Representation Learning, Spoken Dialogue Systems, Spoken Language Understanding
Published	2016-06-12
URL	http://arxiv.org/abs/1606.03777v2
PDF	http://arxiv.org/pdf/1606.03777v2.pdf
PWC	https://paperswithcode.com/paper/neural-belief-tracker-data-driven-dialogue
Repo
Framework

Image Labeling by Assignment


Title	Image Labeling by Assignment
Authors	Freddie Åström, Stefania Petra, Bernhard Schmitzer, Christoph Schnörr
Abstract	We introduce a novel geometric approach to the image labeling problem. Abstracting from specific labeling applications, a general objective function is defined on a manifold of stochastic matrices, whose elements assign prior data that are given in any metric space, to observed image measurements. The corresponding Riemannian gradient flow entails a set of replicator equations, one for each data point, that are spatially coupled by geometric averaging on the manifold. Starting from uniform assignments at the barycenter as natural initialization, the flow terminates at some global maximum, each of which corresponds to an image labeling that uniquely assigns the prior data. Our geometric variational approach constitutes a smooth non-convex inner approximation of the general image labeling problem, implemented with sparse interior-point numerics in terms of parallel multiplicative updates that converge efficiently.
Tasks
Published	2016-03-16
URL	http://arxiv.org/abs/1603.05285v1
PDF	http://arxiv.org/pdf/1603.05285v1.pdf
PWC	https://paperswithcode.com/paper/image-labeling-by-assignment
Repo
Framework

Contextual Weisfeiler-Lehman Graph Kernel For Malware Detection


Title	Contextual Weisfeiler-Lehman Graph Kernel For Malware Detection
Authors	Annamalai Narayanan, Guozhu Meng, Liu Yang, Jinliang Liu, Lihui Chen
Abstract	In this paper, we propose a novel graph kernel specifically to address a challenging problem in the field of cyber-security, namely, malware detection. Previous research has revealed the following: (1) Graph representations of programs are ideally suited for malware detection as they are robust against several attacks, (2) Besides capturing topological neighbourhoods (i.e., structural information) from these graphs it is important to capture the context under which the neighbourhoods are reachable to accurately detect malicious neighbourhoods. We observe that state-of-the-art graph kernels, such as Weisfeiler-Lehman kernel (WLK) capture the structural information well but fail to capture contextual information. To address this, we develop the Contextual Weisfeiler-Lehman kernel (CWLK) which is capable of capturing both these types of information. We show that for the malware detection problem, CWLK is more expressive and hence more accurate than WLK while maintaining comparable efficiency. Through our large-scale experiments with more than 50,000 real-world Android apps, we demonstrate that CWLK outperforms two state-of-the-art graph kernels (including WLK) and three malware detection techniques by more than 5.27% and 4.87% F-measure, respectively, while maintaining high efficiency. This high accuracy and efficiency make CWLK suitable for large-scale real-world malware detection.
Tasks	Malware Detection
Published	2016-06-21
URL	http://arxiv.org/abs/1606.06369v1
PDF	http://arxiv.org/pdf/1606.06369v1.pdf
PWC	https://paperswithcode.com/paper/contextual-weisfeiler-lehman-graph-kernel-for
Repo
Framework

Can fully convolutional networks perform well for general image restoration problems?


Title	Can fully convolutional networks perform well for general image restoration problems?
Authors	Subhajit Chaudhury, Hiya Roy
Abstract	We present a fully convolutional network(FCN) based approach for color image restoration. FCNs have recently shown remarkable performance for high-level vision problem like semantic segmentation. In this paper, we investigate if FCN models can show promising performance for low-level problems like image restoration as well. We propose a fully convolutional model, that learns a direct end-to-end mapping between the corrupted images as input and the desired clean images as output. Our proposed method takes inspiration from domain transformation techniques but presents a data-driven task specific approach where filters for novel basis projection, task dependent coefficient alterations, and image reconstruction are represented as convolutional networks. Experimental results show that our FCN model outperforms traditional sparse coding based methods and demonstrates competitive performance compared to the state-of-the-art methods for image denoising. We further show that our proposed model can solve the difficult problem of blind image inpainting and can produce reconstructed images of impressive visual quality.
Tasks	Denoising, Image Denoising, Image Inpainting, Image Reconstruction, Image Restoration, Semantic Segmentation
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04481v2
PDF	http://arxiv.org/pdf/1611.04481v2.pdf
PWC	https://paperswithcode.com/paper/can-fully-convolutional-networks-perform-well
Repo
Framework

Toward Optimal Feature Selection in Naive Bayes for Text Categorization


Title	Toward Optimal Feature Selection in Naive Bayes for Text Categorization
Authors	Bo Tang, Steven Kay, Haibo He
Abstract	Automated feature selection is important for text categorization to reduce the feature size and to speed up the learning process of classifiers. In this paper, we present a novel and efficient feature selection framework based on the Information Theory, which aims to rank the features with their discriminative capacity for classification. We first revisit two information measures: Kullback-Leibler divergence and Jeffreys divergence for binary hypothesis testing, and analyze their asymptotic properties relating to type I and type II errors of a Bayesian classifier. We then introduce a new divergence measure, called Jeffreys-Multi-Hypothesis (JMH) divergence, to measure multi-distribution divergence for multi-class classification. Based on the JMH-divergence, we develop two efficient feature selection methods, termed maximum discrimination ($MD$) and $MD-\chi^2$ methods, for text categorization. The promising results of extensive experiments demonstrate the effectiveness of the proposed approaches.
Tasks	Feature Selection, Text Classification
Published	2016-02-09
URL	http://arxiv.org/abs/1602.02850v1
PDF	http://arxiv.org/pdf/1602.02850v1.pdf
PWC	https://paperswithcode.com/paper/toward-optimal-feature-selection-in-naive
Repo
Framework

Wavelet-Based Segmentation on the Sphere


Title	Wavelet-Based Segmentation on the Sphere
Authors	Xiaohao Cai, Christopher G. R. Wallis, Jennifer Y. H. Chan, Jason D. McEwen
Abstract	Segmentation, a useful/powerful technique in pattern recognition, is the process of identifying object outlines within images. There are a number of efficient algorithms for segmentation in Euclidean space that depend on the variational approach and partial differential equation modelling. Wavelets have been used successfully in various problems in image processing, including segmentation, inpainting, noise removal, super-resolution image restoration, and many others. Wavelets on the sphere have been developed to solve such problems for data defined on the sphere, which arise in numerous fields such as cosmology and geophysics. In this work, we propose a wavelet-based method to segment images on the sphere, accounting for the underlying geometry of spherical data. Our method is a direct extension of the tight-frame based segmentation method used to automatically identify tube-like structures such as blood vessels in medical imaging. It is compatible with any arbitrary type of wavelet frame defined on the sphere, such as axisymmetric wavelets, directional wavelets, curvelets, and hybrid wavelet constructions. Such an approach allows the desirable properties of wavelets to be naturally inherited in the segmentation process. In particular, directional wavelets and curvelets, which were designed to efficiently capture directional signal content, provide additional advantages in segmenting images containing prominent directional and curvilinear features. We present several numerical experiments, applying our wavelet-based segmentation method, as well as the common K-means method, on real-world spherical images. These experiments demonstrate the superiority of our method and show that it is capable of segmenting different kinds of spherical images, including those with prominent directional features. Moreover, our algorithm is efficient with convergence usually within a few iterations.
Tasks	Image Restoration, Super-Resolution
Published	2016-09-21
URL	https://arxiv.org/abs/1609.06500v2
PDF	https://arxiv.org/pdf/1609.06500v2.pdf
PWC	https://paperswithcode.com/paper/wavelet-based-segmentation-on-the-sphere
Repo
Framework

A Deep Metric for Multimodal Registration


Title	A Deep Metric for Multimodal Registration
Authors	Martin Simonovsky, Benjamín Gutiérrez-Becker, Diana Mateus, Nassir Navab, Nikos Komodakis
Abstract	Multimodal registration is a challenging problem in medical imaging due the high variability of tissue appearance under different imaging modalities. The crucial component here is the choice of the right similarity measure. We make a step towards a general learning-based solution that can be adapted to specific situations and present a metric based on a convolutional neural network. Our network can be trained from scratch even from a few aligned image pairs. The metric is validated on intersubject deformable registration on a dataset different from the one used for training, demonstrating good generalization. In this task, we outperform mutual information by a significant margin.
Tasks
Published	2016-09-17
URL	http://arxiv.org/abs/1609.05396v1
PDF	http://arxiv.org/pdf/1609.05396v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-metric-for-multimodal-registration
Repo
Framework

A Probabilistic Modeling Approach to Hearing Loss Compensation


Title	A Probabilistic Modeling Approach to Hearing Loss Compensation
Authors	Thijs van de Laar, Bert de Vries
Abstract	Hearing Aid (HA) algorithms need to be tuned (“fitted”) to match the impairment of each specific patient. The lack of a fundamental HA fitting theory is a strong contributing factor to an unsatisfying sound experience for about 20% of hearing aid patients. This paper proposes a probabilistic modeling approach to the design of HA algorithms. The proposed method relies on a generative probabilistic model for the hearing loss problem and provides for automated inference of the corresponding (1) signal processing algorithm, (2) the fitting solution as well as a principled (3) performance evaluation metric. All three tasks are realized as message passing algorithms in a factor graph representation of the generative model, which in principle allows for fast implementation on hearing aid or mobile device hardware. The methods are theoretically worked out and simulated with a custom-built factor graph toolbox for a specific hearing loss model.
Tasks
Published	2016-02-03
URL	http://arxiv.org/abs/1602.01345v2
PDF	http://arxiv.org/pdf/1602.01345v2.pdf
PWC	https://paperswithcode.com/paper/a-probabilistic-modeling-approach-to-hearing
Repo
Framework

Composing inference algorithms as program transformations


Title	Composing inference algorithms as program transformations
Authors	Robert Zinkov, Chung-chieh Shan
Abstract	Probabilistic inference procedures are usually coded painstakingly from scratch, for each target model and each inference algorithm. We reduce this effort by generating inference procedures from models automatically. We make this code generation modular by decomposing inference algorithms into reusable program-to-program transformations. These transformations perform exact inference as well as generate probabilistic programs that compute expectations, densities, and MCMC samples. The resulting inference procedures are about as accurate and fast as other probabilistic programming systems on real-world problems.
Tasks	Code Generation, Probabilistic Programming
Published	2016-03-06
URL	http://arxiv.org/abs/1603.01882v2
PDF	http://arxiv.org/pdf/1603.01882v2.pdf
PWC	https://paperswithcode.com/paper/composing-inference-algorithms-as-program
Repo
Framework

Dropout with Expectation-linear Regularization


Title	Dropout with Expectation-linear Regularization
Authors	Xuezhe Ma, Yingkai Gao, Zhiting Hu, Yaoliang Yu, Yuntian Deng, Eduard Hovy
Abstract	Dropout, a simple and effective way to train deep neural networks, has led to a number of impressive empirical successes and spawned many recent theoretical investigations. However, the gap between dropout’s training and inference phases, introduced due to tractability considerations, has largely remained under-appreciated. In this work, we first formulate dropout as a tractable approximation of some latent variable model, leading to a clean view of parameter sharing and enabling further theoretical analysis. Then, we introduce (approximate) expectation-linear dropout neural networks, whose inference gap we are able to formally characterize. Algorithmically, we show that our proposed measure of the inference gap can be used to regularize the standard dropout training objective, resulting in an \emph{explicit} control of the gap. Our method is as simple and efficient as standard dropout. We further prove the upper bounds on the loss in accuracy due to expectation-linearization, describe classes of input distributions that expectation-linearize easily. Experiments on three image classification benchmark datasets demonstrate that reducing the inference gap can indeed improve the performance consistently.
Tasks	Image Classification
Published	2016-09-26
URL	http://arxiv.org/abs/1609.08017v3
PDF	http://arxiv.org/pdf/1609.08017v3.pdf
PWC	https://paperswithcode.com/paper/dropout-with-expectation-linear
Repo
Framework