May 6, 2019

2784 words 14 mins read

Paper Group ANR 238

Enriching Linked Datasets with New Object Properties. Balancing, Regression, Difference-In-Differences and Synthetic Control Methods: A Synthesis. Color Homography Color Correction. Steerable Principal Components for Space-Frequency Localized Images. Lexicon Integrated CNN Models with Attention for Sentiment Analysis. Semi-supervised Learning with …

Enriching Linked Datasets with New Object Properties


Title	Enriching Linked Datasets with New Object Properties
Authors	Subhashree S, P Sreenivasa Kumar
Abstract	Although several RDF knowledge bases are available through the LOD initiative, the ontology schema of such linked datasets is not very rich. In particular, they lack object properties. The problem of finding new object properties (and their instances) between any two given classes has not been investigated in detail in the context of Linked Data. In this paper, we present DART (Detecting Arbitrary Relations for enriching T-Boxes of Linked Data) - an unsupervised solution to enrich the LOD cloud with new object properties between two given classes. DART exploits contextual similarity to identify text patterns from the web corpus that can potentially represent relations between individuals. These text patterns are then clustered by means of paraphrase detection to capture the object properties between the two given LOD classes. DART also performs fully automated mapping of the discovered relations to the properties in the linked dataset. This serves many purposes such as identification of completely new relations, elimination of irrelevant relations, and generation of prospective property axioms. We have empirically evaluated our approach on several pairs of classes and found that the system can indeed be used for enriching the linked datasets with new object properties and their instances. We compared DART with newOntExt system which is an offshoot of the NELL (Never-Ending Language Learning) effort. Our experiments reveal that DART gives better results than newOntExt with respect to both the correctness, as well as the number of relations.
Tasks
Published	2016-06-24
URL	http://arxiv.org/abs/1606.07572v3
PDF	http://arxiv.org/pdf/1606.07572v3.pdf
PWC	https://paperswithcode.com/paper/enriching-linked-datasets-with-new-object
Repo
Framework

Balancing, Regression, Difference-In-Differences and Synthetic Control Methods: A Synthesis


Title	Balancing, Regression, Difference-In-Differences and Synthetic Control Methods: A Synthesis
Authors	Nikolay Doudchenko, Guido W. Imbens
Abstract	In a seminal paper Abadie, Diamond, and Hainmueller [2010] (ADH), see also Abadie and Gardeazabal [2003], Abadie et al. [2014], develop the synthetic control procedure for estimating the effect of a treatment, in the presence of a single treated unit and a number of control units, with pre-treatment outcomes observed for all units. The method constructs a set of weights such that selected covariates and pre-treatment outcomes of the treated unit are approximately matched by a weighted average of control units (the synthetic control). The weights are restricted to be nonnegative and sum to one, which is important because it allows the procedure to obtain unique weights even when the number of lagged outcomes is modest relative to the number of control units, a common setting in applications. In the current paper we propose a generalization that allows the weights to be negative, and their sum to differ from one, and that allows for a permanent additive difference between the treated unit and the controls, similar to difference-in-difference procedures. The weights directly minimize the distance between the lagged outcomes for the treated and the control units, using regularization methods to deal with a potentially large number of possible control units.
Tasks
Published	2016-10-25
URL	http://arxiv.org/abs/1610.07748v2
PDF	http://arxiv.org/pdf/1610.07748v2.pdf
PWC	https://paperswithcode.com/paper/balancing-regression-difference-in
Repo
Framework

Color Homography Color Correction


Title	Color Homography Color Correction
Authors	Graham D. Finlayson, Han Gong, Robert B. Fisher
Abstract	Homographies – a mathematical formalism for relating image points across different camera viewpoints – are at the foundations of geometric methods in computer vision and are used in geometric camera calibration, image registration, and stereo vision and other tasks. In this paper, we show the surprising result that colors across a change in viewing condition (changing light color, shading and camera) are also related by a homography. We propose a new color correction method based on color homography. Experiments demonstrate that solving the color homography problem leads to more accurate calibration.
Tasks	Calibration, Image Registration
Published	2016-07-20
URL	http://arxiv.org/abs/1607.05947v3
PDF	http://arxiv.org/pdf/1607.05947v3.pdf
PWC	https://paperswithcode.com/paper/color-homography-color-correction
Repo
Framework

Steerable Principal Components for Space-Frequency Localized Images


Title	Steerable Principal Components for Space-Frequency Localized Images
Authors	Boris Landa, Yoel Shkolnisky
Abstract	This paper describes a fast and accurate method for obtaining steerable principal components from a large dataset of images, assuming the images are well localized in space and frequency. The obtained steerable principal components are optimal for expanding the images in the dataset and all of their rotations. The method relies upon first expanding the images using a series of two-dimensional Prolate Spheroidal Wave Functions (PSWFs), where the expansion coefficients are evaluated using a specially designed numerical integration scheme. Then, the expansion coefficients are used to construct a rotationally-invariant covariance matrix which admits a block-diagonal structure, and the eigen-decomposition of its blocks provides us with the desired steerable principal components. The proposed method is shown to be faster then existing methods, while providing appropriate error bounds which guarantee its accuracy.
Tasks
Published	2016-08-09
URL	http://arxiv.org/abs/1608.02702v2
PDF	http://arxiv.org/pdf/1608.02702v2.pdf
PWC	https://paperswithcode.com/paper/steerable-principal-components-for-space
Repo
Framework

Lexicon Integrated CNN Models with Attention for Sentiment Analysis


Title	Lexicon Integrated CNN Models with Attention for Sentiment Analysis
Authors	Bonggun Shin, Timothy Lee, Jinho D. Choi
Abstract	With the advent of word embeddings, lexicons are no longer fully utilized for sentiment analysis although they still provide important features in the traditional setting. This paper introduces a novel approach to sentiment analysis that integrates lexicon embeddings and an attention mechanism into Convolutional Neural Networks. Our approach performs separate convolutions for word and lexicon embeddings and provides a global view of the document using attention. Our models are experimented on both the SemEval’16 Task 4 dataset and the Stanford Sentiment Treebank, and show comparative or better results against the existing state-of-the-art systems. Our analysis shows that lexicon embeddings allow to build high-performing models with much smaller word embeddings, and the attention mechanism effectively dims out noisy words for sentiment analysis.
Tasks	Sentiment Analysis, Word Embeddings
Published	2016-10-20
URL	http://arxiv.org/abs/1610.06272v2
PDF	http://arxiv.org/pdf/1610.06272v2.pdf
PWC	https://paperswithcode.com/paper/lexicon-integrated-cnn-models-with-attention
Repo
Framework

Semi-supervised Learning with Sparse Autoencoders in Phone Classification


Title	Semi-supervised Learning with Sparse Autoencoders in Phone Classification
Authors	Akash Kumar Dhaka, Giampiero Salvi
Abstract	We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by supervised fine tuning, our method takes advantage of both unlabelled and labelled data simultaneously through mini- batch stochastic gradient descent. We tested the method with varying proportions of labelled vs unlabelled observations in frame-based phoneme classification on the TIMIT database. Our experiments show that the method outperforms standard supervised training for an equal amount of labelled data and provides competitive error rates compared to state-of-the-art graph-based semi-supervised learning techniques.
Tasks	Acoustic Modelling, Speech Recognition
Published	2016-10-03
URL	http://arxiv.org/abs/1610.00520v1
PDF	http://arxiv.org/pdf/1610.00520v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-learning-with-sparse
Repo
Framework

Stochastic Variance-Reduced ADMM


Title	Stochastic Variance-Reduced ADMM
Authors	Shuai Zheng, James T. Kwok
Abstract	The alternating direction method of multipliers (ADMM) is a powerful optimization solver in machine learning. Recently, stochastic ADMM has been integrated with variance reduction methods for stochastic gradient, leading to SAG-ADMM and SDCA-ADMM that have fast convergence rates and low iteration complexities. However, their space requirements can still be high. In this paper, we propose an integration of ADMM with the method of stochastic variance reduced gradient (SVRG). Unlike another recent integration attempt called SCAS-ADMM, the proposed algorithm retains the fast convergence benefits of SAG-ADMM and SDCA-ADMM, but is more advantageous in that its storage requirement is very low, even independent of the sample size $n$. We also extend the proposed method for nonconvex problems, and obtain a convergence rate of $O(1/T)$. Experimental results demonstrate that it is as fast as SAG-ADMM and SDCA-ADMM, much faster than SCAS-ADMM, and can be used on much bigger data sets.
Tasks
Published	2016-04-24
URL	http://arxiv.org/abs/1604.07070v3
PDF	http://arxiv.org/pdf/1604.07070v3.pdf
PWC	https://paperswithcode.com/paper/stochastic-variance-reduced-admm
Repo
Framework

Improving the Performance of Neural Networks in Regression Tasks Using Drawering


Title	Improving the Performance of Neural Networks in Regression Tasks Using Drawering
Authors	Konrad Zolna
Abstract	The method presented extends a given regression neural network to make its performance improve. The modification affects the learning procedure only, hence the extension may be easily omitted during evaluation without any change in prediction. It means that the modified model may be evaluated as quickly as the original one but tends to perform better. This improvement is possible because the modification gives better expressive power, provides better behaved gradients and works as a regularization. The knowledge gained by the temporarily extended neural network is contained in the parameters shared with the original neural network. The only cost is an increase in learning time.
Tasks
Published	2016-12-05
URL	http://arxiv.org/abs/1612.01589v1
PDF	http://arxiv.org/pdf/1612.01589v1.pdf
PWC	https://paperswithcode.com/paper/improving-the-performance-of-neural-networks
Repo
Framework

Deep Residual Networks with Exponential Linear Unit


Title	Deep Residual Networks with Exponential Linear Unit
Authors	Anish Shah, Eashan Kadam, Hena Shah, Sameer Shinde, Sandip Shingade
Abstract	Very deep convolutional neural networks introduced new problems like vanishing gradient and degradation. The recent successful contributions towards solving these problems are Residual and Highway Networks. These networks introduce skip connections that allow the information (from the input or those learned in earlier layers) to flow more into the deeper layers. These very deep models have lead to a considerable decrease in test errors, on benchmarks like ImageNet and COCO. In this paper, we propose the use of exponential linear unit instead of the combination of ReLU and Batch Normalization in Residual Networks. We show that this not only speeds up learning in Residual Networks but also improves the accuracy as the depth increases. It improves the test error on almost all data sets, like CIFAR-10 and CIFAR-100
Tasks	Image Classification
Published	2016-04-14
URL	http://arxiv.org/abs/1604.04112v4
PDF	http://arxiv.org/pdf/1604.04112v4.pdf
PWC	https://paperswithcode.com/paper/deep-residual-networks-with-exponential
Repo
Framework

Weakly Learning to Match Experts in Online Community


Title	Weakly Learning to Match Experts in Online Community
Authors	Yujie Qian, Jie Tang, Kan Wu
Abstract	In online question-and-answer (QA) websites like Quora, one central issue is to find (invite) users who are able to provide answers to a given question and at the same time would be unlikely to say “no” to the invitation. The challenge is how to trade off the matching degree between users’ expertise and the question topic, and the likelihood of positive response from the invited users. In this paper, we formally formulate the problem and develop a weakly supervised factor graph (WeakFG) model to address the problem. The model explicitly captures expertise matching degree between questions and users. To model the likelihood that an invited user is willing to answer a specific question, we incorporate a set of correlations based on social identity theory into the WeakFG model. We use two different genres of datasets: QA-Expert and Paper-Reviewer, to validate the proposed model. Our experimental results show that the proposed model can significantly outperform (+1.5-10.7% by MAP) the state-of-the-art algorithms for matching users (experts) with community questions. We have also developed an online system to further demonstrate the advantages of the proposed method.
Tasks
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04363v2
PDF	http://arxiv.org/pdf/1611.04363v2.pdf
PWC	https://paperswithcode.com/paper/weakly-learning-to-match-experts-in-online
Repo
Framework

Discriminative Phrase Embedding for Paraphrase Identification


Title	Discriminative Phrase Embedding for Paraphrase Identification
Authors	Wenpeng Yin, Hinrich Schütze
Abstract	This work, concerning paraphrase identification task, on one hand contributes to expanding deep learning embeddings to include continuous and discontinuous linguistic phrases. On the other hand, it comes up with a new scheme TF-KLD-KNN to learn the discriminative weights of words and phrases specific to paraphrase task, so that a weighted sum of embeddings can represent sentences more effectively. Based on these two innovations we get competitive state-of-the-art performance on paraphrase identification.
Tasks	Paraphrase Identification
Published	2016-04-02
URL	http://arxiv.org/abs/1604.00503v1
PDF	http://arxiv.org/pdf/1604.00503v1.pdf
PWC	https://paperswithcode.com/paper/discriminative-phrase-embedding-for
Repo
Framework

Semantic Regularities in Document Representations


Title	Semantic Regularities in Document Representations
Authors	Fei Sun, Jiafeng Guo, Yanyan Lan, Jun Xu, Xueqi Cheng
Abstract	Recent work exhibited that distributed word representations are good at capturing linguistic regularities in language. This allows vector-oriented reasoning based on simple linear algebra between words. Since many different methods have been proposed for learning document representations, it is natural to ask whether there is also linear structure in these learned representations to allow similar reasoning at document level. To answer this question, we design a new document analogy task for testing the semantic regularities in document representations, and conduct empirical evaluations over several state-of-the-art document representation models. The results reveal that neural embedding based document representations work better on this analogy task than conventional methods, and we provide some preliminary explanations over these observations.
Tasks
Published	2016-03-24
URL	http://arxiv.org/abs/1603.07603v1
PDF	http://arxiv.org/pdf/1603.07603v1.pdf
PWC	https://paperswithcode.com/paper/semantic-regularities-in-document
Repo
Framework

Faster Kernel Ridge Regression Using Sketching and Preconditioning


Title	Faster Kernel Ridge Regression Using Sketching and Preconditioning
Authors	Haim Avron, Kenneth L. Clarkson, David P. Woodruff
Abstract	Kernel Ridge Regression (KRR) is a simple yet powerful technique for non-parametric regression whose computation amounts to solving a linear system. This system is usually dense and highly ill-conditioned. In addition, the dimensions of the matrix are the same as the number of data points, so direct methods are unrealistic for large-scale datasets. In this paper, we propose a preconditioning technique for accelerating the solution of the aforementioned linear system. The preconditioner is based on random feature maps, such as random Fourier features, which have recently emerged as a powerful technique for speeding up and scaling the training of kernel-based methods, such as kernel ridge regression, by resorting to approximations. However, random feature maps only provide crude approximations to the kernel function, so delivering state-of-the-art results by directly solving the approximated system requires the number of random features to be very large. We show that random feature maps can be much more effective in forming preconditioners, since under certain conditions a not-too-large number of random features is sufficient to yield an effective preconditioner. We empirically evaluate our method and show it is highly effective for datasets of up to one million training examples.
Tasks
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03220v4
PDF	http://arxiv.org/pdf/1611.03220v4.pdf
PWC	https://paperswithcode.com/paper/faster-kernel-ridge-regression-using
Repo
Framework

Deep Models for Engagement Assessment With Scarce Label Information


Title	Deep Models for Engagement Assessment With Scarce Label Information
Authors	Feng Li, Guangfan Zhang, Wei Wang, Roger Xu, Tom Schnell, Jonathan Wen, Frederic McKenzie, Jiang Li
Abstract	Task engagement is defined as loadings on energetic arousal (affect), task motivation, and concentration (cognition). It is usually challenging and expensive to label cognitive state data, and traditional computational models trained with limited label information for engagement assessment do not perform well because of overfitting. In this paper, we proposed two deep models (i.e., a deep classifier and a deep autoencoder) for engagement assessment with scarce label information. We recruited 15 pilots to conduct a 4-h flight simulation from Seattle to Chicago and recorded their electroencephalograph (EEG) signals during the simulation. Experts carefully examined the EEG signals and labeled 20 min of the EEG data for each pilot. The EEG signals were preprocessed and power spectral features were extracted. The deep models were pretrained by the unlabeled data and were fine-tuned by a different proportion of the labeled data (top 1%, 3%, 5%, 10%, 15%, and 20%) to learn new representations for engagement assessment. The models were then tested on the remaining labeled data. We compared performances of the new data representations with the original EEG features for engagement assessment. Experimental results show that the representations learned by the deep models yielded better accuracies for the six scenarios (77.09%, 80.45%, 83.32%, 85.74%, 85.78%, and 86.52%), based on different proportions of the labeled data for training, as compared with the corresponding accuracies (62.73%, 67.19%, 73.38%, 79.18%, 81.47%, and 84.92%) achieved by the original EEG features. Deep models are effective for engagement assessment especially when less label information was used for training.
Tasks	EEG
Published	2016-10-21
URL	http://arxiv.org/abs/1610.06815v1
PDF	http://arxiv.org/pdf/1610.06815v1.pdf
PWC	https://paperswithcode.com/paper/deep-models-for-engagement-assessment-with
Repo
Framework

Identification of Parallel Passages Across a Large Hebrew/Aramaic Corpus


Title	Identification of Parallel Passages Across a Large Hebrew/Aramaic Corpus
Authors	Avi Shmidman, Moshe Koppel, Ely Porat
Abstract	We propose a method for efficiently finding all parallel passages in a large corpus, even if the passages are not quite identical due to rephrasing and orthographic variation. The key ideas are the representation of each word in the corpus by its two most infrequent letters, finding matched pairs of strings of four or five words that differ by at most one word and then identifying clusters of such matched pairs. Using this method, over 4600 parallel pairs of passages were identified in the Babylonian Talmud, a Hebrew-Aramaic corpus of over 1.8 million words, in just over 30 seconds. Empirical comparisons on sample data indicate that the coverage obtained by our method is essentially the same as that obtained using slow exhaustive methods.
Tasks
Published	2016-02-28
URL	http://arxiv.org/abs/1602.08715v2
PDF	http://arxiv.org/pdf/1602.08715v2.pdf
PWC	https://paperswithcode.com/paper/identification-of-parallel-passages-across-a
Repo
Framework