July 29, 2019

2881 words 14 mins read

Paper Group ANR 9

An Empirical Evaluation of Zero Resource Acoustic Unit Discovery. Amobee at SemEval-2017 Task 4: Deep Learning System for Sentiment Detection on Twitter. Data-Efficient Policy Evaluation Through Behavior Policy Search. Interacting Attention-gated Recurrent Networks for Recommendation. Compact Model Representation for 3D Reconstruction. Side Informa …

An Empirical Evaluation of Zero Resource Acoustic Unit Discovery


Title	An Empirical Evaluation of Zero Resource Acoustic Unit Discovery
Authors	Chunxi Liu, Jinyi Yang, Ming Sun, Santosh Kesiraju, Alena Rott, Lucas Ondel, Pegah Ghahremani, Najim Dehak, Lukas Burget, Sanjeev Khudanpur
Abstract	Acoustic unit discovery (AUD) is a process of automatically identifying a categorical acoustic unit inventory from speech and producing corresponding acoustic unit tokenizations. AUD provides an important avenue for unsupervised acoustic model training in a zero resource setting where expert-provided linguistic knowledge and transcribed speech are unavailable. Therefore, to further facilitate zero-resource AUD process, in this paper, we demonstrate acoustic feature representations can be significantly improved by (i) performing linear discriminant analysis (LDA) in an unsupervised self-trained fashion, and (ii) leveraging resources of other languages through building a multilingual bottleneck (BN) feature extractor to give effective cross-lingual generalization. Moreover, we perform comprehensive evaluations of AUD efficacy on multiple downstream speech applications, and their correlated performance suggests that AUD evaluations are feasible using different alternative language resources when only a subset of these evaluation resources can be available in typical zero resource applications.
Tasks
Published	2017-02-05
URL	http://arxiv.org/abs/1702.01360v1
PDF	http://arxiv.org/pdf/1702.01360v1.pdf
PWC	https://paperswithcode.com/paper/an-empirical-evaluation-of-zero-resource
Repo
Framework

Amobee at SemEval-2017 Task 4: Deep Learning System for Sentiment Detection on Twitter


Title	Amobee at SemEval-2017 Task 4: Deep Learning System for Sentiment Detection on Twitter
Authors	Alon Rozental, Daniel Fleischer
Abstract	This paper describes the Amobee sentiment analysis system, adapted to compete in SemEval 2017 task 4. The system consists of two parts: a supervised training of RNN models based on a Twitter sentiment treebank, and the use of feedforward NN, Naive Bayes and logistic regression classifiers to produce predictions for the different sub-tasks. The algorithm reached the 3rd place on the 5-label classification task (sub-task C).
Tasks	Sentiment Analysis
Published	2017-05-03
URL	http://arxiv.org/abs/1705.01306v1
PDF	http://arxiv.org/pdf/1705.01306v1.pdf
PWC	https://paperswithcode.com/paper/amobee-at-semeval-2017-task-4-deep-learning
Repo
Framework

Data-Efficient Policy Evaluation Through Behavior Policy Search


Title	Data-Efficient Policy Evaluation Through Behavior Policy Search
Authors	Josiah P. Hanna, Philip S. Thomas, Peter Stone, Scott Niekum
Abstract	We consider the task of evaluating a policy for a Markov decision process (MDP). The standard unbiased technique for evaluating a policy is to deploy the policy and observe its performance. We show that the data collected from deploying a different policy, commonly called the behavior policy, can be used to produce unbiased estimates with lower mean squared error than this standard technique. We derive an analytic expression for the optimal behavior policy — the behavior policy that minimizes the mean squared error of the resulting estimates. Because this expression depends on terms that are unknown in practice, we propose a novel policy evaluation sub-problem, behavior policy search: searching for a behavior policy that reduces mean squared error. We present a behavior policy search algorithm and empirically demonstrate its effectiveness in lowering the mean squared error of policy performance estimates.
Tasks
Published	2017-06-12
URL	http://arxiv.org/abs/1706.03469v1
PDF	http://arxiv.org/pdf/1706.03469v1.pdf
PWC	https://paperswithcode.com/paper/data-efficient-policy-evaluation-through
Repo
Framework

Interacting Attention-gated Recurrent Networks for Recommendation


Title	Interacting Attention-gated Recurrent Networks for Recommendation
Authors	Wenjie Pei, Jie Yang, Zhu Sun, Jie Zhang, Alessandro Bozzon, David M. J. Tax
Abstract	Capturing the temporal dynamics of user preferences over items is important for recommendation. Existing methods mainly assume that all time steps in user-item interaction history are equally relevant to recommendation, which however does not apply in real-world scenarios where user-item interactions can often happen accidentally. More importantly, they learn user and item dynamics separately, thus failing to capture their joint effects on user-item interactions. To better model user and item dynamics, we present the Interacting Attention-gated Recurrent Network (IARN) which adopts the attention model to measure the relevance of each time step. In particular, we propose a novel attention scheme to learn the attention scores of user and item history in an interacting way, thus to account for the dependencies between user and item dynamics in shaping user-item interactions. By doing so, IARN can selectively memorize different time steps of a user’s history when predicting her preferences over different items. Our model can therefore provide meaningful interpretations for recommendation results, which could be further enhanced by auxiliary features. Extensive validation on real-world datasets shows that IARN consistently outperforms state-of-the-art methods.
Tasks
Published	2017-09-05
URL	http://arxiv.org/abs/1709.01532v2
PDF	http://arxiv.org/pdf/1709.01532v2.pdf
PWC	https://paperswithcode.com/paper/interacting-attention-gated-recurrent
Repo
Framework

Compact Model Representation for 3D Reconstruction


Title	Compact Model Representation for 3D Reconstruction
Authors	Jhony K. Pontes, Chen Kong, Anders Eriksson, Clinton Fookes, Sridha Sridharan, Simon Lucey
Abstract	3D reconstruction from 2D images is a central problem in computer vision. Recent works have been focusing on reconstruction directly from a single image. It is well known however that only one image cannot provide enough information for such a reconstruction. A prior knowledge that has been entertained are 3D CAD models due to its online ubiquity. A fundamental question is how to compactly represent millions of CAD models while allowing generalization to new unseen objects with fine-scaled geometry. We introduce an approach to compactly represent a 3D mesh. Our method first selects a 3D model from a graph structure by using a novel free-form deformation FFD 3D-2D registration, and then the selected 3D model is refined to best fit the image silhouette. We perform a comprehensive quantitative and qualitative analysis that demonstrates impressive dense and realistic 3D reconstruction from single images.
Tasks	3D Reconstruction
Published	2017-07-23
URL	http://arxiv.org/abs/1707.07360v1
PDF	http://arxiv.org/pdf/1707.07360v1.pdf
PWC	https://paperswithcode.com/paper/compact-model-representation-for-3d
Repo
Framework

Side Information in Robust Principal Component Analysis: Algorithms and Applications


Title	Side Information in Robust Principal Component Analysis: Algorithms and Applications
Authors	Niannan Xue, Yannis Panagakis, Stefanos Zafeiriou
Abstract	Robust Principal Component Analysis (RPCA) aims at recovering a low-rank subspace from grossly corrupted high-dimensional (often visual) data and is a cornerstone in many machine learning and computer vision applications. Even though RPCA has been shown to be very successful in solving many rank minimisation problems, there are still cases where degenerate or suboptimal solutions are obtained. This is likely to be remedied by taking into account of domain-dependent prior knowledge. In this paper, we propose two models for the RPCA problem with the aid of side information on the low-rank structure of the data. The versatility of the proposed methods is demonstrated by applying them to four applications, namely background subtraction, facial image denoising, face and facial expression recognition. Experimental results on synthetic and five real world datasets indicate the robustness and effectiveness of the proposed methods on these application domains, largely outperforming six previous approaches.
Tasks	Denoising, Facial Expression Recognition, Image Denoising
Published	2017-02-02
URL	http://arxiv.org/abs/1702.00648v2
PDF	http://arxiv.org/pdf/1702.00648v2.pdf
PWC	https://paperswithcode.com/paper/side-information-in-robust-principal
Repo
Framework

A Product Shape Congruity Measure via Entropy in Shape Scale Space


Title	A Product Shape Congruity Measure via Entropy in Shape Scale Space
Authors	Asli Genctav, Sibel Tari
Abstract	Product shape is one of the factors that trigger preference decisions of customers. Congruity of shape elements and deformation of shape from the prototype are two factors that are found to influence aesthetic response, hence preference. We propose a measure to indirectly quantify congruity of different parts of the shape and the degree to which the parts deviate from a sphere, i.e. our choice of the prototype, without explicitly defining parts and their relations. The basic signals and systems concept that we use is the entropy. Our measure attains its lowest value for a volume enclosed by a sphere. On one hand, deformations from the prototype cause an increase in the measure. On the other hand, as deformations create congruent parts, our measure decreases due to the attained harmony. Our preliminary experimental results are consistent with our expectations.
Tasks
Published	2017-09-10
URL	http://arxiv.org/abs/1709.03086v1
PDF	http://arxiv.org/pdf/1709.03086v1.pdf
PWC	https://paperswithcode.com/paper/a-product-shape-congruity-measure-via-entropy
Repo
Framework

Deep Visual Attention Prediction


Title	Deep Visual Attention Prediction
Authors	Wenguan Wang, Jianbing Shen
Abstract	In this work, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although Convolutional Neural Networks (CNNs) have made substantial improvement on human attention prediction, it is still needed to improve CNN based attention models by efficiently leveraging multi-scale features. Our visual attention network is proposed to capture hierarchical saliency information from deep, coarse layers with global saliency information to shallow, fine layers with local saliency response. Our model is based on a skip-layer network structure, which predicts human attention from multiple convolutional layers with various reception fields. Final saliency prediction is achieved via the cooperation of those global and local predictions. Our model is learned in a deep supervision manner, where supervision is directly fed into multi-level layers, instead of previous approaches of providing supervision only at the output layer and propagating this supervision back to earlier layers. Our model thus incorporates multi-level saliency predictions within a single network, which significantly decreases the redundancy of previous approaches of learning multiple network streams with different input scales. Extensive experimental analysis on various challenging benchmark datasets demonstrate our method yields state-of-the-art performance with competitive inference time.
Tasks	Saliency Prediction
Published	2017-05-07
URL	http://arxiv.org/abs/1705.02544v3
PDF	http://arxiv.org/pdf/1705.02544v3.pdf
PWC	https://paperswithcode.com/paper/deep-visual-attention-prediction
Repo
Framework

Mining Best Closed Itemsets for Projection-antimonotonic Constraints in Polynomial Time


Title	Mining Best Closed Itemsets for Projection-antimonotonic Constraints in Polynomial Time
Authors	Aleksey Buzmakov, Sergei O. Kuznetsov, Amedeo Napoli
Abstract	The exponential explosion of the set of patterns is one of the main challenges in pattern mining. This challenge is approached by introducing a constraint for pattern selection. One of the first constraints proposed in pattern mining is support (frequency) of a pattern in a dataset. Frequency is an anti-monotonic function, i.e., given an infrequent pattern, all its superpatterns are not frequent. However, many other constraints for pattern selection are neither monotonic nor anti-monotonic, which makes it difficult to generate patterns satisfying these constraints. In order to deal with nonmonotonic constraints we introduce the notion of “projection antimonotonicity” and SOFIA algorithm that allow generating best patterns for a class of nonmonotonic constraints. Cosine interest, robustness, stability of closed itemsets, and the associated delta-measure are among these constraints. SOFIA starts from light descriptions of transactions in dataset (a small set of items in the case of itemset description) and then iteratively adds more information to these descriptions (more items with indication of tidsets they describe).
Tasks
Published	2017-03-28
URL	http://arxiv.org/abs/1703.09513v1
PDF	http://arxiv.org/pdf/1703.09513v1.pdf
PWC	https://paperswithcode.com/paper/mining-best-closed-itemsets-for-projection
Repo
Framework

Optimality of Approximate Inference Algorithms on Stable Instances


Title	Optimality of Approximate Inference Algorithms on Stable Instances
Authors	Hunter Lang, David Sontag, Aravindan Vijayaraghavan
Abstract	Approximate algorithms for structured prediction problems—such as LP relaxations and the popular alpha-expansion algorithm (Boykov et al. 2001)—typically far exceed their theoretical performance guarantees on real-world instances. These algorithms often find solutions that are very close to optimal. The goal of this paper is to partially explain the performance of alpha-expansion and an LP relaxation algorithm on MAP inference in Ferromagnetic Potts models (FPMs). Our main results give stability conditions under which these two algorithms provably recover the optimal MAP solution. These theoretical results complement numerous empirical observations of good performance.
Tasks	Structured Prediction
Published	2017-11-06
URL	http://arxiv.org/abs/1711.02195v2
PDF	http://arxiv.org/pdf/1711.02195v2.pdf
PWC	https://paperswithcode.com/paper/optimality-of-approximate-inference
Repo
Framework

An Efficient Pseudo-likelihood Method for Sparse Binary Pairwise Markov Network Estimation


Title	An Efficient Pseudo-likelihood Method for Sparse Binary Pairwise Markov Network Estimation
Authors	Sinong Geng, Zhaobin Kuang, David Page
Abstract	The pseudo-likelihood method is one of the most popular algorithms for learning sparse binary pairwise Markov networks. In this paper, we formulate the $L_1$ regularized pseudo-likelihood problem as a sparse multiple logistic regression problem. In this way, many insights and optimization procedures for sparse logistic regression can be applied to the learning of discrete Markov networks. Specifically, we use the coordinate descent algorithm for generalized linear models with convex penalties, combined with strong screening rules, to solve the pseudo-likelihood problem with $L_1$ regularization. Therefore a substantial speedup without losing any accuracy can be achieved. Furthermore, this method is more stable than the node-wise logistic regression approach on unbalanced high-dimensional data when penalized by small regularization parameters. Thorough numerical experiments on simulated data and real world data demonstrate the advantages of the proposed method.
Tasks
Published	2017-02-27
URL	http://arxiv.org/abs/1702.08320v2
PDF	http://arxiv.org/pdf/1702.08320v2.pdf
PWC	https://paperswithcode.com/paper/an-efficient-pseudo-likelihood-method-for
Repo
Framework

10Sent: A Stable Sentiment Analysis Method Based on the Combination of Off-The-Shelf Approaches


Title	10Sent: A Stable Sentiment Analysis Method Based on the Combination of Off-The-Shelf Approaches
Authors	Philipe F. Melo, Daniel H. Dalip, Manoel M. Junior, Marcos A. Gonçalves, Fabrício Benevenuto
Abstract	Sentiment analysis has become a very important tool for analysis of social media data. There are several methods developed for this research field, many of them working very differently from each other, covering distinct aspects of the problem and disparate strategies. Despite the large number of existent techniques, there is no single one which fits well in all cases or for all data sources. Supervised approaches may be able to adapt to specific situations but they require manually labeled training, which is very cumbersome and expensive to acquire, mainly for a new application. In this context, in here, we propose to combine several very popular and effective state-of-the-practice sentiment analysis methods, by means of an unsupervised bootstrapped strategy for polarity classification. One of our main goals is to reduce the large variability (lack of stability) of the unsupervised methods across different domains (datasets). Our solution was thoroughly tested considering thirteen different datasets in several domains such as opinions, comments, and social media. The experimental results demonstrate that our combined method (aka, 10SENT) improves the effectiveness of the classification task, but more importantly, it solves a key problem in the field. It is consistently among the best methods in many data types, meaning that it can produce the best (or close to best) results in almost all considered contexts, without any additional costs (e.g., manual labeling). Our self-learning approach is also very independent of the base methods, which means that it is highly extensible to incorporate any new additional method that can be envisioned in the future. Finally, we also investigate a transfer learning approach for sentiment analysis as a means to gather additional (unsupervised) information for the proposed approach and we show the potential of this technique to improve our results.
Tasks	Sentiment Analysis, Transfer Learning
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07915v1
PDF	http://arxiv.org/pdf/1711.07915v1.pdf
PWC	https://paperswithcode.com/paper/10sent-a-stable-sentiment-analysis-method
Repo
Framework

Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent


Title	Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent
Authors	Zhilin Yang, Saizheng Zhang, Jack Urbanek, Will Feng, Alexander H. Miller, Arthur Szlam, Douwe Kiela, Jason Weston
Abstract	Contrary to most natural language processing research, which makes use of static datasets, humans learn language interactively, grounded in an environment. In this work we propose an interactive learning procedure called Mechanical Turker Descent (MTD) and use it to train agents to execute natural language commands grounded in a fantasy text adventure game. In MTD, Turkers compete to train better agents in the short term, and collaborate by sharing their agents’ skills in the long term. This results in a gamified, engaging experience for the Turkers and a better quality teaching signal for the agents compared to static datasets, as the Turkers naturally adapt the training data to the agent’s abilities.
Tasks
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07950v3
PDF	http://arxiv.org/pdf/1711.07950v3.pdf
PWC	https://paperswithcode.com/paper/mastering-the-dungeon-grounded-language
Repo
Framework

Interacting with Acoustic Simulation and Fabrication


Title	Interacting with Acoustic Simulation and Fabrication
Authors	Dingzeyu Li
Abstract	Incorporating accurate physics-based simulation into interactive design tools is challenging. However, adding the physics accurately becomes crucial to several emerging technologies. For example, in virtual/augmented reality (VR/AR) videos, the faithful reproduction of surrounding audios is required to bring the immersion to the next level. Similarly, as personal fabrication is made possible with accessible 3D printers, more intuitive tools that respect the physical constraints can help artists to prototype designs. One main hurdle is the sheer amount of computation complexity to accurately reproduce the real-world phenomena through physics-based simulation. In my thesis research, I develop interactive tools that implement efficient physics-based simulation algorithms for automatic optimization and intuitive user interaction.
Tasks
Published	2017-08-09
URL	http://arxiv.org/abs/1708.02895v2
PDF	http://arxiv.org/pdf/1708.02895v2.pdf
PWC	https://paperswithcode.com/paper/interacting-with-acoustic-simulation-and
Repo
Framework

Classification via Tensor Decompositions of Echo State Networks


Title	Classification via Tensor Decompositions of Echo State Networks
Authors	Ashley Prater
Abstract	This work introduces a tensor-based method to perform supervised classification on spatiotemporal data processed in an echo state network. Typically when performing supervised classification tasks on data processed in an echo state network, the entire collection of hidden layer node states from the training dataset is shaped into a matrix, allowing one to use standard linear algebra techniques to train the output layer. However, the collection of hidden layer states is multidimensional in nature, and representing it as a matrix may lead to undesirable numerical conditions or loss of spatial and temporal correlations in the data. This work proposes a tensor-based supervised classification method on echo state network data that preserves and exploits the multidimensional nature of the hidden layer states. The method, which is based on orthogonal Tucker decompositions of tensors, is compared with the standard linear output weight approach in several numerical experiments on both synthetic and natural data. The results show that the tensor-based approach tends to outperform the standard approach in terms of classification accuracy.
Tasks
Published	2017-08-23
URL	http://arxiv.org/abs/1708.07147v1
PDF	http://arxiv.org/pdf/1708.07147v1.pdf
PWC	https://paperswithcode.com/paper/classification-via-tensor-decompositions-of
Repo
Framework