October 16, 2019

3243 words 16 mins read

Paper Group ANR 1048

Growing Story Forest Online from Massive Breaking News. Sentiment Analysis of Arabic Tweets: Feature Engineering and A Hybrid Approach. High Dimensional Spaces, Deep Learning and Adversarial Examples. Analysis of Noise Contrastive Estimation from the Perspective of Asymptotic Variance. Comparison of Classical and Nonlinear Models for Short-Term Ele …

Growing Story Forest Online from Massive Breaking News


Title	Growing Story Forest Online from Massive Breaking News
Authors	Bang Liu, Di Niu, Kunfeng Lai, Linglong Kong, Yu Xu
Abstract	We describe our experience of implementing a news content organization system at Tencent that discovers events from vast streams of breaking news and evolves news story structures in an online fashion. Our real-world system has distinct requirements in contrast to previous studies on topic detection and tracking (TDT) and event timeline or graph generation, in that we 1) need to accurately and quickly extract distinguishable events from massive streams of long text documents that cover diverse topics and contain highly redundant information, and 2) must develop the structures of event stories in an online manner, without repeatedly restructuring previously formed stories, in order to guarantee a consistent user viewing experience. In solving these challenges, we propose Story Forest, a set of online schemes that automatically clusters streaming documents into events, while connecting related events in growing trees to tell evolving stories. We conducted extensive evaluation based on 60 GB of real-world Chinese news data, although our ideas are not language-dependent and can easily be extended to other languages, through detailed pilot user experience studies. The results demonstrate the superior capability of Story Forest to accurately identify events and organize news text into a logical structure that is appealing to human readers, compared to multiple existing algorithm frameworks.
Tasks	Graph Generation
Published	2018-03-01
URL	http://arxiv.org/abs/1803.00189v1
PDF	http://arxiv.org/pdf/1803.00189v1.pdf
PWC	https://paperswithcode.com/paper/growing-story-forest-online-from-massive
Repo
Framework

Sentiment Analysis of Arabic Tweets: Feature Engineering and A Hybrid Approach


Title	Sentiment Analysis of Arabic Tweets: Feature Engineering and A Hybrid Approach
Authors	Nora Al-Twairesh, Hend Al-Khalifa, AbdulMalik Alsalman, Yousef Al-Ohali
Abstract	Sentiment Analysis in Arabic is a challenging task due to the rich morphology of the language. Moreover, the task is further complicated when applied to Twitter data that is known to be highly informal and noisy. In this paper, we develop a hybrid method for sentiment analysis for Arabic tweets for a specific Arabic dialect which is the Saudi Dialect. Several features were engineered and evaluated using a feature backward selection method. Then a hybrid method that combines a corpus-based and lexicon-based method was developed for several classification models (two-way, three-way, four-way). The best F1-score for each of these models was (69.9,61.63,55.07) respectively.
Tasks	Feature Engineering, Sentiment Analysis
Published	2018-05-22
URL	http://arxiv.org/abs/1805.08533v1
PDF	http://arxiv.org/pdf/1805.08533v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-analysis-of-arabic-tweets-feature
Repo
Framework

High Dimensional Spaces, Deep Learning and Adversarial Examples


Title	High Dimensional Spaces, Deep Learning and Adversarial Examples
Authors	Simant Dube
Abstract	In this paper, we analyze deep learning from a mathematical point of view and derive several novel results. The results are based on intriguing mathematical properties of high dimensional spaces. We first look at perturbation based adversarial examples and show how they can be understood using topological and geometrical arguments in high dimensions. We point out mistake in an argument presented in prior published literature, and we present a more rigorous, general and correct mathematical result to explain adversarial examples in terms of topology of image manifolds. Second, we look at optimization landscapes of deep neural networks and examine the number of saddle points relative to that of local minima. Third, we show how multiresolution nature of images explains perturbation based adversarial examples in form of a stronger result. Our results state that expectation of $L_2$-norm of adversarial perturbations is $O\left(\frac{1}{\sqrt{n}}\right)$ and therefore shrinks to 0 as image resolution $n$ becomes arbitrarily large. Finally, by incorporating the parts-whole manifold learning hypothesis for natural images, we investigate the working of deep neural networks and root causes of adversarial examples and discuss how future improvements can be made and how adversarial examples can be eliminated.
Tasks
Published	2018-01-02
URL	http://arxiv.org/abs/1801.00634v5
PDF	http://arxiv.org/pdf/1801.00634v5.pdf
PWC	https://paperswithcode.com/paper/high-dimensional-spaces-deep-learning-and
Repo
Framework

Analysis of Noise Contrastive Estimation from the Perspective of Asymptotic Variance


Title	Analysis of Noise Contrastive Estimation from the Perspective of Asymptotic Variance
Authors	Masatoshi Uehara, Takeru Matsuda, Fumiyasu Komaki
Abstract	There are many models, often called unnormalized models, whose normalizing constants are not calculated in closed form. Maximum likelihood estimation is not directly applicable to unnormalized models. Score matching, contrastive divergence method, pseudo-likelihood, Monte Carlo maximum likelihood, and noise contrastive estimation (NCE) are popular methods for estimating parameters of such models. In this paper, we focus on NCE. The estimator derived from NCE is consistent and asymptotically normal because it is an M-estimator. NCE characteristically uses an auxiliary distribution to calculate the normalizing constant in the same spirit of the importance sampling. In addition, there are several candidates as objective functions of NCE. We focus on how to reduce asymptotic variance. First, we propose a method for reducing asymptotic variance by estimating the parameters of the auxiliary distribution. Then, we determine the form of the objective functions, where the asymptotic variance takes the smallest values in the original estimator class and the proposed estimator classes. We further analyze the robustness of the estimator.
Tasks
Published	2018-08-24
URL	http://arxiv.org/abs/1808.07983v1
PDF	http://arxiv.org/pdf/1808.07983v1.pdf
PWC	https://paperswithcode.com/paper/analysis-of-noise-contrastive-estimation-from
Repo
Framework

Comparison of Classical and Nonlinear Models for Short-Term Electricity Price Prediction


Title	Comparison of Classical and Nonlinear Models for Short-Term Electricity Price Prediction
Authors	Elaheh Fata, Igor Kadota, Ian Schneider
Abstract	Electricity is bought and sold in wholesale markets at prices that fluctuate significantly. Short-term forecasting of electricity prices is an important endeavor because it helps electric utilities control risk and because it influences competitive strategy for generators. As the “smart grid” grows, short-term price forecasts are becoming an important input to bidding and control algorithms for battery operators and demand response aggregators. While the statistics and machine learning literature offers many proposed methods for electricity price prediction, there is no consensus supporting a single best approach. We test two contrasting machine learning approaches for predicting electricity prices, regression decision trees and recurrent neural networks (RNNs), and compare them to a more traditional ARIMA implementation. We conduct the analysis on a challenging dataset of electricity prices from ERCOT, in Texas, where price fluctuation is especially high. We find that regression decision trees in particular achieves high performance compared to the other methods, suggesting that regression trees should be more carefully considered for electricity price forecasting.
Tasks
Published	2018-05-02
URL	http://arxiv.org/abs/1805.05431v1
PDF	http://arxiv.org/pdf/1805.05431v1.pdf
PWC	https://paperswithcode.com/paper/comparison-of-classical-and-nonlinear-models
Repo
Framework

Learning to Read by Spelling: Towards Unsupervised Text Recognition


Title	Learning to Read by Spelling: Towards Unsupervised Text Recognition
Authors	Ankush Gupta, Andrea Vedaldi, Andrew Zisserman
Abstract	This work presents a method for visual text recognition without using any paired supervisory data. We formulate the text recognition task as one of aligning the conditional distribution of strings predicted from given text images, with lexically valid strings sampled from target corpora. This enables fully automated, and unsupervised learning from just line-level text-images, and unpaired text-string samples, obviating the need for large aligned datasets. We present detailed analysis for various aspects of the proposed method, namely - (1) impact of the length of training sequences on convergence, (2) relation between character frequencies and the order in which they are learnt, (3) generalisation ability of our recognition network to inputs of arbitrary lengths, and (4) impact of varying the text corpus on recognition accuracy. Finally, we demonstrate excellent text recognition accuracy on both synthetically generated text images, and scanned images of real printed books, using no labelled training examples.
Tasks
Published	2018-09-23
URL	http://arxiv.org/abs/1809.08675v2
PDF	http://arxiv.org/pdf/1809.08675v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-read-by-spelling-towards
Repo
Framework

Expectation Optimization with Probabilistic Guarantees in POMDPs with Discounted-sum Objectives


Title	Expectation Optimization with Probabilistic Guarantees in POMDPs with Discounted-sum Objectives
Authors	Krishnendu Chatterjee, Adrián Elgyütt, Petr Novotný, Owen Rouillé
Abstract	Partially-observable Markov decision processes (POMDPs) with discounted-sum payoff are a standard framework to model a wide range of problems related to decision making under uncertainty. Traditionally, the goal has been to obtain policies that optimize the expectation of the discounted-sum payoff. A key drawback of the expectation measure is that even low probability events with extreme payoff can significantly affect the expectation, and thus the obtained policies are not necessarily risk-averse. An alternate approach is to optimize the probability that the payoff is above a certain threshold, which allows obtaining risk-averse policies, but ignores optimization of the expectation. We consider the expectation optimization with probabilistic guarantee (EOPG) problem, where the goal is to optimize the expectation ensuring that the payoff is above a given threshold with at least a specified probability. We present several results on the EOPG problem, including the first algorithm to solve it.
Tasks	Decision Making, Decision Making Under Uncertainty
Published	2018-04-27
URL	http://arxiv.org/abs/1804.10601v2
PDF	http://arxiv.org/pdf/1804.10601v2.pdf
PWC	https://paperswithcode.com/paper/expectation-optimization-with-probabilistic
Repo
Framework

Inferring the time-varying functional connectivity of large-scale computer networks from emitted events


Title	Inferring the time-varying functional connectivity of large-scale computer networks from emitted events
Authors	Antoine Messager, George Parisis, Istvan Z Kiss, Robert Harper, Phil Tee, Luc Berthouze
Abstract	We consider the problem of inferring the functional connectivity of a large-scale computer network from sparse time series of events emitted by its nodes. We do so under the following three domain-specific constraints: (a) non-stationarity of the functional connectivity due to unknown temporal changes in the network, (b) sparsity of the time-series of events that limits the effectiveness of classical correlation-based analysis, and (c) lack of an explicit model describing how events propagate through the network. Under the assumption that the probability of two nodes being functionally connected correlates with the mean delay between their respective events, we develop an inference method whose output is an undirected weighted network where the weight of an edge between two nodes denotes the probability of these nodes being functionally connected. Using a combination of windowing and convolution to calculate at each time window a score quantifying the likelihood of a pair of nodes emitting events in quick succession, we develop a model of time-varying connectivity whose parameters are determined by maximising the model’s predictive power from one time window to the next. To assess the effectiveness of our inference method, we construct synthetic data for which ground truth is available and use these data to benchmark our approach against three state-of-the-art inference methods. We conclude by discussing its application to data from a real-world large-scale computer network.
Tasks	Time Series
Published	2018-02-12
URL	http://arxiv.org/abs/1802.04036v1
PDF	http://arxiv.org/pdf/1802.04036v1.pdf
PWC	https://paperswithcode.com/paper/inferring-the-time-varying-functional
Repo
Framework

A real-time and unsupervised face Re-Identification system for Human-Robot Interaction


Title	A real-time and unsupervised face Re-Identification system for Human-Robot Interaction
Authors	Yujiang Wang, Jie Shen, Stavros Petridis, Maja Pantic
Abstract	In the context of Human-Robot Interaction (HRI), face Re-Identification (face Re-ID) aims to verify if certain detected faces have already been observed by robots. The ability of distinguishing between different users is crucial in social robots as it will enable the robot to tailor the interaction strategy toward the users’ individual preferences. So far face recognition research has achieved great success, however little attention has been paid to the realistic applications of Face Re-ID in social robots. In this paper, we present an effective and unsupervised face Re-ID system which simultaneously re-identifies multiple faces for HRI. This Re-ID system employs Deep Convolutional Neural Networks to extract features, and an online clustering algorithm to determine the face’s ID. Its performance is evaluated on two datasets: the TERESA video dataset collected by the TERESA robot, and the YouTube Face Dataset (YTF Dataset). We demonstrate that the optimised combination of techniques achieves an overall 93.55% accuracy on TERESA dataset and an overall 90.41% accuracy on YTF dataset. We have implemented the proposed method into a software module in the HCI^2 Framework for it to be further integrated into the TERESA robot, and has achieved real-time performance at 10~26 Frames per second.
Tasks	Face Recognition
Published	2018-04-10
URL	http://arxiv.org/abs/1804.03547v2
PDF	http://arxiv.org/pdf/1804.03547v2.pdf
PWC	https://paperswithcode.com/paper/a-real-time-and-unsupervised-face-re
Repo
Framework

Multi-Expert Gender Classification on Age Group by Integrating Deep Neural Networks


Title	Multi-Expert Gender Classification on Age Group by Integrating Deep Neural Networks
Authors	Jun Beom Kho
Abstract	Generally, facial age variations affect gender classification accuracy significantly, because facial shape and skin texture change as they grow old. This requires re-examination on the gender classification system to consider facial age information. In this paper, we propose Multi-expert Gender Classification on Age Group (MGA), an end-to-end multi-task learning schemes of age estimation and gender classification. First, two types of deep neural networks are utilized; Convolutional Appearance Network (CAN) for facial appearance feature and Deep Geometry Network (DGN) for facial geometric feature. Then, CAN and DGN are integrated by the proposed model integration strategy and fine-tuned in order to improve age and gender classification accuracy. The facial images are categorized into one of three age groups (young, adult and elder group) based on their estimated age, and the system makes a gender prediction according to average fusion strategy of three gender classification experts, which are trained to fit gender characteristics of each age group. Rigorous experimental results conducted on the challenging databases suggest that the proposed MGA outperforms several state-of-art researches with smaller computational cost.
Tasks	Age And Gender Classification, Age Estimation, Gender Prediction, Multi-Task Learning
Published	2018-09-06
URL	http://arxiv.org/abs/1809.01990v2
PDF	http://arxiv.org/pdf/1809.01990v2.pdf
PWC	https://paperswithcode.com/paper/multi-expert-gender-classification-on-age
Repo
Framework

Multimodal Recurrent Neural Networks with Information Transfer Layers for Indoor Scene Labeling


Title	Multimodal Recurrent Neural Networks with Information Transfer Layers for Indoor Scene Labeling
Authors	Abrar H. Abdulnabi, Bing Shuai, Zhen Zuo, Lap-Pui Chau, Gang Wang
Abstract	This paper proposes a new method called Multimodal RNNs for RGB-D scene semantic segmentation. It is optimized to classify image pixels given two input sources: RGB color channels and Depth maps. It simultaneously performs training of two recurrent neural networks (RNNs) that are crossly connected through information transfer layers, which are learnt to adaptively extract relevant cross-modality features. Each RNN model learns its representations from its own previous hidden states and transferred patterns from the other RNNs previous hidden states; thus, both model-specific and crossmodality features are retained. We exploit the structure of quad-directional 2D-RNNs to model the short and long range contextual information in the 2D input image. We carefully designed various baselines to efficiently examine our proposed model structure. We test our Multimodal RNNs method on popular RGB-D benchmarks and show how it outperforms previous methods significantly and achieves competitive results with other state-of-the-art works.
Tasks	Scene Labeling, Semantic Segmentation
Published	2018-03-13
URL	http://arxiv.org/abs/1803.04687v1
PDF	http://arxiv.org/pdf/1803.04687v1.pdf
PWC	https://paperswithcode.com/paper/multimodal-recurrent-neural-networks-with
Repo
Framework

Boosting Self-Supervised Learning via Knowledge Transfer


Title	Boosting Self-Supervised Learning via Knowledge Transfer
Authors	Mehdi Noroozi, Ananth Vinjimoor, Paolo Favaro, Hamed Pirsiavash
Abstract	In self-supervised learning, one trains a model to solve a so-called pretext task on a dataset without the need for human annotation. The main objective, however, is to transfer this model to a target domain and task. Currently, the most effective transfer strategy is fine-tuning, which restricts one to use the same model or parts thereof for both pretext and target tasks. In this paper, we present a novel framework for self-supervised learning that overcomes limitations in designing and comparing different tasks, models, and data domains. In particular, our framework decouples the structure of the self-supervised model from the final task-specific fine-tuned model. This allows us to: 1) quantitatively assess previously incompatible models including handcrafted features; 2) show that deeper neural network models can learn better representations from the same pretext task; 3) transfer knowledge learned with a deep model to a shallower one and thus boost its learning. We use this framework to design a novel self-supervised task, which achieves state-of-the-art performance on the common benchmarks in PASCAL VOC 2007, ILSVRC12 and Places by a significant margin. Our learned features shrink the mAP gap between models trained via self-supervised learning and supervised learning from 5.9% to 2.6% in object detection on PASCAL VOC 2007.
Tasks	Object Detection, Transfer Learning
Published	2018-05-01
URL	http://arxiv.org/abs/1805.00385v1
PDF	http://arxiv.org/pdf/1805.00385v1.pdf
PWC	https://paperswithcode.com/paper/boosting-self-supervised-learning-via
Repo
Framework

CuisineNet: Food Attributes Classification using Multi-scale Convolution Network


Title	CuisineNet: Food Attributes Classification using Multi-scale Convolution Network
Authors	Md. Mostafa Kamal Sarker, Mohammed Jabreel, Hatem A. Rashwan, Syeda Furruka Banu, Antonio Moreno, Petia Radeva, Domenec Puig
Abstract	Diversity of food and its attributes represents the culinary habits of peoples from different countries. Thus, this paper addresses the problem of identifying food culture of people around the world and its flavor by classifying two main food attributes, cuisine and flavor. A deep learning model based on multi-scale convotuional networks is proposed for extracting more accurate features from input images. The aggregation of multi-scale convolution layers with different kernel size is also used for weighting the features results from different scales. In addition, a joint loss function based on Negative Log Likelihood (NLL) is used to fit the model probability to multi labeled classes for multi-modal classification task. Furthermore, this work provides a new dataset for food attributes, so-called Yummly48K, extracted from the popular food website, Yummly. Our model is assessed on the constructed Yummly48K dataset. The experimental results show that our proposed method yields 65% and 62% average F1 score on validation and test set which outperforming the state-of-the-art models.
Tasks
Published	2018-05-30
URL	http://arxiv.org/abs/1805.12081v2
PDF	http://arxiv.org/pdf/1805.12081v2.pdf
PWC	https://paperswithcode.com/paper/cuisinenet-food-attributes-classification
Repo
Framework

Achieving Human Parity on Automatic Chinese to English News Translation


Title	Achieving Human Parity on Automatic Chinese to English News Translation
Authors	Hany Hassan, Anthony Aue, Chang Chen, Vishal Chowdhary, Jonathan Clark, Christian Federmann, Xuedong Huang, Marcin Junczys-Dowmunt, William Lewis, Mu Li, Shujie Liu, Tie-Yan Liu, Renqian Luo, Arul Menezes, Tao Qin, Frank Seide, Xu Tan, Fei Tian, Lijun Wu, Shuangzhi Wu, Yingce Xia, Dongdong Zhang, Zhirui Zhang, Ming Zhou
Abstract	Machine translation has made rapid advances in recent years. Millions of people are using it today in online translation systems and mobile applications in order to communicate across language barriers. The question naturally arises whether such systems can approach or achieve parity with human translations. In this paper, we first address the problem of how to define and accurately measure human parity in translation. We then describe Microsoft’s machine translation system and measure the quality of its translations on the widely used WMT 2017 news translation task from Chinese to English. We find that our latest neural machine translation system has reached a new state-of-the-art, and that the translation quality is at human parity when compared to professional human translations. We also find that it significantly exceeds the quality of crowd-sourced non-professional translations.
Tasks	Machine Translation
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05567v2
PDF	http://arxiv.org/pdf/1803.05567v2.pdf
PWC	https://paperswithcode.com/paper/achieving-human-parity-on-automatic-chinese
Repo
Framework

Learning Multiple Categories on Deep Convolution Networks


Title	Learning Multiple Categories on Deep Convolution Networks
Authors	Mohamed Hajaj, Duncan Gillies
Abstract	Deep convolution networks have proved very successful with big datasets such as the 1000-classes ImageNet. Results show that the error rate increases slowly as the size of the dataset increases. Experiments presented here may explain why these networks are very effective in solving big recognition problems. If the big task is made up of multiple smaller tasks, then the results show the ability of deep convolution networks to decompose the complex task into a number of smaller tasks and to learn them simultaneously. The results show that the performance of solving the big task on a single network is very close to the average performance of solving each of the smaller tasks on a separate network. Experiments also show the advantage of using task specific or category labels in combination with class labels.
Tasks
Published	2018-02-21
URL	http://arxiv.org/abs/1802.07672v1
PDF	http://arxiv.org/pdf/1802.07672v1.pdf
PWC	https://paperswithcode.com/paper/learning-multiple-categories-on-deep
Repo
Framework