October 19, 2019

3284 words 16 mins read

Paper Group ANR 187

Automatically Detecting Self-Reported Birth Defect Outcomes on Twitter for Large-scale Epidemiological Research. Faster k-Medoids Clustering: Improving the PAM, CLARA, and CLARANS Algorithms. Probabilistic Multilevel Clustering via Composite Transportation Distance. Exploiting Deep Learning for Persian Sentiment Analysis. Dynamic Multivariate Funct …

Automatically Detecting Self-Reported Birth Defect Outcomes on Twitter for Large-scale Epidemiological Research


Title	Automatically Detecting Self-Reported Birth Defect Outcomes on Twitter for Large-scale Epidemiological Research
Authors	Ari Z. Klein, Abeed Sarker, Davy Weissenbacher, Graciela Gonzalez-Hernandez
Abstract	In recent work, we identified and studied a small cohort of Twitter users whose pregnancies with birth defect outcomes could be observed via their publicly available tweets. Exploiting social media’s large-scale potential to complement the limited methods for studying birth defects, the leading cause of infant mortality, depends on the further development of automatic methods. The primary objective of this study was to take the first step towards scaling the use of social media for observing pregnancies with birth defect outcomes, namely, developing methods for automatically detecting tweets by users reporting their birth defect outcomes. We annotated and pre-processed approximately 23,000 tweets that mention birth defects in order to train and evaluate supervised machine learning algorithms, including feature-engineered and deep learning-based classifiers. We also experimented with various under-sampling and over-sampling approaches to address the class imbalance. A Support Vector Machine (SVM) classifier trained on the original, imbalanced data set, with n-grams, word clusters, and structural features, achieved the best baseline performance for the positive classes: an F1-score of 0.65 for the “defect” class and 0.51 for the “possible defect” class. Our contributions include (i) natural language processing (NLP) and supervised machine learning methods for automatically detecting tweets by users reporting their birth defect outcomes, (ii) a comparison of feature-engineered and deep learning-based classifiers trained on imbalanced, under-sampled, and over-sampled data, and (iii) an error analysis that could inform classification improvements using our publicly available corpus. Future work will focus on automating user-level analyses for cohort inclusion.
Tasks
Published	2018-10-22
URL	http://arxiv.org/abs/1810.09506v1
PDF	http://arxiv.org/pdf/1810.09506v1.pdf
PWC	https://paperswithcode.com/paper/automatically-detecting-self-reported-birth
Repo
Framework

Faster k-Medoids Clustering: Improving the PAM, CLARA, and CLARANS Algorithms


Title	Faster k-Medoids Clustering: Improving the PAM, CLARA, and CLARANS Algorithms
Authors	Erich Schubert, Peter J. Rousseeuw
Abstract	Clustering non-Euclidean data is difficult, and one of the most used algorithms besides hierarchical clustering is the popular algorithm Partitioning Around Medoids (PAM), also simply referred to as k-medoids. In Euclidean geometry the mean-as used in k-means-is a good estimator for the cluster center, but this does not hold for arbitrary dissimilarities. PAM uses the medoid instead, the object with the smallest dissimilarity to all others in the cluster. This notion of centrality can be used with any (dis-)similarity, and thus is of high relevance to many domains such as biology that require the use of Jaccard, Gower, or more complex distances. A key issue with PAM is its high run time cost. We propose modifications to the PAM algorithm to achieve an O(k)-fold speedup in the second SWAP phase of the algorithm, but will still find the same results as the original PAM algorithm. If we slightly relax the choice of swaps performed (at comparable quality), we can further accelerate the algorithm by performing up to k swaps in each iteration. With the substantially faster SWAP, we can now also explore alternative strategies for choosing the initial medoids. We also show how the CLARA and CLARANS algorithms benefit from these modifications. It can easily be combined with earlier approaches to use PAM and CLARA on big data (some of which use PAM as a subroutine, hence can immediately benefit from these improvements), where the performance with high k becomes increasingly important. In experiments on real data with k=100, we observed a 200-fold speedup compared to the original PAM SWAP algorithm, making PAM applicable to larger data sets as long as we can afford to compute a distance matrix, and in particular to higher k (at k=2, the new SWAP was only 1.5 times faster, as the speedup is expected to increase with k).
Tasks
Published	2018-10-12
URL	https://arxiv.org/abs/1810.05691v4
PDF	https://arxiv.org/pdf/1810.05691v4.pdf
PWC	https://paperswithcode.com/paper/faster-k-medoids-clustering-improving-the-pam
Repo
Framework

Probabilistic Multilevel Clustering via Composite Transportation Distance


Title	Probabilistic Multilevel Clustering via Composite Transportation Distance
Authors	Nhat Ho, Viet Huynh, Dinh Phung, Michael I. Jordan
Abstract	We propose a novel probabilistic approach to multilevel clustering problems based on composite transportation distance, which is a variant of transportation distance where the underlying metric is Kullback-Leibler divergence. Our method involves solving a joint optimization problem over spaces of probability measures to simultaneously discover grouping structures within groups and among groups. By exploiting the connection of our method to the problem of finding composite transportation barycenters, we develop fast and efficient optimization algorithms even for potentially large-scale multilevel datasets. Finally, we present experimental results with both synthetic and real data to demonstrate the efficiency and scalability of the proposed approach.
Tasks
Published	2018-10-29
URL	http://arxiv.org/abs/1810.11911v1
PDF	http://arxiv.org/pdf/1810.11911v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-multilevel-clustering-via
Repo
Framework

Exploiting Deep Learning for Persian Sentiment Analysis


Title	Exploiting Deep Learning for Persian Sentiment Analysis
Authors	Kia Dashtipour, Mandar Gogate, Ahsan Adeel, Cosimo Ieracitano, Hadi Larijani, Amir Hussain
Abstract	The rise of social media is enabling people to freely express their opinions about products and services. The aim of sentiment analysis is to automatically determine subject’s sentiment (e.g., positive, negative, or neutral) towards a particular aspect such as topic, product, movie, news etc. Deep learning has recently emerged as a powerful machine learning technique to tackle a growing demand of accurate sentiment analysis. However, limited work has been conducted to apply deep learning algorithms to languages other than English, such as Persian. In this work, two deep learning models (deep autoencoders and deep convolutional neural networks (CNNs)) are developed and applied to a novel Persian movie reviews dataset. The proposed deep learning models are analyzed and compared with the state-of-the-art shallow multilayer perceptron (MLP) based machine learning model. Simulation results demonstrate the enhanced performance of deep learning over state-of-the-art MLP.
Tasks	Sentiment Analysis
Published	2018-08-15
URL	http://arxiv.org/abs/1808.05077v1
PDF	http://arxiv.org/pdf/1808.05077v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-deep-learning-for-persian
Repo
Framework

Dynamic Multivariate Functional Data Modeling via Sparse Subspace Learning


Title	Dynamic Multivariate Functional Data Modeling via Sparse Subspace Learning
Authors	Chen Zhang, Hao Yan, Seungho Lee, Jianjun Shi
Abstract	Multivariate functional data from a complex system are naturally high-dimensional and have complex cross-correlation structure. The complexity of data structure can be observed as that (1) some functions are strongly correlated with similar features, while some others may have almost no cross-correlations with quite diverse features; and (2) the cross-correlation structure may also change over time due to the system evolution. With this regard, this paper presents a dynamic subspace learning method for multivariate functional data modeling. In particular, we consider different functions come from different subspaces, and only functions of the same subspace have cross-correlations with each other. The subspaces can be automatically formulated and learned by reformatting the problem as a sparse regression. By allowing but regularizing the regression change over time, we can describe the cross-correlation dynamics. The model can be efficiently estimated by the fast iterative shrinkage-thresholding algorithm (FISTA), and the features of every subspace can be extracted using the smooth multi-channel functional PCA. Numerical studies together with case studies demonstrate the efficiency and applicability of the proposed methodology.
Tasks
Published	2018-04-11
URL	http://arxiv.org/abs/1804.03797v1
PDF	http://arxiv.org/pdf/1804.03797v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-multivariate-functional-data-modeling
Repo
Framework

Recurrent Neural Networks for Person Re-identification Revisited


Title	Recurrent Neural Networks for Person Re-identification Revisited
Authors	Jean-Baptiste Boin, Andre Araujo, Bernd Girod
Abstract	The task of person re-identification has recently received rising attention due to the high performance achieved by new methods based on deep learning. In particular, in the context of video-based re-identification, many state-of-the-art works have explored the use of Recurrent Neural Networks (RNNs) to process input sequences. In this work, we revisit this tool by deriving an approximation which reveals the small effect of recurrent connections, leading to a much simpler feed-forward architecture. Using the same parameters as the recurrent version, our proposed feed-forward architecture obtains very similar accuracy. More importantly, our model can be combined with a new training process to significantly improve re-identification performance. Our experiments demonstrate that the proposed models converge substantially faster than recurrent ones, with accuracy improvements by up to 5% on two datasets. The performance achieved is better or on par with other RNN-based person re-identification techniques.
Tasks	Person Re-Identification
Published	2018-04-10
URL	http://arxiv.org/abs/1804.03281v1
PDF	http://arxiv.org/pdf/1804.03281v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-neural-networks-for-person-re
Repo
Framework

Scenic: A Language for Scenario Specification and Scene Generation


Title	Scenic: A Language for Scenario Specification and Scene Generation
Authors	Daniel J. Fremont, Tommaso Dreossi, Shromona Ghosh, Xiangyu Yue, Alberto L. Sangiovanni-Vincentelli, Sanjit A. Seshia
Abstract	We propose a new probabilistic programming language for the design and analysis of perception systems, especially those based on machine learning. Specifically, we consider the problems of training a perception system to handle rare events, testing its performance under different conditions, and debugging failures. We show how a probabilistic programming language can help address these problems by specifying distributions encoding interesting types of inputs and sampling these to generate specialized training and test sets. More generally, such languages can be used for cyber-physical systems and robotics to write environment models, an essential prerequisite to any formal analysis. In this paper, we focus on systems like autonomous cars and robots, whose environment is a “scene”, a configuration of physical objects and agents. We design a domain-specific language, Scenic, for describing “scenarios” that are distributions over scenes. As a probabilistic programming language, Scenic allows assigning distributions to features of the scene, as well as declaratively imposing hard and soft constraints over the scene. We develop specialized techniques for sampling from the resulting distribution, taking advantage of the structure provided by Scenic’s domain-specific syntax. Finally, we apply Scenic in a case study on a convolutional neural network designed to detect cars in road images, improving its performance beyond that achieved by state-of-the-art synthetic data generation methods.
Tasks	Probabilistic Programming, Scene Generation, Synthetic Data Generation
Published	2018-09-25
URL	https://arxiv.org/abs/1809.09310v2
PDF	https://arxiv.org/pdf/1809.09310v2.pdf
PWC	https://paperswithcode.com/paper/scenic-language-based-scene-generation
Repo
Framework

Learning to Extract Coherent Summary via Deep Reinforcement Learning


Title	Learning to Extract Coherent Summary via Deep Reinforcement Learning
Authors	Yuxiang Wu, Baotian Hu
Abstract	Coherence plays a critical role in producing a high-quality summary from a document. In recent years, neural extractive summarization is becoming increasingly attractive. However, most of them ignore the coherence of summaries when extracting sentences. As an effort towards extracting coherent summaries, we propose a neural coherence model to capture the cross-sentence semantic and syntactic coherence patterns. The proposed neural coherence model obviates the need for feature engineering and can be trained in an end-to-end fashion using unlabeled data. Empirical results show that the proposed neural coherence model can efficiently capture the cross-sentence coherence patterns. Using the combined output of the neural coherence model and ROUGE package as the reward, we design a reinforcement learning method to train a proposed neural extractive summarizer which is named Reinforced Neural Extractive Summarization (RNES) model. The RNES model learns to optimize coherence and informative importance of the summary simultaneously. Experimental results show that the proposed RNES outperforms existing baselines and achieves state-of-the-art performance in term of ROUGE on CNN/Daily Mail dataset. The qualitative evaluation indicates that summaries produced by RNES are more coherent and readable.
Tasks	Feature Engineering
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07036v1
PDF	http://arxiv.org/pdf/1804.07036v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-extract-coherent-summary-via-deep
Repo
Framework

Kernel-estimated Nonparametric Overlap-Based Syncytial Clustering


Title	Kernel-estimated Nonparametric Overlap-Based Syncytial Clustering
Authors	Israel Almodóvar-Rivera, Ranjan Maitra
Abstract	Commonly-used clustering algorithms usually find ellipsoidal, spherical or other regular-structured clusters, but are more challenged when the underlying groups lack formal structure or definition. Syncytial clustering is the name that we introduce for methods that merge groups obtained from standard clustering algorithms in order to reveal complex group structure in the data. Here, we develop a distribution-free fully-automated syncytial clustering algorithm that can be used with $k$-means and other algorithms. Our approach computes the cumulative distribution function of the normed residuals from an appropriately fit $k$-groups model and calculates the nonparametric overlap between each pair of clusters. Groups with high pairwise overlap are merged as long as the generalized overlap decreases. Our methodology is always a top performer in identifying groups with regular and irregular structures in several datasets and can be applied to datasets with scatter or incomplete records. The approach is also used to identify the distinct kinds of gamma ray bursts in the Burst and Transient Source Experiment 4Br catalog and the distinct kinds of activation in a functional Magnetic Resonance Imaging study.
Tasks
Published	2018-05-24
URL	https://arxiv.org/abs/1805.09505v3
PDF	https://arxiv.org/pdf/1805.09505v3.pdf
PWC	https://paperswithcode.com/paper/kernel-estimated-nonparametric-overlap-based
Repo
Framework

Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representations


Title	Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representations
Authors	Caglar Aytekin, Xingyang Ni, Francesco Cricri, Emre Aksu
Abstract	Clustering is essential to many tasks in pattern recognition and computer vision. With the advent of deep learning, there is an increasing interest in learning deep unsupervised representations for clustering analysis. Many works on this domain rely on variants of auto-encoders and use the encoder outputs as representations/features for clustering. In this paper, we show that an l2 normalization constraint on these representations during auto-encoder training, makes the representations more separable and compact in the Euclidean space after training. This greatly improves the clustering accuracy when k-means clustering is employed on the representations. We also propose a clustering based unsupervised anomaly detection method using l2 normalized deep auto-encoder representations. We show the effect of l2 normalization on anomaly detection accuracy. We further show that the proposed anomaly detection method greatly improves accuracy compared to previously proposed deep methods such as reconstruction error based anomaly detection.
Tasks	Anomaly Detection, Unsupervised Anomaly Detection
Published	2018-02-01
URL	http://arxiv.org/abs/1802.00187v1
PDF	http://arxiv.org/pdf/1802.00187v1.pdf
PWC	https://paperswithcode.com/paper/clustering-and-unsupervised-anomaly-detection
Repo
Framework

Difficulty Controllable Generation of Reading Comprehension Questions


Title	Difficulty Controllable Generation of Reading Comprehension Questions
Authors	Yifan Gao, Lidong Bing, Wang Chen, Michael R. Lyu, Irwin King
Abstract	We investigate the difficulty levels of questions in reading comprehension datasets such as SQuAD, and propose a new question generation setting, named Difficulty-controllable Question Generation (DQG). Taking as input a sentence in the reading comprehension paragraph and some of its text fragments (i.e., answers) that we want to ask questions about, a DQG method needs to generate questions each of which has a given text fragment as its answer, and meanwhile the generation is under the control of specified difficulty labels—the output questions should satisfy the specified difficulty as much as possible. To solve this task, we propose an end-to-end framework to generate questions of designated difficulty levels by exploring a few important intuitions. For evaluation, we prepared the first dataset of reading comprehension questions with difficulty labels. The results show that the question generated by our framework not only have better quality under the metrics like BLEU, but also comply with the specified difficulty labels.
Tasks	Question Generation, Reading Comprehension
Published	2018-07-10
URL	https://arxiv.org/abs/1807.03586v5
PDF	https://arxiv.org/pdf/1807.03586v5.pdf
PWC	https://paperswithcode.com/paper/difficulty-controllable-generation-of-reading
Repo
Framework

Efficient Outlier Removal in Large Scale Global Structure-from-Motion


Title	Efficient Outlier Removal in Large Scale Global Structure-from-Motion
Authors	Fei Wen, Danping Zou, Rendong Ying, Peilin Liu
Abstract	This work addresses the outlier removal problem in large-scale global structure-from-motion. In such applications, global outlier removal is very useful to mitigate the deterioration caused by mismatches in the feature point matching step. Unlike existing outlier removal methods, we exploit the structure in multiview geometry problems to propose a dimension reduced formulation, based on which two methods have been developed. The first method considers a convex relaxed $\ell_1$ minimization and is solved by a single linear programming (LP), whilst the second one approximately solves the ideal $\ell_0$ minimization by an iteratively reweighted method. The dimension reduction results in a significant speedup of the new algorithms. Further, the iteratively reweighted method can significantly reduce the possibility of removing true inliers. Realistic multiview reconstruction experiments demonstrated that, compared with state-of-the-art algorithms, the new algorithms are much more efficient and meanwhile can give improved solution. Matlab code for reproducing the results is available at \textit{https://github.com/FWen/OUTLR.git}.
Tasks	Dimensionality Reduction
Published	2018-08-09
URL	http://arxiv.org/abs/1808.03041v4
PDF	http://arxiv.org/pdf/1808.03041v4.pdf
PWC	https://paperswithcode.com/paper/efficient-outlier-removal-in-large-scale
Repo
Framework


Title	Identifying Object States in Cooking-Related Images
Authors	Ahmad Babaeian Jelodar, Md Sirajus Salekin, Yu Sun
Abstract	Understanding object states is as important as object recognition for robotic task planning and manipulation. To our knowledge, this paper explicitly introduces and addresses the state identification problem in cooking related images for the first time. In this paper, objects and ingredients in cooking videos are explored and the most frequent objects are analyzed. Eleven states from the most frequent cooking objects are examined and a dataset of images containing those objects and their states is created. As a solution to the state identification problem, a Resnet based deep model is proposed. The model is initialized with Imagenet weights and trained on the dataset of eleven classes. The trained state identification model is evaluated on a subset of the Imagenet dataset and state labels are provided using a combination of the model with manual checking. Moreover, an individual model is fine-tuned for each object in the dataset using the weights from the initially trained model and object-specific images, where significant improvement is demonstrated.
Tasks	Object Recognition
Published	2018-05-17
URL	http://arxiv.org/abs/1805.06956v3
PDF	http://arxiv.org/pdf/1805.06956v3.pdf
PWC	https://paperswithcode.com/paper/identifying-object-states-in-cooking-related
Repo
Framework

“When and Where?": Behavior Dominant Location Forecasting with Micro-blog Streams


Title	“When and Where?": Behavior Dominant Location Forecasting with Micro-blog Streams
Authors	Bhaskar Gautam, Annappa Basava, Abhishek Singh, Amit Agrawal
Abstract	The proliferation of smartphones and wearable devices has increased the availability of large amounts of geospatial streams to provide significant automated discovery of knowledge in pervasive environments, but most prominent information related to altering interests have not yet adequately capitalized. In this paper, we provide a novel algorithm to exploit the dynamic fluctuations in user’s point-of-interest while forecasting the future place of visit with fine granularity. Our proposed algorithm is based on the dynamic formation of collective personality communities using different languages, opinions, geographical and temporal distributions for finding out optimized equivalent content. We performed extensive empirical experiments involving, real-time streams derived from 0.6 million stream tuples of micro-blog comprising 1945 social person fusion with graph algorithm and feed-forward neural network model as a predictive classification model. Lastly, The framework achieves 62.10% mean average precision on 1,20,000 embeddings on unlabeled users and surprisingly 85.92% increment on the state-of-the-art approach.
Tasks
Published	2018-12-16
URL	http://arxiv.org/abs/1812.06443v1
PDF	http://arxiv.org/pdf/1812.06443v1.pdf
PWC	https://paperswithcode.com/paper/when-and-where-behavior-dominant-location
Repo
Framework

Learning from Noisy Web Data with Category-level Supervision


Title	Learning from Noisy Web Data with Category-level Supervision
Authors	Li Niu, Qingtao Tang, Ashok Veeraraghavan, Ashu Sabharwal
Abstract	As tons of photos are being uploaded to public websites (e.g., Flickr, Bing, and Google) every day, learning from web data has become an increasingly popular research direction because of freely available web resources, which is also referred to as webly supervised learning. Nevertheless, the performance gap between webly supervised learning and traditional supervised learning is still very large, owning to the label noise of web data. To be exact, the labels of images crawled from public websites are very noisy and often inaccurate. Some existing works tend to facilitate learning from web data with the aid of extra information, such as augmenting or purifying web data by virtue of instance-level supervision, which is usually in demand of heavy manual annotation. Instead, we propose to tackle the label noise by leveraging more accessible category-level supervision. In particular, we build our method upon variational autoencoder (VAE), in which the classification network is attached on the hidden layer of VAE in a way that the classification network and VAE can jointly leverage the category-level hybrid semantic information. The effectiveness of our proposed method is clearly demonstrated by extensive experiments on three benchmark datasets.
Tasks
Published	2018-03-10
URL	http://arxiv.org/abs/1803.03857v3
PDF	http://arxiv.org/pdf/1803.03857v3.pdf
PWC	https://paperswithcode.com/paper/learning-from-noisy-web-data-with-category
Repo
Framework