July 28, 2019

2738 words 13 mins read

Paper Group ANR 238

Nationality Classification Using Name Embeddings. On the Sample Complexity of Graphical Model Selection for Non-Stationary Processes. Abstract Argumentation / Persuasion / Dynamics. Multi-stream 3D FCN with Multi-scale Deep Supervision for Multi-modality Isointense Infant Brain MR Image Segmentation. Convergence Results for Neural Networks via Elec …

Nationality Classification Using Name Embeddings


Title	Nationality Classification Using Name Embeddings
Authors	Junting Ye, Shuchu Han, Yifan Hu, Baris Coskun, Meizhu Liu, Hong Qin, Steven Skiena
Abstract	Nationality identification unlocks important demographic information, with many applications in biomedical and sociological research. Existing name-based nationality classifiers use name substrings as features and are trained on small, unrepresentative sets of labeled names, typically extracted from Wikipedia. As a result, these methods achieve limited performance and cannot support fine-grained classification. We exploit the phenomena of homophily in communication patterns to learn name embeddings, a new representation that encodes gender, ethnicity, and nationality which is readily applicable to building classifiers and other systems. Through our analysis of 57M contact lists from a major Internet company, we are able to design a fine-grained nationality classifier covering 39 groups representing over 90% of the world population. In an evaluation against other published systems over 13 common classes, our F1 score (0.795) is substantial better than our closest competitor Ethnea (0.580). To the best of our knowledge, this is the most accurate, fine-grained nationality classifier available. As a social media application, we apply our classifiers to the followers of major Twitter celebrities over six different domains. We demonstrate stark differences in the ethnicities of the followers of Trump and Obama, and in the sports and entertainments favored by different groups. Finally, we identify an anomalous political figure whose presumably inflated following appears largely incapable of reading the language he posts in.
Tasks
Published	2017-08-25
URL	http://arxiv.org/abs/1708.07903v1
PDF	http://arxiv.org/pdf/1708.07903v1.pdf
PWC	https://paperswithcode.com/paper/nationality-classification-using-name
Repo
Framework

On the Sample Complexity of Graphical Model Selection for Non-Stationary Processes


Title	On the Sample Complexity of Graphical Model Selection for Non-Stationary Processes
Authors	Nguyen Q. Tran, Oleksii Abramenko, Alexander Jung
Abstract	We characterize the sample size required for accurate graphical model selection from non-stationary samples. The observed data is modeled as a vector-valued zero-mean Gaussian random process whose samples are uncorrelated but have different covariance matrices. This model contains as special cases the standard setting of i.i.d. samples as well as the case of samples forming a stationary or underspread (non-stationary) processes. More generally, our model applies to any process model for which an efficient decorrelation can be obtained. By analyzing a particular model selection method, we derive a sufficient condition on the required sample size for accurate graphical model selection based on non-stationary data.
Tasks	Model Selection
Published	2017-01-17
URL	https://arxiv.org/abs/1701.04724v5
PDF	https://arxiv.org/pdf/1701.04724v5.pdf
PWC	https://paperswithcode.com/paper/on-the-sample-complexity-of-graphical-model
Repo
Framework

Abstract Argumentation / Persuasion / Dynamics


Title	Abstract Argumentation / Persuasion / Dynamics
Authors	Ryuta Arisaka, Ken Satoh
Abstract	The act of persuasion, a key component in rhetoric argumentation, may be viewed as a dynamics modifier. We extend Dung’s frameworks with acts of persuasion among agents, and consider interactions among attack, persuasion and defence that have been largely unheeded so far. We characterise basic notions of admissibilities in this framework, and show a way of enriching them through, effectively, CTL (computation tree logic) encoding, which also permits importation of the theoretical results known to the logic into our argumentation frameworks. Our aim is to complement the growing interest in coordination of static and dynamic argumentation.
Tasks	Abstract Argumentation
Published	2017-05-29
URL	http://arxiv.org/abs/1705.10044v3
PDF	http://arxiv.org/pdf/1705.10044v3.pdf
PWC	https://paperswithcode.com/paper/abstract-argumentation-persuasion-dynamics
Repo
Framework

Multi-stream 3D FCN with Multi-scale Deep Supervision for Multi-modality Isointense Infant Brain MR Image Segmentation


Title	Multi-stream 3D FCN with Multi-scale Deep Supervision for Multi-modality Isointense Infant Brain MR Image Segmentation
Authors	Guodong Zeng, Guoyan Zheng
Abstract	We present a method to address the challenging problem of segmentation of multi-modality isointense infant brain MR images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Our method is based on context-guided, multi-stream fully convolutional networks (FCN), which after training, can directly map a whole volumetric data to its volume-wise labels. In order to alleviate the poten-tial gradient vanishing problem during training, we designed multi-scale deep supervision. Furthermore, context infor-mation was used to further improve the performance of our method. Validated on the test data of the MICCAI 2017 Grand Challenge on 6-month infant brain MRI segmentation (iSeg-2017), our method achieved an average Dice Overlap Coefficient of 95.4%, 91.6% and 89.6% for CSF, GM and WM, respectively.
Tasks	Infant Brain Mri Segmentation, Semantic Segmentation
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10212v2
PDF	http://arxiv.org/pdf/1711.10212v2.pdf
PWC	https://paperswithcode.com/paper/multi-stream-3d-fcn-with-multi-scale-deep
Repo
Framework

Convergence Results for Neural Networks via Electrodynamics


Title	Convergence Results for Neural Networks via Electrodynamics
Authors	Rina Panigrahy, Sushant Sachdeva, Qiuyi Zhang
Abstract	We study whether a depth two neural network can learn another depth two network using gradient descent. Assuming a linear output node, we show that the question of whether gradient descent converges to the target function is equivalent to the following question in electrodynamics: Given $k$ fixed protons in $\mathbb{R}^d,$ and $k$ electrons, each moving due to the attractive force from the protons and repulsive force from the remaining electrons, whether at equilibrium all the electrons will be matched up with the protons, up to a permutation. Under the standard electrical force, this follows from the classic Earnshaw’s theorem. In our setting, the force is determined by the activation function and the input distribution. Building on this equivalence, we prove the existence of an activation function such that gradient descent learns at least one of the hidden nodes in the target network. Iterating, we show that gradient descent can be used to learn the entire network one node at a time.
Tasks
Published	2017-02-01
URL	http://arxiv.org/abs/1702.00458v5
PDF	http://arxiv.org/pdf/1702.00458v5.pdf
PWC	https://paperswithcode.com/paper/convergence-results-for-neural-networks-via
Repo
Framework

YEDDA: A Lightweight Collaborative Text Span Annotation Tool


Title	YEDDA: A Lightweight Collaborative Text Span Annotation Tool
Authors	Jie Yang, Yue Zhang, Linwei Li, Xingxuan Li
Abstract	In this paper, we introduce \textsc{Yedda}, a lightweight but efficient and comprehensive open-source tool for text span annotation. \textsc{Yedda} provides a systematic solution for text span annotation, ranging from collaborative user annotation to administrator evaluation and analysis. It overcomes the low efficiency of traditional text annotation tools by annotating entities through both command line and shortcut keys, which are configurable with custom labels. \textsc{Yedda} also gives intelligent recommendations by learning the up-to-date annotated text. An administrator client is developed to evaluate annotation quality of multiple annotators and generate detailed comparison report for each annotator pair. Experiments show that the proposed system can reduce the annotation time by half compared with existing annotation tools. And the annotation time can be further compressed by 16.47% through intelligent recommendation.
Tasks
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03759v3
PDF	http://arxiv.org/pdf/1711.03759v3.pdf
PWC	https://paperswithcode.com/paper/yedda-a-lightweight-collaborative-text-span
Repo
Framework

Deep-Learning for Classification of Colorectal Polyps on Whole-Slide Images


Title	Deep-Learning for Classification of Colorectal Polyps on Whole-Slide Images
Authors	Bruno Korbar, Andrea M. Olofson, Allen P. Miraflor, Katherine M. Nicka, Matthew A. Suriawinata, Lorenzo Torresani, Arief A. Suriawinata, Saeed Hassanpour
Abstract	Histopathological characterization of colorectal polyps is an important principle for determining the risk of colorectal cancer and future rates of surveillance for patients. This characterization is time-intensive, requires years of specialized training, and suffers from significant inter-observer and intra-observer variability. In this work, we built an automatic image-understanding method that can accurately classify different types of colorectal polyps in whole-slide histology images to help pathologists with histopathological characterization and diagnosis of colorectal polyps. The proposed image-understanding method is based on deep-learning techniques, which rely on numerous levels of abstraction for data representation and have shown state-of-the-art results for various image analysis tasks. Our image-understanding method covers all five polyp types (hyperplastic polyp, sessile serrated polyp, traditional serrated adenoma, tubular adenoma, and tubulovillous/villous adenoma) that are included in the US multi-society task force guidelines for colorectal cancer risk assessment and surveillance, and encompasses the most common occurrences of colorectal polyps. Our evaluation on 239 independent test samples shows our proposed method can identify the types of colorectal polyps in whole-slide images with a high efficacy (accuracy: 93.0%, precision: 89.7%, recall: 88.3%, F1 score: 88.8%). The presented method in this paper can reduce the cognitive burden on pathologists and improve their accuracy and efficiency in histopathological characterization of colorectal polyps, and in subsequent risk assessment and follow-up recommendations.
Tasks
Published	2017-03-05
URL	http://arxiv.org/abs/1703.01550v2
PDF	http://arxiv.org/pdf/1703.01550v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-classification-of
Repo
Framework

Perspective: Energy Landscapes for Machine Learning


Title	Perspective: Energy Landscapes for Machine Learning
Authors	Andrew J. Ballard, Ritankar Das, Stefano Martiniani, Dhagash Mehta, Levent Sagun, Jacob D. Stevenson, David J. Wales
Abstract	Machine learning techniques are being increasingly used as flexible non-linear fitting and prediction tools in the physical sciences. Fitting functions that exhibit multiple solutions as local minima can be analysed in terms of the corresponding machine learning landscape. Methods to explore and visualise molecular potential energy landscapes can be applied to these machine learning landscapes to gain new insight into the solution space involved in training and the nature of the corresponding predictions. In particular, we can define quantities analogous to molecular structure, thermodynamics, and kinetics, and relate these emergent properties to the structure of the underlying landscape. This Perspective aims to describe these analogies with examples from recent applications, and suggest avenues for new interdisciplinary research.
Tasks
Published	2017-03-23
URL	http://arxiv.org/abs/1703.07915v1
PDF	http://arxiv.org/pdf/1703.07915v1.pdf
PWC	https://paperswithcode.com/paper/perspective-energy-landscapes-for-machine
Repo
Framework

A New Medical Diagnosis Method Based on Z-Numbers


Title	A New Medical Diagnosis Method Based on Z-Numbers
Authors	Dong Wu, Xiang Liu, Feng Xue, Hanqing Zheng, Yehang Shou, Wen Jiang
Abstract	How to handle uncertainty in medical diagnosis is an open issue. In this paper, a new decision making methodology based on Z-numbers is presented. Firstly, the experts’ opinions are represented by Z-numbers. Z-number is an ordered pair of fuzzy numbers denoted as Z = (A, B). Then, a new method for ranking fuzzy numbers is proposed. And based on the proposed fuzzy number ranking method, a novel method is presented to transform the Z-numbers into Basic Probability Assignment (BPA). As a result, the information from different sources is combined by the Dempster’ combination rule. The final decision making is more reasonable due to the advantage of information fusion. Finally, two experiments, risk analysis and medical diagnosis, are illustrated to show the efficiency of the proposed methodology.
Tasks	Decision Making, Medical Diagnosis
Published	2017-05-07
URL	http://arxiv.org/abs/1705.02620v1
PDF	http://arxiv.org/pdf/1705.02620v1.pdf
PWC	https://paperswithcode.com/paper/a-new-medical-diagnosis-method-based-on-z
Repo
Framework

Linear convergence of SDCA in statistical estimation


Title	Linear convergence of SDCA in statistical estimation
Authors	Chao Qu, Huan Xu
Abstract	In this paper, we consider stochastic dual coordinate (SDCA) {\em without} strongly convex assumption or convex assumption. We show that SDCA converges linearly under mild conditions termed restricted strong convexity. This covers a wide array of popular statistical models including Lasso, group Lasso, and logistic regression with $\ell_1$ regularization, corrected Lasso and linear regression with SCAD regularizer. This significantly improves previous convergence results on SDCA for problems that are not strongly convex. As a by product, we derive a dual free form of SDCA that can handle general regularization term, which is of interest by itself.
Tasks
Published	2017-01-26
URL	http://arxiv.org/abs/1701.07808v4
PDF	http://arxiv.org/pdf/1701.07808v4.pdf
PWC	https://paperswithcode.com/paper/linear-convergence-of-sdca-in-statistical
Repo
Framework

Training Group Orthogonal Neural Networks with Privileged Information


Title	Training Group Orthogonal Neural Networks with Privileged Information
Authors	Yunpeng Chen, Xiaojie Jin, Jiashi Feng, Shuicheng Yan
Abstract	Learning rich and diverse representations is critical for the performance of deep convolutional neural networks (CNNs). In this paper, we consider how to use privileged information to promote inherent diversity of a single CNN model such that the model can learn better representations and offer stronger generalization ability. To this end, we propose a novel group orthogonal convolutional neural network (GoCNN) that learns untangled representations within each layer by exploiting provided privileged information and enhances representation diversity effectively. We take image classification as an example where image segmentation annotations are used as privileged information during the training process. Experiments on two benchmark datasets – ImageNet and PASCAL VOC – clearly demonstrate the strong generalization ability of our proposed GoCNN model. On the ImageNet dataset, GoCNN improves the performance of state-of-the-art ResNet-152 model by absolute value of 1.2% while only uses privileged information of 10% of the training images, confirming effectiveness of GoCNN on utilizing available privileged knowledge to train better CNNs.
Tasks	Image Classification, Semantic Segmentation
Published	2017-01-24
URL	http://arxiv.org/abs/1701.06772v2
PDF	http://arxiv.org/pdf/1701.06772v2.pdf
PWC	https://paperswithcode.com/paper/training-group-orthogonal-neural-networks
Repo
Framework

Embedding-Based Speaker Adaptive Training of Deep Neural Networks


Title	Embedding-Based Speaker Adaptive Training of Deep Neural Networks
Authors	Xiaodong Cui, Vaibhava Goel, George Saon
Abstract	An embedding-based speaker adaptive training (SAT) approach is proposed and investigated in this paper for deep neural network acoustic modeling. In this approach, speaker embedding vectors, which are a constant given a particular speaker, are mapped through a control network to layer-dependent element-wise affine transformations to canonicalize the internal feature representations at the output of hidden layers of a main network. The control network for generating the speaker-dependent mappings is jointly estimated with the main network for the overall speaker adaptive acoustic modeling. Experiments on large vocabulary continuous speech recognition (LVCSR) tasks show that the proposed SAT scheme can yield superior performance over the widely-used speaker-aware training using i-vectors with speaker-adapted input features.
Tasks	Large Vocabulary Continuous Speech Recognition, Speech Recognition
Published	2017-10-17
URL	http://arxiv.org/abs/1710.06937v1
PDF	http://arxiv.org/pdf/1710.06937v1.pdf
PWC	https://paperswithcode.com/paper/embedding-based-speaker-adaptive-training-of
Repo
Framework

ASR error management for improving spoken language understanding


Title	ASR error management for improving spoken language understanding
Authors	Edwin Simonnet, Sahar Ghannay, Nathalie Camelin, Yannick Estève, Renato De Mori
Abstract	This paper addresses the problem of automatic speech recognition (ASR) error detection and their use for improving spoken language understanding (SLU) systems. In this study, the SLU task consists in automatically extracting, from ASR transcriptions , semantic concepts and concept/values pairs in a e.g touristic information system. An approach is proposed for enriching the set of semantic labels with error specific labels and by using a recently proposed neural approach based on word embeddings to compute well calibrated ASR confidence measures. Experimental results are reported showing that it is possible to decrease significantly the Concept/Value Error Rate with a state of the art system, outperforming previously published results performance on the same experimental data. It also shown that combining an SLU approach based on conditional random fields with a neural encoder/decoder attention based architecture , it is possible to effectively identifying confidence islands and uncertain semantic output segments useful for deciding appropriate error handling actions by the dialogue manager strategy .
Tasks	Speech Recognition, Spoken Language Understanding, Word Embeddings
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09515v1
PDF	http://arxiv.org/pdf/1705.09515v1.pdf
PWC	https://paperswithcode.com/paper/asr-error-management-for-improving-spoken
Repo
Framework

Learning quadrangulated patches for 3D shape parameterization and completion


Title	Learning quadrangulated patches for 3D shape parameterization and completion
Authors	Kripasindhu Sarkar, Kiran Varanasi, Didier Stricker
Abstract	We propose a novel 3D shape parameterization by surface patches, that are oriented by 3D mesh quadrangulation of the shape. By encoding 3D surface detail on local patches, we learn a patch dictionary that identifies principal surface features of the shape. Unlike previous methods, we are able to encode surface patches of variable size as determined by the user. We propose novel methods for dictionary learning and patch reconstruction based on the query of a noisy input patch with holes. We evaluate the patch dictionary towards various applications in 3D shape inpainting, denoising and compression. Our method is able to predict missing vertices and inpaint moderately sized holes. We demonstrate a complete pipeline for reconstructing the 3D mesh from the patch encoding. We validate our shape parameterization and reconstruction methods on both synthetic shapes and real world scans. We show that our patch dictionary performs successful shape completion of complicated surface textures.
Tasks	Denoising, Dictionary Learning
Published	2017-09-20
URL	http://arxiv.org/abs/1709.06868v1
PDF	http://arxiv.org/pdf/1709.06868v1.pdf
PWC	https://paperswithcode.com/paper/learning-quadrangulated-patches-for-3d-shape
Repo
Framework

Quantifying homologous proteins and proteoforms


Title	Quantifying homologous proteins and proteoforms
Authors	Dmitry Malioutov, Tianchi Chen, Jacob Jaffe, Edoardo Airoldi, Steven Carr, Bogdan Budnik, Nikolai Slavov
Abstract	Many proteoforms - arising from alternative splicing, post-translational modifications (PTMs), or paralogous genes - have distinct biological functions, such as histone PTM proteoforms. However, their quantification by existing bottom-up mass-spectrometry (MS) methods is undermined by peptide-specific biases. To avoid these biases, we developed and implemented a first-principles model (HIquant) for quantifying proteoform stoichiometries. We characterized when MS data allow inferring proteoform stoichiometries by HIquant, derived an algorithm for optimal inference, and demonstrated experimentally high accuracy in quantifying fractional PTM occupancy without using external standards, even in the challenging case of the histone modification code. HIquant server is implemented at: https://web.northeastern.edu/slavov/2014_HIquant/
Tasks
Published	2017-08-05
URL	http://arxiv.org/abs/1708.01772v1
PDF	http://arxiv.org/pdf/1708.01772v1.pdf
PWC	https://paperswithcode.com/paper/quantifying-homologous-proteins-and
Repo
Framework