January 26, 2020

2728 words 13 mins read

Paper Group ANR 1434

A multiscale Laplacian of Gaussian (LoG) filtering approach to pulmonary nodule detection from whole-lung CT scans. Transition-Based Deep Input Linearization. Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision. Interactive Language Learning by Question Answering. City-level Geolocation of Tweets for Real-time Visual Anal …

A multiscale Laplacian of Gaussian (LoG) filtering approach to pulmonary nodule detection from whole-lung CT scans


Title	A multiscale Laplacian of Gaussian (LoG) filtering approach to pulmonary nodule detection from whole-lung CT scans
Authors	Sergei V. Fotin, David F. Yankelevitz, Claudia I. Henschke, Anthony P. Reeves
Abstract	Candidate generation, the first stage for most computer aided detection (CAD) systems, rapidly scans the entire image data for any possible abnormality locations, while the subsequent stages of the CAD system refine the candidates list to determine the most probable or significant of these candidates. The candidate generator creates a list of the locations and provides a size estimate for each candidate. A multiscale scale-normalized Laplacian of Gaussian (LoG) filtering method for detecting pulmonary nodules in whole-lung CT scans, presented in this paper, achieves a high sensitivity for both solid and nonsolid pulmonary nodules. The pulmonary nodule LoG filtering method was validated on a size-enriched database of 706 whole-lung low-dose CT scans containing 499 solid (>= 4 mm) and 107 nonsolid (>= 6 mm) pulmonary nodules. The method achieved a sensitivity of 0.998 (498/499) for solid nodules and a sensitivity of 1.000 (107/107) for nonsolid nodules. Furthermore, compared to radiologist measurements, the method provided low average nodule size estimation error of 0.12 mm for solid and 1.27 mm for nonsolid nodules. The average distance between automatically and manually determined nodule centroids were 1.41 mm and 1.43 mm, respectively.
Tasks
Published	2019-07-19
URL	https://arxiv.org/abs/1907.08328v1
PDF	https://arxiv.org/pdf/1907.08328v1.pdf
PWC	https://paperswithcode.com/paper/a-multiscale-laplacian-of-gaussian-log
Repo
Framework

Transition-Based Deep Input Linearization


Title	Transition-Based Deep Input Linearization
Authors	Ratish Puduppully, Yue Zhang, Manish Shrivastava
Abstract	Traditional methods for deep NLG adopt pipeline approaches comprising stages such as constructing syntactic input, predicting function words, linearizing the syntactic input and generating the surface forms. Though easier to visualize, pipeline approaches suffer from error propagation. In addition, information available across modules cannot be leveraged by all modules. We construct a transition-based model to jointly perform linearization, function word prediction and morphological generation, which considerably improves upon the accuracy compared to a pipelined baseline system. On a standard deep input linearization shared task, our system achieves the best results reported so far.
Tasks
Published	2019-11-07
URL	https://arxiv.org/abs/1911.02808v1
PDF	https://arxiv.org/pdf/1911.02808v1.pdf
PWC	https://paperswithcode.com/paper/transition-based-deep-input-linearization-1
Repo
Framework

Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision


Title	Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision
Authors	Hongliang Dai, Yangqiu Song
Abstract	Lack of labeled training data is a major bottleneck for neural network based aspect and opinion term extraction on product reviews. To alleviate this problem, we first propose an algorithm to automatically mine extraction rules from existing training examples based on dependency parsing results. The mined rules are then applied to label a large amount of auxiliary data. Finally, we study training procedures to train a neural model which can learn from both the data automatically labeled by the rules and a small amount of data accurately annotated by human. Experimental results show that although the mined rules themselves do not perform well due to their limited flexibility, the combination of human annotated data and rule labeled auxiliary data can improve the neural model and allow it to achieve performance better than or comparable with the current state-of-the-art.
Tasks	Dependency Parsing
Published	2019-07-07
URL	https://arxiv.org/abs/1907.03750v1
PDF	https://arxiv.org/pdf/1907.03750v1.pdf
PWC	https://paperswithcode.com/paper/neural-aspect-and-opinion-term-extraction
Repo
Framework

Interactive Language Learning by Question Answering


Title	Interactive Language Learning by Question Answering
Authors	Xingdi Yuan, Marc-Alexandre Cote, Jie Fu, Zhouhan Lin, Christopher Pal, Yoshua Bengio, Adam Trischler
Abstract	Humans observe and interact with the world to acquire knowledge. However, most existing machine reading comprehension (MRC) tasks miss the interactive, information-seeking component of comprehension. Such tasks present models with static documents that contain all necessary information, usually concentrated in a single short substring. Thus, models can achieve strong performance through simple word- and phrase-based pattern matching. We address this problem by formulating a novel text-based question answering task: Question Answering with Interactive Text (QAit). In QAit, an agent must interact with a partially observable text-based environment to gather information required to answer questions. QAit poses questions about the existence, location, and attributes of objects found in the environment. The data is built using a text-based game generator that defines the underlying dynamics of interaction with the environment. We propose and evaluate a set of baseline models for the QAit task that includes deep reinforcement learning agents. Experiments show that the task presents a major challenge for machine reading systems, while humans solve it with relative ease.
Tasks	Machine Reading Comprehension, Question Answering, Reading Comprehension
Published	2019-08-28
URL	https://arxiv.org/abs/1908.10909v1
PDF	https://arxiv.org/pdf/1908.10909v1.pdf
PWC	https://paperswithcode.com/paper/interactive-language-learning-by-question
Repo
Framework

City-level Geolocation of Tweets for Real-time Visual Analytics


Title	City-level Geolocation of Tweets for Real-time Visual Analytics
Authors	Luke S. Snyder, Morteza Karimzadeh, Ray Chen, David S. Ebert
Abstract	Real-time tweets can provide useful information on evolving events and situations. Geotagged tweets are especially useful, as they indicate the location of origin and provide geographic context. However, only a small portion of tweets are geotagged, limiting their use for situational awareness. In this paper, we adapt, improve, and evaluate a state-of-the-art deep learning model for city-level geolocation prediction, and integrate it with a visual analytics system tailored for real-time situational awareness. We provide computational evaluations to demonstrate the superiority and utility of our geolocation prediction model within an interactive system.
Tasks
Published	2019-10-05
URL	https://arxiv.org/abs/1910.02213v1
PDF	https://arxiv.org/pdf/1910.02213v1.pdf
PWC	https://paperswithcode.com/paper/city-level-geolocation-of-tweets-for-real
Repo
Framework

Machine Learning Testing: Survey, Landscapes and Horizons


Title	Machine Learning Testing: Survey, Landscapes and Horizons
Authors	Jie M. Zhang, Mark Harman, Lei Ma, Yang Liu
Abstract	This paper provides a comprehensive survey of Machine Learning Testing (ML testing) research. It covers 144 papers on testing properties (e.g., correctness, robustness, and fairness), testing components (e.g., the data, learning program, and framework), testing workflow (e.g., test generation and test evaluation), and application scenarios (e.g., autonomous driving, machine translation). The paper also analyses trends concerning datasets, research trends, and research focus, concluding with research challenges and promising research directions in ML testing.
Tasks	Autonomous Driving, Machine Translation
Published	2019-06-19
URL	https://arxiv.org/abs/1906.10742v2
PDF	https://arxiv.org/pdf/1906.10742v2.pdf
PWC	https://paperswithcode.com/paper/machine-learning-testing-survey-landscapes
Repo
Framework

$\ell_{\infty}$ Vector Contraction for Rademacher Complexity


Title	$\ell_{\infty}$ Vector Contraction for Rademacher Complexity
Authors	Dylan J. Foster, Alexander Rakhlin
Abstract	We show that the Rademacher complexity of any $\mathbb{R}^{K}$-valued function class composed with an $\ell_{\infty}$-Lipschitz function is bounded by the maximum Rademacher complexity of the restriction of the function class along each coordinate, times a factor of $\tilde{O}(\sqrt{K})$.
Tasks
Published	2019-11-15
URL	https://arxiv.org/abs/1911.06468v1
PDF	https://arxiv.org/pdf/1911.06468v1.pdf
PWC	https://paperswithcode.com/paper/ell_infty-vector-contraction-for-rademacher
Repo
Framework

Multi-task Self-Supervised Learning for Human Activity Detection


Title	Multi-task Self-Supervised Learning for Human Activity Detection
Authors	Aaqib Saeed, Tanir Ozcelebi, Johan Lukkien
Abstract	Deep learning methods are successfully used in applications pertaining to ubiquitous computing, health, and well-being. Specifically, the area of human activity recognition (HAR) is primarily transformed by the convolutional and recurrent neural networks, thanks to their ability to learn semantic representations from raw input. However, to extract generalizable features, massive amounts of well-curated data are required, which is a notoriously challenging task; hindered by privacy issues, and annotation costs. Therefore, unsupervised representation learning is of prime importance to leverage the vast amount of unlabeled data produced by smart devices. In this work, we propose a novel self-supervised technique for feature learning from sensory data that does not require access to any form of semantic labels. We learn a multi-task temporal convolutional network to recognize transformations applied on an input signal. By exploiting these transformations, we demonstrate that simple auxiliary tasks of the binary classification result in a strong supervisory signal for extracting useful features for the downstream task. We extensively evaluate the proposed approach on several publicly available datasets for smartphone-based HAR in unsupervised, semi-supervised, and transfer learning settings. Our method achieves performance levels superior to or comparable with fully-supervised networks, and it performs significantly better than autoencoders. Notably, for the semi-supervised case, the self-supervised features substantially boost the detection rate by attaining a kappa score between 0.7-0.8 with only 10 labeled examples per class. We get similar impressive performance even if the features are transferred from a different data source. While this paper focuses on HAR as the application domain, the proposed technique is general and could be applied to a wide variety of problems in other areas.
Tasks	Action Detection, Activity Detection, Activity Recognition, Human Activity Recognition, Representation Learning, Transfer Learning, Unsupervised Representation Learning
Published	2019-07-27
URL	https://arxiv.org/abs/1907.11879v1
PDF	https://arxiv.org/pdf/1907.11879v1.pdf
PWC	https://paperswithcode.com/paper/multi-task-self-supervised-learning-for-human
Repo
Framework

Rare Disease Detection by Sequence Modeling with Generative Adversarial Networks


Title	Rare Disease Detection by Sequence Modeling with Generative Adversarial Networks
Authors	Kezi Yu, Yunlong Wang, Yong Cai, Cao Xiao, Emily Zhao, Lucas Glass, Jimeng Sun
Abstract	Rare diseases affecting 350 million individuals are commonly associated with delay in diagnosis or misdiagnosis. To improve those patients’ outcome, rare disease detection is an important task for identifying patients with rare conditions based on longitudinal medical claims. In this paper, we present a deep learning method for detecting patients with exocrine pancreatic insufficiency (EPI) (a rare disease). The contribution includes 1) a large longitudinal study using 7 years medical claims from 1.8 million patients including 29,149 EPI patients, 2) a new deep learning model using generative adversarial networks (GANs) to boost rare disease class, and also leveraging recurrent neural networks to model patient sequence data, 3) an accurate prediction with 0.56 PR-AUC which outperformed benchmark models in terms of precision and recall.
Tasks
Published	2019-07-01
URL	https://arxiv.org/abs/1907.01022v1
PDF	https://arxiv.org/pdf/1907.01022v1.pdf
PWC	https://paperswithcode.com/paper/rare-disease-detection-by-sequence-modeling
Repo
Framework

Program Classification Using Gated Graph Attention Neural Network for Online Programming Service


Title	Program Classification Using Gated Graph Attention Neural Network for Online Programming Service
Authors	Mingming Lu, Dingwu Tan, Naixue Xiong, Zailiang Chen, Haifeng Li
Abstract	The online programing services, such as Github,TopCoder, and EduCoder, have promoted a lot of social interactions among the service users. However, the existing social interactions is rather limited and inefficient due to the rapid increasing of source-code repositories, which is difficult to explore manually. The emergence of source-code mining provides a promising way to analyze those source codes, so that those source codes can be relatively easy to understand and share among those service users. Among all the source-code mining attempts,program classification lays a foundation for various tasks related to source-code understanding, because it is impossible for a machine to understand a computer program if it cannot classify the program correctly. Although numerous machine learning models, such as the Natural Language Processing (NLP) based models and the Abstract Syntax Tree (AST) based models, have been proposed to classify computer programs based on their corresponding source codes, the existing works cannot fully characterize the source codes from the perspective of both the syntax and semantic information. To address this problem, we proposed a Graph Neural Network (GNN) based model, which integrates data flow and function call information to the AST,and applies an improved GNN model to the integrated graph, so as to achieve the state-of-art program classification accuracy. The experiment results have shown that the proposed work can classify programs with accuracy over 97%.
Tasks
Published	2019-03-09
URL	http://arxiv.org/abs/1903.03804v1
PDF	http://arxiv.org/pdf/1903.03804v1.pdf
PWC	https://paperswithcode.com/paper/program-classification-using-gated-graph
Repo
Framework

Integral Mixabilty: a Tool for Efficient Online Aggregation of Functional and Probabilistic Forecasts


Title	Integral Mixabilty: a Tool for Efficient Online Aggregation of Functional and Probabilistic Forecasts
Authors	Alexander Korotin, Vladimir V’yugin, Evgeny Burnaev
Abstract	In this paper we extend the setting of the online prediction with expert advice to function-valued forecasts. At each step of the online game several experts predict a function and the learner has to efficiently aggregate these functional forecasts into one a single forecast. We adapt basic mixable loss functions to compare functional predictions and prove that these “integral” expansions are also mixable. We call this phenomena integral mixability. As an application, we consider various loss functions for prediction of probability distributions and show that they are mixable by using our main result. The considered loss functions include Continuous ranking probability score (CRPS), Optimal transport costs (OT), Beta-2 and Kullback-Leibler (KL) divergences.
Tasks
Published	2019-12-15
URL	https://arxiv.org/abs/1912.07048v1
PDF	https://arxiv.org/pdf/1912.07048v1.pdf
PWC	https://paperswithcode.com/paper/integral-mixabilty-a-tool-for-efficient
Repo
Framework

Neural Program Synthesis By Self-Learning


Title	Neural Program Synthesis By Self-Learning
Authors	Yifan Xu, Lu Dai, Udaikaran Singh, Kening Zhang, Zhuowen Tu
Abstract	Neural inductive program synthesis is a task generating instructions that can produce desired outputs from given inputs. In this paper, we focus on the generation of a chunk of assembly code that can be executed to match a state change inside the CPU and RAM. We develop a neural program synthesis algorithm, AutoAssemblet, learned via self-learning reinforcement learning that explores the large code space efficiently. Policy networks and value networks are learned to reduce the breadth and depth of the Monte Carlo Tree Search, resulting in better synthesis performance. We also propose an effective multi-entropy policy sampling technique to alleviate online update correlations. We apply AutoAssemblet to basic programming tasks and show significant higher success rates compared to several competing baselines.
Tasks	Program Synthesis
Published	2019-10-13
URL	https://arxiv.org/abs/1910.05865v1
PDF	https://arxiv.org/pdf/1910.05865v1.pdf
PWC	https://paperswithcode.com/paper/neural-program-synthesis-by-self-learning-1
Repo
Framework

Breast Cancer Classification with Ultrasound Images Based on SLIC


Title	Breast Cancer Classification with Ultrasound Images Based on SLIC
Authors	Zhihao Fang, Wanyi Zhang, He Ma
Abstract	Ultrasound image diagnosis of breast tumors has been widely used in recent years. However, there are some problems of it, for instance, poor quality, intense noise and uneven echo distribution, which has created a huge obstacle to diagnosis. To overcome these problems, we propose a novel method, a breast cancer classification with ultrasound images based on SLIC (BCCUI). We first utilize the Region of Interest (ROI) extraction based on Simple Linear Iterative Clustering (SLIC) algorithm and region growing algorithm to extract the ROI at the super-pixel level. Next, the features of ROI are extracted. Furthermore, the Support Vector Machine (SVM) classifier is applied. The calculation states that the accuracy of this segment algorithm is up to 88.00% and the sensitivity of the algorithm is up to 92.05%, which proves that the classifier presents in this paper has certain research meaning and applied worthiness.
Tasks
Published	2019-04-25
URL	https://arxiv.org/abs/1904.11322v2
PDF	https://arxiv.org/pdf/1904.11322v2.pdf
PWC	https://paperswithcode.com/paper/breast-cancer-classification-with-ultrasound
Repo
Framework

CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition


Title	CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition
Authors	Yuying Zhu, Guoxin Wang, Börje F. Karlsson
Abstract	Named entity recognition (NER) in Chinese is essential but difficult because of the lack of natural delimiters. Therefore, Chinese Word Segmentation (CWS) is usually considered as the first step for Chinese NER. However, models based on word-level embeddings and lexicon features often suffer from segmentation errors and out-of-vocabulary (OOV) words. In this paper, we investigate a Convolutional Attention Network called CAN for Chinese NER, which consists of a character-based convolutional neural network (CNN) with local-attention layer and a gated recurrent unit (GRU) with global self-attention layer to capture the information from adjacent characters and sentence contexts. Also, compared to other models, not depending on any external resources like lexicons and employing small size of char embeddings make our model more practical. Extensive experimental results show that our approach outperforms state-of-the-art methods without word embedding and external lexicon resources on different domain datasets including Weibo, MSRA and Chinese Resume NER dataset.
Tasks	Chinese Named Entity Recognition, Chinese Word Segmentation, Named Entity Recognition
Published	2019-04-03
URL	http://arxiv.org/abs/1904.02141v2
PDF	http://arxiv.org/pdf/1904.02141v2.pdf
PWC	https://paperswithcode.com/paper/can-ner-convolutional-attention-network
Repo
Framework

Path homologies of deep feedforward networks


Title	Path homologies of deep feedforward networks
Authors	Samir Chowdhury, Thomas Gebhart, Steve Huntsman, Matvey Yutin
Abstract	We provide a characterization of two types of directed homology for fully-connected, feedforward neural network architectures. These exact characterizations of the directed homology structure of a neural network architecture are the first of their kind. We show that the directed flag homology of deep networks reduces to computing the simplicial homology of the underlying undirected graph, which is explicitly given by Euler characteristic computations. We also show that the path homology of these networks is non-trivial in higher dimensions and depends on the number and size of the layers within the network. These results provide a foundation for investigating homological differences between neural network architectures and their realized structure as implied by their parameters.
Tasks
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07617v1
PDF	https://arxiv.org/pdf/1910.07617v1.pdf
PWC	https://paperswithcode.com/paper/path-homologies-of-deep-feedforward-networks
Repo
Framework