July 27, 2019

2914 words 14 mins read

Paper Group ANR 469

Binary Matrix Guessing Problem. Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation. Unified Pragmatic Models for Generating and Following Instructions. Naturalizing a Programming Language via Interactive Learning. Pedagogical learning. Fixing an error in Caponnetto and de Vito (2007). Geometrical morphology. Iris: A C …

Binary Matrix Guessing Problem


Title	Binary Matrix Guessing Problem
Authors	Çağrı Latifoğlu
Abstract	We introduce the Binary Matrix Guessing Problem and provide two algorithms to solve this problem. The first algorithm we introduce is Elementwise Probing Algorithm (EPA) which is very fast under a score which utilizes Frobenius Distance. The second algorithm is Additive Reinforcement Learning Algorithm which combines ideas from perceptron algorithm and reinforcement learning algorithm. This algorithm is significantly slower compared to first one, but less restrictive and generalizes better. We compare computational performance of both algorithms and provide numerical results. reason for withdrawal: Paper will be rewritten with experiments replicated on verified and validated hardware and software.
Tasks
Published	2017-01-22
URL	http://arxiv.org/abs/1701.06167v2
PDF	http://arxiv.org/pdf/1701.06167v2.pdf
PWC	https://paperswithcode.com/paper/binary-matrix-guessing-problem
Repo
Framework

Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation


Title	Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation
Authors	Michal Drozdzal, Gabriel Chartrand, Eugene Vorontsov, Lisa Di Jorio, An Tang, Adriana Romero, Yoshua Bengio, Chris Pal, Samuel Kadoury
Abstract	In this paper, we introduce a simple, yet powerful pipeline for medical image segmentation that combines Fully Convolutional Networks (FCNs) with Fully Convolutional Residual Networks (FC-ResNets). We propose and examine a design that takes particular advantage of recent advances in the understanding of both Convolutional Neural Networks as well as ResNets. Our approach focuses upon the importance of a trainable pre-processing when using FC-ResNets and we show that a low-capacity FCN model can serve as a pre-processor to normalize medical input data. In our image segmentation pipeline, we use FCNs to obtain normalized images, which are then iteratively refined by means of a FC-ResNet to generate a segmentation prediction. As in other fully convolutional approaches, our pipeline can be used off-the-shelf on different image modalities. We show that using this pipeline, we exhibit state-of-the-art performance on the challenging Electron Microscopy benchmark, when compared to other 2D methods. We improve segmentation results on CT images of liver lesions, when contrasting with standard FCN methods. Moreover, when applying our 2D pipeline on a challenging 3D MRI prostate segmentation challenge we reach results that are competitive even when compared to 3D methods. The obtained results illustrate the strong potential and versatility of the pipeline by achieving highly accurate results on multi-modality images from different anatomical regions and organs.
Tasks	Medical Image Segmentation, Semantic Segmentation
Published	2017-02-16
URL	http://arxiv.org/abs/1702.05174v1
PDF	http://arxiv.org/pdf/1702.05174v1.pdf
PWC	https://paperswithcode.com/paper/learning-normalized-inputs-for-iterative
Repo
Framework

Unified Pragmatic Models for Generating and Following Instructions


Title	Unified Pragmatic Models for Generating and Following Instructions
Authors	Daniel Fried, Jacob Andreas, Dan Klein
Abstract	We show that explicit pragmatic inference aids in correctly generating and following natural language instructions for complex, sequential tasks. Our pragmatics-enabled models reason about why speakers produce certain instructions, and about how listeners will react upon hearing them. Like previous pragmatic models, we use learned base listener and speaker models to build a pragmatic speaker that uses the base listener to simulate the interpretation of candidate descriptions, and a pragmatic listener that reasons counterfactually about alternative descriptions. We extend these models to tasks with sequential structure. Evaluation of language generation and interpretation shows that pragmatic inference improves state-of-the-art listener models (at correctly interpreting human instructions) and speaker models (at producing instructions correctly interpreted by humans) in diverse settings.
Tasks	Text Generation
Published	2017-11-14
URL	http://arxiv.org/abs/1711.04987v3
PDF	http://arxiv.org/pdf/1711.04987v3.pdf
PWC	https://paperswithcode.com/paper/unified-pragmatic-models-for-generating-and
Repo
Framework

Naturalizing a Programming Language via Interactive Learning


Title	Naturalizing a Programming Language via Interactive Learning
Authors	Sida I. Wang, Samuel Ginn, Percy Liang, Christoper D. Manning
Abstract	Our goal is to create a convenient natural language interface for performing well-specified but complex actions such as analyzing data, manipulating text, and querying databases. However, existing natural language interfaces for such tasks are quite primitive compared to the power one wields with a programming language. To bridge this gap, we start with a core programming language and allow users to “naturalize” the core language incrementally by defining alternative, more natural syntax and increasingly complex concepts in terms of compositions of simpler ones. In a voxel world, we show that a community of users can simultaneously teach a common system a diverse language and use it to build hundreds of complex voxel structures. Over the course of three days, these users went from using only the core language to using the naturalized language in 85.9% of the last 10K utterances.
Tasks
Published	2017-04-23
URL	http://arxiv.org/abs/1704.06956v1
PDF	http://arxiv.org/pdf/1704.06956v1.pdf
PWC	https://paperswithcode.com/paper/naturalizing-a-programming-language-via
Repo
Framework

Pedagogical learning


Title	Pedagogical learning
Authors	Long Ouyang, Michael C. Frank
Abstract	A common assumption in machine learning is that training data are i.i.d. samples from some distribution. Processes that generate i.i.d. samples are, in a sense, uninformative—they produce data without regard to how good this data is for learning. By contrast, cognitive science research has shown that when people generate training data for others (i.e., teaching), they deliberately select examples that are helpful for learning. Because the data is more informative, learning can require less data. Interestingly, such examples are most effective when learners know that the data were pedagogically generated (as opposed to randomly generated). We call this pedagogical learning—when a learner assumes that evidence comes from a helpful teacher. In this work, we ask how pedagogical learning might work for machine learning algorithms. Studying this question requires understanding how people actually teach complex concepts with examples, so we conducted a behavioral study examining how people teach regular expressions using example strings. We found that teachers’ examples contain powerful clustering structure that can greatly facilitate learning. We then develop a model of teaching and show a proof of concept that using this model inside of a learner can improve performance.
Tasks
Published	2017-11-26
URL	http://arxiv.org/abs/1711.09401v2
PDF	http://arxiv.org/pdf/1711.09401v2.pdf
PWC	https://paperswithcode.com/paper/pedagogical-learning
Repo
Framework

Fixing an error in Caponnetto and de Vito (2007)


Title	Fixing an error in Caponnetto and de Vito (2007)
Authors	Dougal J. Sutherland
Abstract	The seminal paper of Caponnetto and de Vito (2007) provides minimax-optimal rates for kernel ridge regression in a very general setting. Its proof, however, contains an error in its bound on the effective dimensionality. In this note, we explain the mistake, provide a correct bound, and show that the main theorem remains true.
Tasks
Published	2017-02-09
URL	http://arxiv.org/abs/1702.02982v1
PDF	http://arxiv.org/pdf/1702.02982v1.pdf
PWC	https://paperswithcode.com/paper/fixing-an-error-in-caponnetto-and-de-vito
Repo
Framework

Geometrical morphology


Title	Geometrical morphology
Authors	John Goldsmith, Eric Rosen
Abstract	We explore inflectional morphology as an example of the relationship of the discrete and the continuous in linguistics. The grammar requests a form of a lexeme by specifying a set of feature values, which corresponds to a corner M of a hypercube in feature value space. The morphology responds to that request by providing a morpheme, or a set of morphemes, whose vector sum is geometrically closest to the corner M. In short, the chosen morpheme $\mu$ is the morpheme (or set of morphemes) that maximizes the inner product of $\mu$ and M.
Tasks
Published	2017-03-13
URL	http://arxiv.org/abs/1703.04481v1
PDF	http://arxiv.org/pdf/1703.04481v1.pdf
PWC	https://paperswithcode.com/paper/geometrical-morphology
Repo
Framework

Iris: A Conversational Agent for Complex Tasks


Title	Iris: A Conversational Agent for Complex Tasks
Authors	Ethan Fast, Binbin Chen, Julia Mendelsohn, Jonathan Bassen, Michael Bernstein
Abstract	Today’s conversational agents are restricted to simple standalone commands. In this paper, we present Iris, an agent that draws on human conversational strategies to combine commands, allowing it to perform more complex tasks that it has not been explicitly designed to support: for example, composing one command to “plot a histogram” with another to first “log-transform the data”. To enable this complexity, we introduce a domain specific language that transforms commands into automata that Iris can compose, sequence, and execute dynamically by interacting with a user through natural language, as well as a conversational type system that manages what kinds of commands can be combined. We have designed Iris to help users with data science tasks, a domain that requires support for command combination. In evaluation, we find that data scientists complete a predictive modeling task significantly faster (2.6 times speedup) with Iris than a modern non-conversational programming environment. Iris supports the same kinds of commands as today’s agents, but empowers users to weave together these commands to accomplish complex goals.
Tasks
Published	2017-07-17
URL	http://arxiv.org/abs/1707.05015v1
PDF	http://arxiv.org/pdf/1707.05015v1.pdf
PWC	https://paperswithcode.com/paper/iris-a-conversational-agent-for-complex-tasks
Repo
Framework

BENGAL: An Automatic Benchmark Generator for Entity Recognition and Linking


Title	BENGAL: An Automatic Benchmark Generator for Entity Recognition and Linking
Authors	Axel-Cyrille Ngonga Ngomo, Michael Röder, Diego Moussallem, Ricardo Usbeck, René Speck
Abstract	The manual creation of gold standards for named entity recognition and entity linking is time- and resource-intensive. Moreover, recent works show that such gold standards contain a large proportion of mistakes in addition to being difficult to maintain. We hence present BENGAL, a novel automatic generation of such gold standards as a complement to manually created benchmarks. The main advantage of our benchmarks is that they can be readily generated at any time. They are also cost-effective while being guaranteed to be free of annotation errors. We compare the performance of 11 tools on benchmarks in English generated by BENGAL and on 16benchmarks created manually. We show that our approach can be ported easily across languages by presenting results achieved by 4 tools on both Brazilian Portuguese and Spanish. Overall, our results suggest that our automatic benchmark generation approach can create varied benchmarks that have characteristics similar to those of existing benchmarks. Our approach is open-source. Our experimental results are available at http://faturl.com/bengalexpinlg and the code at https://github.com/dice-group/BENGAL.
Tasks	Entity Linking, Named Entity Recognition
Published	2017-10-24
URL	http://arxiv.org/abs/1710.08691v3
PDF	http://arxiv.org/pdf/1710.08691v3.pdf
PWC	https://paperswithcode.com/paper/bengal-an-automatic-benchmark-generator-for
Repo
Framework

Beyond Bilingual: Multi-sense Word Embeddings using Multilingual Context


Title	Beyond Bilingual: Multi-sense Word Embeddings using Multilingual Context
Authors	Shyam Upadhyay, Kai-Wei Chang, Matt Taddy, Adam Kalai, James Zou
Abstract	Word embeddings, which represent a word as a point in a vector space, have become ubiquitous to several NLP tasks. A recent line of work uses bilingual (two languages) corpora to learn a different vector for each sense of a word, by exploiting crosslingual signals to aid sense identification. We present a multi-view Bayesian non-parametric algorithm which improves multi-sense word embeddings by (a) using multilingual (i.e., more than two languages) corpora to significantly improve sense embeddings beyond what one achieves with bilingual information, and (b) uses a principled approach to learn a variable number of senses per word, in a data-driven manner. Ours is the first approach with the ability to leverage multilingual corpora efficiently for multi-sense representation learning. Experiments show that multilingual training significantly improves performance over monolingual and bilingual training, by allowing us to combine different parallel corpora to leverage multilingual context. Multilingual training yields comparable performance to a state of the art mono-lingual model trained on five times more training data.
Tasks	Representation Learning, Word Embeddings
Published	2017-06-25
URL	http://arxiv.org/abs/1706.08160v1
PDF	http://arxiv.org/pdf/1706.08160v1.pdf
PWC	https://paperswithcode.com/paper/beyond-bilingual-multi-sense-word-embeddings
Repo
Framework

Improving Palliative Care with Deep Learning


Title	Improving Palliative Care with Deep Learning
Authors	Anand Avati, Kenneth Jung, Stephanie Harman, Lance Downing, Andrew Ng, Nigam H. Shah
Abstract	Improving the quality of end-of-life care for hospitalized patients is a priority for healthcare organizations. Studies have shown that physicians tend to over-estimate prognoses, which in combination with treatment inertia results in a mismatch between patients wishes and actual care at the end of life. We describe a method to address this problem using Deep Learning and Electronic Health Record (EHR) data, which is currently being piloted, with Institutional Review Board approval, at an academic medical center. The EHR data of admitted patients are automatically evaluated by an algorithm, which brings patients who are likely to benefit from palliative care services to the attention of the Palliative Care team. The algorithm is a Deep Neural Network trained on the EHR data from previous years, to predict all-cause 3-12 month mortality of patients as a proxy for patients that could benefit from palliative care. Our predictions enable the Palliative Care team to take a proactive approach in reaching out to such patients, rather than relying on referrals from treating physicians, or conduct time consuming chart reviews of all patients. We also present a novel interpretation technique which we use to provide explanations of the model’s predictions.
Tasks
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06402v1
PDF	http://arxiv.org/pdf/1711.06402v1.pdf
PWC	https://paperswithcode.com/paper/improving-palliative-care-with-deep-learning
Repo
Framework

A Sequential Approximation Framework for Coded Distributed Optimization


Title	A Sequential Approximation Framework for Coded Distributed Optimization
Authors	Jingge Zhu, Ye Pu, Vipul Gupta, Claire Tomlin, Kannan Ramchandran
Abstract	Building on the previous work of Lee et al. and Ferdinand et al. on coded computation, we propose a sequential approximation framework for solving optimization problems in a distributed manner. In a distributed computation system, latency caused by individual processors (“stragglers”) usually causes a significant delay in the overall process. The proposed method is powered by a sequential computation scheme, which is designed specifically for systems with stragglers. This scheme has the desirable property that the user is guaranteed to receive useful (approximate) computation results whenever a processor finishes its subtask, even in the presence of uncertain latency. In this paper, we give a coding theorem for sequentially computing matrix-vector multiplications, and the optimality of this coding scheme is also established. As an application of the results, we demonstrate solving optimization problems using a sequential approximation approach, which accelerates the algorithm in a distributed system with stragglers.
Tasks	Distributed Optimization
Published	2017-10-24
URL	http://arxiv.org/abs/1710.09001v1
PDF	http://arxiv.org/pdf/1710.09001v1.pdf
PWC	https://paperswithcode.com/paper/a-sequential-approximation-framework-for
Repo
Framework

The Network Nullspace Property for Compressed Sensing of Big Data over Networks


Title	The Network Nullspace Property for Compressed Sensing of Big Data over Networks
Authors	Alexander Jung, Madelon Hulsebos
Abstract	We present a novel condition, which we term the net- work nullspace property, which ensures accurate recovery of graph signals representing massive network-structured datasets from few signal values. The network nullspace property couples the cluster structure of the underlying network-structure with the geometry of the sampling set. Our results can be used to design efficient sampling strategies based on the network topology.
Tasks
Published	2017-05-11
URL	http://arxiv.org/abs/1705.04379v4
PDF	http://arxiv.org/pdf/1705.04379v4.pdf
PWC	https://paperswithcode.com/paper/the-network-nullspace-property-for-compressed
Repo
Framework

Multi-task Dictionary Learning based Convolutional Neural Network for Computer aided Diagnosis with Longitudinal Images


Title	Multi-task Dictionary Learning based Convolutional Neural Network for Computer aided Diagnosis with Longitudinal Images
Authors	Jie Zhang, Qingyang Li, Richard J. Caselli, Jieping Ye, Yalin Wang
Abstract	Algorithmic image-based diagnosis and prognosis of neurodegenerative diseases on longitudinal data has drawn great interest from computer vision researchers. The current state-of-the-art models for many image classification tasks are based on the Convolutional Neural Networks (CNN). However, a key challenge in applying CNN to biological problems is that the available labeled training samples are very limited. Another issue for CNN to be applied in computer aided diagnosis applications is that to achieve better diagnosis and prognosis accuracy, one usually has to deal with the longitudinal dataset, i.e., the dataset of images scanned at different time points. Here we argue that an enhanced CNN model with transfer learning for the joint analysis of tasks from multiple time points or regions of interests may have a potential to improve the accuracy of computer aided diagnosis. To reach this goal, we innovate a CNN based deep learning multi-task dictionary learning framework to address the above challenges. Firstly, we pre-train CNN on the ImageNet dataset and transfer the knowledge from the pre-trained model to the medical imaging progression representation, generating the features for different tasks. Then, we propose a novel unsupervised learning method, termed Multi-task Stochastic Coordinate Coding (MSCC), for learning different tasks by using shared and individual dictionaries and generating the sparse features required to predict the future cognitive clinical scores. We apply our new model in a publicly available neuroimaging cohort to predict clinical measures with two different feature sets and compare them with seven other state-of-the-art methods. The experimental results show our proposed method achieved superior results.
Tasks	Dictionary Learning, Image Classification, Transfer Learning
Published	2017-08-31
URL	http://arxiv.org/abs/1709.00042v1
PDF	http://arxiv.org/pdf/1709.00042v1.pdf
PWC	https://paperswithcode.com/paper/multi-task-dictionary-learning-based
Repo
Framework

200x Low-dose PET Reconstruction using Deep Learning


Title	200x Low-dose PET Reconstruction using Deep Learning
Authors	Junshen Xu, Enhao Gong, John Pauly, Greg Zaharchuk
Abstract	Positron emission tomography (PET) is widely used in various clinical applications, including cancer diagnosis, heart disease and neuro disorders. The use of radioactive tracer in PET imaging raises concerns due to the risk of radiation exposure. To minimize this potential risk in PET imaging, efforts have been made to reduce the amount of radio-tracer usage. However, lowing dose results in low Signal-to-Noise-Ratio (SNR) and loss of information, both of which will heavily affect clinical diagnosis. Besides, the ill-conditioning of low-dose PET image reconstruction makes it a difficult problem for iterative reconstruction algorithms. Previous methods proposed are typically complicated and slow, yet still cannot yield satisfactory results at significantly low dose. Here, we propose a deep learning method to resolve this issue with an encoder-decoder residual deep network with concatenate skip connections. Experiments shows the proposed method can reconstruct low-dose PET image to a standard-dose quality with only two-hundredth dose. Different cost functions for training model are explored. Multi-slice input strategy is introduced to provide the network with more structural information and make it more robust to noise. Evaluation on ultra-low-dose clinical data shows that the proposed method can achieve better result than the state-of-the-art methods and reconstruct images with comparable quality using only 0.5% of the original regular dose.
Tasks	Image Reconstruction
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04119v1
PDF	http://arxiv.org/pdf/1712.04119v1.pdf
PWC	https://paperswithcode.com/paper/200x-low-dose-pet-reconstruction-using-deep
Repo
Framework