January 27, 2020

2851 words 14 mins read

Paper Group ANR 1158

Data augmentation for low resource sentiment analysis using generative adversarial networks. The excluded area of two-dimensional hard particles. Efficient video indexing for monitoring disease activity and progression in the upper gastrointestinal tract. TreeCaps: Tree-Structured Capsule Networks for Program Source Code Processing. Cross-Lingual S …

Data augmentation for low resource sentiment analysis using generative adversarial networks


Title	Data augmentation for low resource sentiment analysis using generative adversarial networks
Authors	Rahul Gupta
Abstract	Sentiment analysis is a task that may suffer from a lack of data in certain cases, as the datasets are often generated and annotated by humans. In cases where data is inadequate for training discriminative models, generate models may aid training via data augmentation. Generative Adversarial Networks (GANs) are one such model that has advanced the state of the art in several tasks, including as image and text generation. In this paper, I train GAN models on low resource datasets, then use them for the purpose of data augmentation towards improving sentiment classifier generalization. Given the constraints of limited data, I explore various techniques to train the GAN models. I also present an analysis of the quality of generated GAN data as more training data for the GAN is made available. In this analysis, the generated data is evaluated as a test set (against a model trained on real data points) as well as a training set to train classification models. Finally, I also conduct a visual analysis by projecting the generated and the real data into a two-dimensional space using the t-Distributed Stochastic Neighbor Embedding (t-SNE) method.
Tasks	Data Augmentation, Sentiment Analysis, Text Generation
Published	2019-02-18
URL	http://arxiv.org/abs/1902.06818v1
PDF	http://arxiv.org/pdf/1902.06818v1.pdf
PWC	https://paperswithcode.com/paper/data-augmentation-for-low-resource-sentiment
Repo
Framework

The excluded area of two-dimensional hard particles


Title	The excluded area of two-dimensional hard particles
Authors	Thomas Geigenfeind, Daniel de las Heras
Abstract	The excluded area between a pair of two-dimensional hard particles with given relative orientation is the region in which one particle cannot be located due to the presence of the other particle. The magnitude of the excluded area as a function of the relative particle orientation plays a major role in the determination of the bulk phase behaviour of hard particles. We use principal component analysis to identify the different types of excluded area corresponding to randomly generated two-dimensional hard particles modeled as non-self-intersecting polygons and star lines (line segments radiating from a common origin). Only three principal components are required to have an excellent representation of the value of the excluded area as a function of the relative particle orientation. Independently of the particle shape, the minimum value of the excluded area is always achieved when the particles are antiparallel to each other. The property that affects the value of the excluded area most strongly is the elongation of the particle shape. Principal component analysis identifies four limiting cases of excluded areas with one to four global minima at equispaced relative orientations. We study selected particle shapes using Monte Carlo simulations.
Tasks
Published	2019-02-15
URL	http://arxiv.org/abs/1902.05961v1
PDF	http://arxiv.org/pdf/1902.05961v1.pdf
PWC	https://paperswithcode.com/paper/the-excluded-area-of-two-dimensional-hard
Repo
Framework

Efficient video indexing for monitoring disease activity and progression in the upper gastrointestinal tract


Title	Efficient video indexing for monitoring disease activity and progression in the upper gastrointestinal tract
Authors	Sharib Ali, Jens Rittscher
Abstract	Endoscopy is a routine imaging technique used for both diagnosis and minimally invasive surgical treatment. While the endoscopy video contains a wealth of information, tools to capture this information for the purpose of clinical reporting are rather poor. In date, endoscopists do not have any access to tools that enable them to browse the video data in an efficient and user friendly manner. Fast and reliable video retrieval methods could for example, allow them to review data from previous exams and therefore improve their ability to monitor disease progression. Deep learning provides new avenues of compressing and indexing video in an extremely efficient manner. In this study, we propose to use an autoencoder for efficient video compression and fast retrieval of video images. To boost the accuracy of video image retrieval and to address data variability like multi-modality and view-point changes, we propose the integration of a Siamese network. We demonstrate that our approach is competitive in retrieving images from 3 large scale videos of 3 different patients obtained against the query samples of their previous diagnosis. Quantitative validation shows that the combined approach yield an overall improvement of 5% and 8% over classical and variational autoencoders, respectively.
Tasks	Image Retrieval, Video Compression, Video Retrieval
Published	2019-05-10
URL	https://arxiv.org/abs/1905.04384v1
PDF	https://arxiv.org/pdf/1905.04384v1.pdf
PWC	https://paperswithcode.com/paper/efficient-video-indexing-for-monitoring
Repo
Framework

TreeCaps: Tree-Structured Capsule Networks for Program Source Code Processing


Title	TreeCaps: Tree-Structured Capsule Networks for Program Source Code Processing
Authors	Vinoj Jayasundara, Nghi Duy Quoc Bui, Lingxiao Jiang, David Lo
Abstract	Program comprehension is a fundamental task in software development and maintenance processes. Software developers often need to understand a large amount of existing code before they can develop new features or fix bugs in existing programs. Being able to process programming language code automatically and provide summaries of code functionality accurately can significantly help developers to reduce time spent in code navigation and understanding, and thus increase productivity. Different from natural language articles, source code in programming languages often follows rigid syntactical structures and there can exist dependencies among code elements that are located far away from each other through complex control flows and data flows. Existing studies on tree-based convolutional neural networks (TBCNN) and gated graph neural networks (GGNN) are not able to capture essential semantic dependencies among code elements accurately. In this paper, we propose novel tree-based capsule networks (TreeCaps) and relevant techniques for processing program code in an automated way that encodes code syntactical structures and captures code dependencies more accurately. Based on evaluation on programs written in different programming languages, we show that our TreeCaps-based approach can outperform other approaches in classifying the functionalities of many programs.
Tasks
Published	2019-10-27
URL	https://arxiv.org/abs/1910.12306v1
PDF	https://arxiv.org/pdf/1910.12306v1.pdf
PWC	https://paperswithcode.com/paper/treecaps-tree-structured-capsule-networks-for-1
Repo
Framework

Cross-Lingual Sentiment Quantification


Title	Cross-Lingual Sentiment Quantification
Authors	Andrea Esuli, Alejandro Moreo, Fabrizio Sebastiani
Abstract	We discuss \emph{Cross-Lingual Text Quantification} (CLTQ), the task of performing text quantification (i.e., estimating the relative frequency $p_{c}(D)$ of all classes $c\in\mathcal{C}$ in a set $D$ of unlabelled documents) when training documents are available for a source language $\mathcal{S}$ but not for the target language $\mathcal{T}$ for which quantification needs to be performed. CLTQ has never been discussed before in the literature; we establish baseline results for the binary case by combining state-of-the-art quantification methods with methods capable of generating cross-lingual vectorial representations of the source and target documents involved. We present experimental results obtained on publicly available datasets for cross-lingual sentiment classification; the results show that the presented methods can perform CLTQ with a surprising level of accuracy.
Tasks	Sentiment Analysis
Published	2019-04-16
URL	http://arxiv.org/abs/1904.07965v1
PDF	http://arxiv.org/pdf/1904.07965v1.pdf
PWC	https://paperswithcode.com/paper/cross-lingual-sentiment-quantification
Repo
Framework

Requisite Variety in Ethical Utility Functions for AI Value Alignment


Title	Requisite Variety in Ethical Utility Functions for AI Value Alignment
Authors	Nadisha-Marie Aliman, Leon Kester
Abstract	Being a complex subject of major importance in AI Safety research, value alignment has been studied from various perspectives in the last years. However, no final consensus on the design of ethical utility functions facilitating AI value alignment has been achieved yet. Given the urgency to identify systematic solutions, we postulate that it might be useful to start with the simple fact that for the utility function of an AI not to violate human ethical intuitions, it trivially has to be a model of these intuitions and reflect their variety $ - $ whereby the most accurate models pertaining to human entities being biological organisms equipped with a brain constructing concepts like moral judgements, are scientific models. Thus, in order to better assess the variety of human morality, we perform a transdisciplinary analysis applying a security mindset to the issue and summarizing variety-relevant background knowledge from neuroscience and psychology. We complement this information by linking it to augmented utilitarianism as a suitable ethical framework. Based on that, we propose first practical guidelines for the design of approximate ethical goal functions that might better capture the variety of human moral judgements. Finally, we conclude and address future possible challenges.
Tasks
Published	2019-06-30
URL	https://arxiv.org/abs/1907.00430v1
PDF	https://arxiv.org/pdf/1907.00430v1.pdf
PWC	https://paperswithcode.com/paper/requisite-variety-in-ethical-utility
Repo
Framework

Symmetrical Gaussian Error Linear Units (SGELUs)


Title	Symmetrical Gaussian Error Linear Units (SGELUs)
Authors	Chao Yu, Zhiguo Su
Abstract	In this paper, a novel neural network activation function, called Symmetrical Gaussian Error Linear Unit (SGELU), is proposed to obtain high performance. It is achieved by effectively integrating the property of the stochastic regularizer in the Gaussian Error Linear Unit (GELU) with the symmetrical characteristics. Combining with these two merits, the proposed unit introduces the capability of the bidirection convergence to successfully optimize the network without the gradient diminishing problem. The evaluations of SGELU against GELU and Linearly Scaled Hyperbolic Tangent (LiSHT) have been carried out on MNIST classification and MNIST auto-encoder, which provide great validations in terms of the performance, the convergence rate among these applications.
Tasks
Published	2019-11-10
URL	https://arxiv.org/abs/1911.03925v1
PDF	https://arxiv.org/pdf/1911.03925v1.pdf
PWC	https://paperswithcode.com/paper/symmetrical-gaussian-error-linear-units
Repo
Framework

Variable selection with false discovery rate control in deep neural networks


Title	Variable selection with false discovery rate control in deep neural networks
Authors	Zixuan Song, Jun Li
Abstract	Deep neural networks (DNNs) are famous for their high prediction accuracy, but they are also known for their black-box nature and poor interpretability. We consider the problem of variable selection, that is, selecting the input variables that have significant predictive power on the output, in DNNs. We propose a backward elimination procedure called SurvNet, which is based on a new measure of variable importance that applies to a wide variety of networks. More importantly, SurvNet is able to estimate and control the false discovery rate of selected variables, while no existing methods provide such a quality control. Further, SurvNet adaptively determines how many variables to eliminate at each step in order to maximize the selection efficiency. To study its validity, SurvNet is applied to image data and gene expression data, as well as various simulation datasets.
Tasks
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07561v1
PDF	https://arxiv.org/pdf/1909.07561v1.pdf
PWC	https://paperswithcode.com/paper/variable-selection-with-false-discovery-rate
Repo
Framework

A highly likely clusterable data model with no clusters


Title	A highly likely clusterable data model with no clusters
Authors	Mireille Boutin, Alden Bradford
Abstract	We propose a model for a dataset in ${\mathbb R}^D$ that does not contain any clusters but yet is such that a projection of the points on a random one-dimensional subspace is likely to yield a clustering of the points. This model is compatible with some recent empirical observations.
Tasks
Published	2019-09-14
URL	https://arxiv.org/abs/1909.06511v1
PDF	https://arxiv.org/pdf/1909.06511v1.pdf
PWC	https://paperswithcode.com/paper/a-highly-likely-clusterable-data-model-with
Repo
Framework

On the Computation and Applications of Large Dense Partial Correlation Networks


Title	On the Computation and Applications of Large Dense Partial Correlation Networks
Authors	Keith Dillon
Abstract	While sparse inverse covariance matrices are very popular for modeling network connectivity, the value of the dense solution is often overlooked. In fact the L2-regularized solution has deep connections to a number of important applications to spectral graph theory, dimensionality reduction, and uncertainty quantification. We derive an approach to directly compute the partial correlations based on concepts from inverse problem theory. This approach also leads to new insights on open problems such as model selection and data preprocessing, as well as new approaches which relate the above application areas.
Tasks	Dimensionality Reduction, Model Selection
Published	2019-03-17
URL	http://arxiv.org/abs/1903.07181v1
PDF	http://arxiv.org/pdf/1903.07181v1.pdf
PWC	https://paperswithcode.com/paper/on-the-computation-and-applications-of-large
Repo
Framework

Optimizing electrode positions in 2D Electrical Impedance Tomography using deep learning


Title	Optimizing electrode positions in 2D Electrical Impedance Tomography using deep learning
Authors	Danny Smyl, Dong Liu
Abstract	Electrical Impedance Tomography (EIT) is a powerful tool for non-destructive evaluation, state estimation, and process tomography - among numerous other use cases. For these applications, and in order to reliably reconstruct images of a given process using EIT, we must obtain high-quality voltage measurements from the target of interest. As such, it is obvious that the locations of electrodes used for measuring plays a key role in this task. Yet, to date, methods for optimally placing electrodes either require knowledge on the EIT target (which is, in practice, never fully known) or are computationally difficult to implement numerically. In this paper, we circumvent these challenges and present a straightforward deep learning based approach for optimizing electrodes positions. It is found that the optimized electrode positions outperformed “standard” uniformly-distributed electrode layouts in all test cases. Further, it is found that the use of optimized electrode positions computed using the approach derived herein can reduce errors in EIT reconstructions as well as improve the distinguishability of EIT measurements.
Tasks
Published	2019-10-21
URL	https://arxiv.org/abs/1910.10077v2
PDF	https://arxiv.org/pdf/1910.10077v2.pdf
PWC	https://paperswithcode.com/paper/optimizing-electrode-positions-for-2d
Repo
Framework

Neural Networks Weights Quantization: Target None-retraining Ternary (TNT)


Title	Neural Networks Weights Quantization: Target None-retraining Ternary (TNT)
Authors	Tianyu Zhang, Lei Zhu, Qian Zhao, Kilho Shin
Abstract	Quantization of weights of deep neural networks (DNN) has proven to be an effective solution for the purpose of implementing DNNs on edge devices such as mobiles, ASICs and FPGAs, because they have no sufficient resources to support computation involving millions of high precision weights and multiply-accumulate operations. This paper proposes a novel method to compress vectors of high precision weights of DNNs to ternary vectors, namely a cosine similarity based target non-retraining ternary (TNT) compression method. Our method leverages cosine similarity instead of Euclidean distances as commonly used in the literature and succeeds in reducing the size of the search space to find optimal ternary vectors from 3N to N, where N is the dimension of target vectors. As a result, the computational complexity for TNT to find theoretically optimal ternary vectors is only O(N log(N)). Moreover, our experiments show that, when we ternarize models of DNN with high precision parameters, the obtained quantized models can exhibit sufficiently high accuracy so that re-training models is not necessary.
Tasks	Quantization
Published	2019-12-18
URL	https://arxiv.org/abs/1912.09236v1
PDF	https://arxiv.org/pdf/1912.09236v1.pdf
PWC	https://paperswithcode.com/paper/neural-networks-weights-quantization-target
Repo
Framework


Title	Patch-based 3D Human Pose Refinement
Authors	Qingfu Wan, Weichao Qiu, Alan L. Yuille
Abstract	State-of-the-art 3D human pose estimation approaches typically estimate pose from the entire RGB image in a single forward run. In this paper, we develop a post-processing step to refine 3D human pose estimation from body part patches. Using local patches as input has two advantages. First, the fine details around body parts are zoomed in to high resolution for preciser 3D pose prediction. Second, it enables the part appearance to be shared between poses to benefit rare poses. In order to acquire informative representation of patches, we explore different input modalities and validate the superiority of fusing predicted segmentation with RGB. We show that our method consistently boosts the accuracy of state-of-the-art 3D human pose methods.
Tasks	3D Human Pose Estimation, Pose Estimation, Pose Prediction
Published	2019-05-20
URL	https://arxiv.org/abs/1905.08231v1
PDF	https://arxiv.org/pdf/1905.08231v1.pdf
PWC	https://paperswithcode.com/paper/patch-based-3d-human-pose-refinement
Repo
Framework

DARec: Deep Domain Adaptation for Cross-Domain Recommendation via Transferring Rating Patterns


Title	DARec: Deep Domain Adaptation for Cross-Domain Recommendation via Transferring Rating Patterns
Authors	Feng Yuan, Lina Yao, Boualem Benatallah
Abstract	Cross-domain recommendation has long been one of the major topics in recommender systems. Recently, various deep models have been proposed to transfer the learned knowledge across domains, but most of them focus on extracting abstract transferable features from auxilliary contents, e.g., images and review texts, and the patterns in the rating matrix itself is rarely touched. In this work, inspired by the concept of domain adaptation, we proposed a deep domain adaptation model (DARec) that is capable of extracting and transferring patterns from rating matrices {\em only} without relying on any auxillary information. We empirically demonstrate on public datasets that our method achieves the best performance among several state-of-the-art alternative cross-domain recommendation models.
Tasks	Domain Adaptation, Recommendation Systems
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10760v1
PDF	https://arxiv.org/pdf/1905.10760v1.pdf
PWC	https://paperswithcode.com/paper/darec-deep-domain-adaptation-for-cross-domain
Repo
Framework

Improving Robustness of Task Oriented Dialog Systems


Title	Improving Robustness of Task Oriented Dialog Systems
Authors	Arash Einolghozati, Sonal Gupta, Mrinal Mohit, Rushin Shah
Abstract	Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word tagging techniques respectively. Similar to adversarial attack problems with computer vision models discussed in existing literature, these intent-slot tagging models are often over-sensitive to small variations in input – predicting different and often incorrect labels when small changes are made to a query, thus reducing their accuracy and reliability. However, evaluating a model’s robustness to these changes is harder for language since words are discrete and an automated change (e.g. adding `noise’) to a query sometimes changes the meaning and thus labels of a query. In this paper, we first describe how to create an adversarial test set to measure the robustness of these models. Furthermore, we introduce and adapt adversarial training methods as well as data augmentation using back-translation to mitigate these issues. Our experiments show that both techniques improve the robustness of the system substantially and can be combined to yield the best results. \|
Tasks	Adversarial Attack, Data Augmentation, Intent Detection, Sentence Classification
Published	2019-11-12
URL	https://arxiv.org/abs/1911.05153v1
PDF	https://arxiv.org/pdf/1911.05153v1.pdf
PWC	https://paperswithcode.com/paper/improving-robustness-of-task-oriented-dialog
Repo
Framework