Paper Group ANR 66
A Neural Approach to Language Variety Translation. AI based Safety System for Employees of Manufacturing Industries in Developing Countries. Transduction with Matrix Completion Using Smoothed Rank Function. Text Summarization as Tree Transduction by Top-Down TreeLSTM. Generating Artificial Data for Private Deep Learning. Long-Term Human Motion Pred …
A Neural Approach to Language Variety Translation
| Title | A Neural Approach to Language Variety Translation |
| Authors | Marta R. Costa-jussà, Marcos Zampieri, Santanu Pal |
| Abstract | In this paper we present the first neural-based machine translation system trained to translate between standard national varieties of the same language. We take the pair Brazilian - European Portuguese as an example and compare the performance of this method to a phrase-based statistical machine translation system. We report a performance improvement of 0.9 BLEU points in translating from European to Brazilian Portuguese and 0.2 BLEU points when translating in the opposite direction. We also carried out a human evaluation experiment with native speakers of Brazilian Portuguese which indicates that humans prefer the output produced by the neural-based system in comparison to the statistical system. |
| Tasks | Machine Translation |
| Published | 2018-07-02 |
| URL | http://arxiv.org/abs/1807.00651v1 |
| http://arxiv.org/pdf/1807.00651v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-neural-approach-to-language-variety |
| Repo | |
| Framework | |
AI based Safety System for Employees of Manufacturing Industries in Developing Countries
| Title | AI based Safety System for Employees of Manufacturing Industries in Developing Countries |
| Authors | Abhisek Das, Satanik Panda, Suman Datta, Soumitra Naskar, Pratep Misra, Tanushyam Chattopadhyay |
| Abstract | In this paper authors are going to present a Markov Decision Process (MDP) based algorithm in Industrial Internet of Things (IIoT) as a safety compliance layer for human in loop system. Though some industries are moving towards Industry 4.0 and attempting to automate the systems as much as possible by using robots, still human in loop systems are very common in developing countries like India. When ever there is a need for human machine interaction, there is a scope of health hazard. In this work we have developed a system for one such industry using MDP. The proposed algorithm used in this system learned the probability of state transition from experience as well as the system is adaptable to new changes by incorporating the concept of transfer learning. The system was evaluated on the data set obtained from 39 sensors connected to a computer numerically controlled (CNC) machine pushing data every second in a 24x7 scenario. The state changes are typically instructed by a human which subsequently lead to some intentional or unintentional mistakes and errors. The proposed system raises an alarm for the operator to warn which he may or may not overlook depending on his own perception about the present condition of the system. Repeated ignorance of the operator for a particular state transition warning guides the system to retrain the model. We observed 95.61% alarms raised by the said system are taken care of by the operator. 3.2% alarms are coming from the changes in the system which in turn used to retrain the model and 1.19% alarms are false alarms. We could not compute the error coming from the mistake performed by the human operator as there is no ground truth available for that. |
| Tasks | Transfer Learning |
| Published | 2018-11-28 |
| URL | http://arxiv.org/abs/1811.12185v1 |
| http://arxiv.org/pdf/1811.12185v1.pdf | |
| PWC | https://paperswithcode.com/paper/ai-based-safety-system-for-employees-of |
| Repo | |
| Framework | |
Transduction with Matrix Completion Using Smoothed Rank Function
| Title | Transduction with Matrix Completion Using Smoothed Rank Function |
| Authors | Ashkan Esmaeili, Kayhan Behdin, Mohammad Amin Fakharian, Farokh Marvasti |
| Abstract | In this paper, we propose two new algorithms for transduction with Matrix Completion (MC) problem. The joint MC and prediction tasks are addressed simultaneously to enhance the accuracy, i.e., the label matrix is concatenated to the data matrix forming a stacked matrix. Assuming the data matrix is of low rank, we propose new recommendation methods by posing the problem as a constrained minimization of the Smoothed Rank Function (SRF). We provide convergence analysis for the proposed algorithms. The simulations are conducted on real datasets in two different scenarios of randomly missing pattern with and without block loss. The results confirm that the accuracy of our proposed methods outperforms those of state-of-the-art methods even up to 10% in low observation rates for the scenario without block loss. Our accuracy in the latter scenario, is comparable to state-of-the-art methods while the complexity of the proposed algorithms are reduced up to 4 times. |
| Tasks | Matrix Completion |
| Published | 2018-05-19 |
| URL | http://arxiv.org/abs/1805.07561v1 |
| http://arxiv.org/pdf/1805.07561v1.pdf | |
| PWC | https://paperswithcode.com/paper/transduction-with-matrix-completion-using |
| Repo | |
| Framework | |
Text Summarization as Tree Transduction by Top-Down TreeLSTM
| Title | Text Summarization as Tree Transduction by Top-Down TreeLSTM |
| Authors | Davide Bacciu, Antonio Bruno |
| Abstract | Extractive compression is a challenging natural language processing problem. This work contributes by formulating neural extractive compression as a parse tree transduction problem, rather than a sequence transduction task. Motivated by this, we introduce a deep neural model for learning structure-to-substructure tree transductions by extending the standard Long Short-Term Memory, considering the parent-child relationships in the structural recursion. The proposed model can achieve state of the art performance on sentence compression benchmarks, both in terms of accuracy and compression rate. |
| Tasks | Sentence Compression, Text Summarization |
| Published | 2018-09-24 |
| URL | http://arxiv.org/abs/1809.09096v1 |
| http://arxiv.org/pdf/1809.09096v1.pdf | |
| PWC | https://paperswithcode.com/paper/text-summarization-as-tree-transduction-by |
| Repo | |
| Framework | |
Generating Artificial Data for Private Deep Learning
| Title | Generating Artificial Data for Private Deep Learning |
| Authors | Aleksei Triastcyn, Boi Faltings |
| Abstract | In this paper, we propose generating artificial data that retain statistical properties of real data as the means of providing privacy with respect to the original dataset. We use generative adversarial network to draw privacy-preserving artificial data samples and derive an empirical method to assess the risk of information disclosure in a differential-privacy-like way. Our experiments show that we are able to generate artificial data of high quality and successfully train and validate machine learning models on this data while limiting potential privacy loss. |
| Tasks | |
| Published | 2018-03-08 |
| URL | http://arxiv.org/abs/1803.03148v3 |
| http://arxiv.org/pdf/1803.03148v3.pdf | |
| PWC | https://paperswithcode.com/paper/generating-artificial-data-for-private-deep |
| Repo | |
| Framework | |
Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic
| Title | Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic |
| Authors | Yongyi Tang, Lin Ma, Wei Liu, Weishi Zheng |
| Abstract | Human motion prediction aims at generating future frames of human motion based on an observed sequence of skeletons. Recent methods employ the latest hidden states of a recurrent neural network (RNN) to encode the historical skeletons, which can only address short-term prediction. In this work, we propose a motion context modeling by summarizing the historical human motion with respect to the current prediction. A modified highway unit (MHU) is proposed for efficiently eliminating motionless joints and estimating next pose given the motion context. Furthermore, we enhance the motion dynamic by minimizing the gram matrix loss for long-term motion prediction. Experimental results show that the proposed model can promisingly forecast the human future movements, which yields superior performances over related state-of-the-art approaches. Moreover, specifying the motion context with the activity labels enables our model to perform human motion transfer. |
| Tasks | motion prediction |
| Published | 2018-05-07 |
| URL | http://arxiv.org/abs/1805.02513v1 |
| http://arxiv.org/pdf/1805.02513v1.pdf | |
| PWC | https://paperswithcode.com/paper/long-term-human-motion-prediction-by-modeling |
| Repo | |
| Framework | |
Mammographic density: Comparison of visual assessment with fully automatic calculation on a multivendor dataset
| Title | Mammographic density: Comparison of visual assessment with fully automatic calculation on a multivendor dataset |
| Authors | Daniela Sacchetto, Lia Morra, Silvano Agliozzo, Daniela Bernardi, Tomas Bjorklund, Beniamino Brancato, Patrizia Bravetti, Luca A. Carbonaro, Loredana Correale, Carmen Fantò, Elisabetta Favettini, Laura Martincich, Luisella Milanesio, Sara Mombelloni, Francesco Monetti, Doralba Morrone, Marco Pellegrini, Barbara Pesce, Antonella Petrillo, Gianni Saguatti, Carmen Stevanin, Rubina M. Trimboli, Paola Tuttobene, Marvi Valentini, Vincenzo Marra, Alfonso Frigerio, Alberto Bert, Francesco Sardanelli |
| Abstract | Objectives: To compare breast density (BD) assessment provided by an automated BD evaluator (ABDE) with that provided by a panel of experienced breast radiologists, on a multivendor dataset. Methods: Twenty-one radiologists assessed 613 screening/diagnostic digital mammograms from 9 centers and 6 different vendors, using the BI-RADS a, b, c, and d density classification. The same mammograms were also evaluated by an ABDE providing the ratio between fibroglandular and total breast area on a continuous scale and, automatically, the BI-RADS score. Panel majority report (PMR) was used as reference standard. Agreement (k) and accuracy (proportion of cases correctly classified) were calculated for binary (BI-RADS a-b versus c-d) and 4-class classification. Results: While the agreement of individual radiologists with PMR ranged from k=0.483 to k=0.885, the ABDE correctly classified 563/613 mammograms (92%). A substantial agreement for binary classification was found for individual reader pairs (k=0.620, standard deviation [SD]=0.140), individual versus PMR (k=0.736, SD=0.117), and individual versus ABDE (k=0.674, SD=0.095). Agreement between ABDE and PMR was almost perfect (k=0.831). Conclusions: The ABDE showed an almost perfect agreement with a 21-radiologist panel in binary BD classification on a multivendor dataset, earning a chance as a reproducible alternative to visual evaluation. |
| Tasks | |
| Published | 2018-11-13 |
| URL | https://arxiv.org/abs/1811.05324v1 |
| https://arxiv.org/pdf/1811.05324v1.pdf | |
| PWC | https://paperswithcode.com/paper/mammographic-density-comparison-of-visual |
| Repo | |
| Framework | |
Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation
| Title | Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation |
| Authors | Ye Jia, Melvin Johnson, Wolfgang Macherey, Ron J. Weiss, Yuan Cao, Chung-Cheng Chiu, Naveen Ari, Stella Laurenzo, Yonghui Wu |
| Abstract | End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of error compounding. However, the quality of end-to-end ST is often limited by a paucity of training data, since it is difficult to collect large parallel corpora of speech and translated transcript pairs. Previous studies have proposed the use of pre-trained components and multi-task learning in order to benefit from weakly supervised training data, such as speech-to-transcript or text-to-foreign-text pairs. In this paper, we demonstrate that using pre-trained MT or text-to-speech (TTS) synthesis models to convert weakly supervised data into speech-to-translation pairs for ST training can be more effective than multi-task learning. Furthermore, we demonstrate that a high quality end-to-end ST model can be trained using only weakly supervised datasets, and that synthetic data sourced from unlabeled monolingual text or speech can be used to improve performance. Finally, we discuss methods for avoiding overfitting to synthetic speech with a quantitative ablation study. |
| Tasks | Machine Translation, Multi-Task Learning, Speech Recognition |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.02050v2 |
| http://arxiv.org/pdf/1811.02050v2.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-weakly-supervised-data-to-improve |
| Repo | |
| Framework | |
Label Propagation for Learning with Label Proportions
| Title | Label Propagation for Learning with Label Proportions |
| Authors | Rafael Poyiadzi, Raul Santos-Rodriguez, Niall Twomey |
| Abstract | Learning with Label Proportions (LLP) is the problem of recovering the underlying true labels given a dataset when the data is presented in the form of bags. This paradigm is particularly suitable in contexts where providing individual labels is expensive and label aggregates are more easily obtained. In the healthcare domain, it is a burden for a patient to keep a detailed diary of their daily routines, but often they will be amenable to provide higher level summaries of daily behavior. We present a novel and efficient graph-based algorithm that encourages local smoothness and exploits the global structure of the data, while preserving the `mass’ of each bag. | |
| Tasks | |
| Published | 2018-10-24 |
| URL | http://arxiv.org/abs/1810.10328v1 |
| http://arxiv.org/pdf/1810.10328v1.pdf | |
| PWC | https://paperswithcode.com/paper/label-propagation-for-learning-with-label |
| Repo | |
| Framework | |
Random Shuffling Beats SGD after Finite Epochs
| Title | Random Shuffling Beats SGD after Finite Epochs |
| Authors | Jeff Z. HaoChen, Suvrit Sra |
| Abstract | A long-standing problem in the theory of stochastic gradient descent (SGD) is to prove that its without-replacement version RandomShuffle converges faster than the usual with-replacement version. We present the first (to our knowledge) non-asymptotic solution to this problem, which shows that after a “reasonable” number of epochs RandomShuffle indeed converges faster than SGD. Specifically, we prove that under strong convexity and second-order smoothness, the sequence generated by RandomShuffle converges to the optimal solution at the rate O(1/T^2 + n^3/T^3), where n is the number of components in the objective, and T is the total number of iterations. This result shows that after a reasonable number of epochs RandomShuffle is strictly better than SGD (which converges as O(1/T)). The key step toward showing this better dependence on T is the introduction of n into the bound; and as our analysis will show, in general a dependence on n is unavoidable without further changes to the algorithm. We show that for sparse data RandomShuffle has the rate O(1/T^2), again strictly better than SGD. Furthermore, we discuss extensions to nonconvex gradient dominated functions, as well as non-strongly convex settings. |
| Tasks | |
| Published | 2018-06-26 |
| URL | https://arxiv.org/abs/1806.10077v2 |
| https://arxiv.org/pdf/1806.10077v2.pdf | |
| PWC | https://paperswithcode.com/paper/random-shuffling-beats-sgd-after-finite |
| Repo | |
| Framework | |
Seq2Seq and Multi-Task Learning for joint intent and content extraction for domain specific interpreters
| Title | Seq2Seq and Multi-Task Learning for joint intent and content extraction for domain specific interpreters |
| Authors | Marc Velay, Fabrice Daniel |
| Abstract | This study evaluates the performances of an LSTM network for detecting and extracting the intent and content of com- mands for a financial chatbot. It presents two techniques, sequence to sequence learning and Multi-Task Learning, which might improve on the previous task. |
| Tasks | Chatbot, Multi-Task Learning |
| Published | 2018-08-01 |
| URL | http://arxiv.org/abs/1808.00423v1 |
| http://arxiv.org/pdf/1808.00423v1.pdf | |
| PWC | https://paperswithcode.com/paper/seq2seq-and-multi-task-learning-for-joint |
| Repo | |
| Framework | |
DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks
| Title | DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks |
| Authors | J. Caldeira, W. L. K. Wu, B. Nord, C. Avestruz, S. Trivedi, K. T. Story |
| Abstract | Next-generation cosmic microwave background (CMB) experiments will have lower noise and therefore increased sensitivity, enabling improved constraints on fundamental physics parameters such as the sum of neutrino masses and the tensor-to-scalar ratio r. Achieving competitive constraints on these parameters requires high signal-to-noise extraction of the projected gravitational potential from the CMB maps. Standard methods for reconstructing the lensing potential employ the quadratic estimator (QE). However, the QE performs suboptimally at the low noise levels expected in upcoming experiments. Other methods, like maximum likelihood estimators (MLE), are under active development. In this work, we demonstrate reconstruction of the CMB lensing potential with deep convolutional neural networks (CNN) - ie, a ResUNet. The network is trained and tested on simulated data, and otherwise has no physical parametrization related to the physical processes of the CMB and gravitational lensing. We show that, over a wide range of angular scales, ResUNets recover the input gravitational potential with a higher signal-to-noise ratio than the QE method, reaching levels comparable to analytic approximations of MLE methods. We demonstrate that the network outputs quantifiably different lensing maps when given input CMB maps generated with different cosmologies. We also show we can use the reconstructed lensing map for cosmological parameter estimation. This application of CNN provides a few innovations at the intersection of cosmology and machine learning. First, while training and regressing on images, we predict a continuous-variable field rather than discrete classes. Second, we are able to establish uncertainty measures for the network output that are analogous to standard methods. We expect this approach to excel in capturing hard-to-model non-Gaussian astrophysical foreground and noise contributions. |
| Tasks | |
| Published | 2018-10-02 |
| URL | https://arxiv.org/abs/1810.01483v2 |
| https://arxiv.org/pdf/1810.01483v2.pdf | |
| PWC | https://paperswithcode.com/paper/deepcmb-lensing-reconstruction-of-the-cosmic |
| Repo | |
| Framework | |
Support Vector Machine (SVM) Recognition Approach adapted to Individual and Touching Moths Counting in Trap Images
| Title | Support Vector Machine (SVM) Recognition Approach adapted to Individual and Touching Moths Counting in Trap Images |
| Authors | Mohamed Chafik Bakkay, Sylvie Chambon, Hatem A. Rashwan, Christian Lubat, Sébastien Barsotti |
| Abstract | This paper aims at developing an automatic algorithm for moth recognition from trap images in real-world conditions. This method uses our previous work for detection [1] and introduces an adapted classification step. More precisely, SVM classifier is trained with a multi-scale descriptor, Histogram Of Curviness Saliency (HCS). This descriptor is robust to illumination changes and is able to detect and to describe the external and the internal contours of the target insect in multi-scale. The proposed classification method can be trained with a small set of images. Quantitative evaluations show that the proposed method is able to classify insects with higher accuracy (rate of 95.8%) than the state-of-the art approaches. |
| Tasks | |
| Published | 2018-09-18 |
| URL | http://arxiv.org/abs/1809.06663v1 |
| http://arxiv.org/pdf/1809.06663v1.pdf | |
| PWC | https://paperswithcode.com/paper/support-vector-machine-svm-recognition |
| Repo | |
| Framework | |
Model change detection with application to machine learning
| Title | Model change detection with application to machine learning |
| Authors | Yuheng Bu, Jiaxun Lu, Venugopal V. Veeravalli |
| Abstract | Model change detection is studied, in which there are two sets of samples that are independently and identically distributed (i.i.d.) according to a pre-change probabilistic model with parameter $\theta$, and a post-change model with parameter $\theta'$, respectively. The goal is to detect whether the change in the model is significant, i.e., whether the difference between the pre-change parameter and the post-change parameter $\theta-\theta’_2$ is larger than a pre-determined threshold $\rho$. The problem is considered in a Neyman-Pearson setting, where the goal is to maximize the probability of detection under a false alarm constraint. Since the generalized likelihood ratio test (GLRT) is difficult to compute in this problem, we construct an empirical difference test (EDT), which approximates the GLRT and has low computational complexity. Moreover, we provide an approximation method to set the threshold of the EDT to meet the false alarm constraint. Experiments with linear regression and logistic regression are conducted to validate the proposed algorithms. |
| Tasks | |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1811.07957v1 |
| http://arxiv.org/pdf/1811.07957v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-change-detection-with-application-to |
| Repo | |
| Framework | |
Self-Guided Belief Propagation – A Homotopy Continuation Method
| Title | Self-Guided Belief Propagation – A Homotopy Continuation Method |
| Authors | Christian Knoll, Florian Kulmer, Franz Pernkopf |
| Abstract | We propose self-guided belief propagation (SBP) that modifies belief propagation (BP) by incorporating the pairwise potentials only gradually. This homotopy continuation method converges to a unique solution and increases the accuracy without increasing the computational burden. We apply SBP to grid graphs, complete graphs, and random graphs with random Ising potentials and show that: (i) SBP is superior in terms of accuracy whenever BP converges, and (ii) SBP obtains a unique, stable, and accurate solution whenever BP does not converge. We further provide a formal analysis to demonstrate that SBP obtains the global optimum of the Bethe approximation for attractive models with unidirectional fields. |
| Tasks | |
| Published | 2018-12-04 |
| URL | http://arxiv.org/abs/1812.01339v1 |
| http://arxiv.org/pdf/1812.01339v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-guided-belief-propagation-a-homotopy |
| Repo | |
| Framework | |
