Paper Group ANR 62
Unsupervised Aspect Term Extraction with B-LSTM & CRF using Automatically Labelled Datasets. Exponentially vanishing sub-optimal local minima in multilayer neural networks. Prediction of the progression of subcortical brain structures in Alzheimer’s disease from baseline. Genetic Algorithm Based Floor Planning System. On the Ontological Modeling of …
Unsupervised Aspect Term Extraction with B-LSTM & CRF using Automatically Labelled Datasets
| Title | Unsupervised Aspect Term Extraction with B-LSTM & CRF using Automatically Labelled Datasets |
| Authors | Athanasios Giannakopoulos, Claudiu Musat, Andreea Hossmann, Michael Baeriswyl |
| Abstract | Aspect Term Extraction (ATE) identifies opinionated aspect terms in texts and is one of the tasks in the SemEval Aspect Based Sentiment Analysis (ABSA) contest. The small amount of available datasets for supervised ATE and the costly human annotation for aspect term labelling give rise to the need for unsupervised ATE. In this paper, we introduce an architecture that achieves top-ranking performance for supervised ATE. Moreover, it can be used efficiently as feature extractor and classifier for unsupervised ATE. Our second contribution is a method to automatically construct datasets for ATE. We train a classifier on our automatically labelled datasets and evaluate it on the human annotated SemEval ABSA test sets. Compared to a strong rule-based baseline, we obtain a dramatically higher F-score and attain precision values above 80%. Our unsupervised method beats the supervised ABSA baseline from SemEval, while preserving high precision scores. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis |
| Published | 2017-09-15 |
| URL | http://arxiv.org/abs/1709.05094v1 |
| http://arxiv.org/pdf/1709.05094v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-aspect-term-extraction-with-b |
| Repo | |
| Framework | |
Exponentially vanishing sub-optimal local minima in multilayer neural networks
| Title | Exponentially vanishing sub-optimal local minima in multilayer neural networks |
| Authors | Daniel Soudry, Elad Hoffer |
| Abstract | Background: Statistical mechanics results (Dauphin et al. (2014); Choromanska et al. (2015)) suggest that local minima with high error are exponentially rare in high dimensions. However, to prove low error guarantees for Multilayer Neural Networks (MNNs), previous works so far required either a heavily modified MNN model or training method, strong assumptions on the labels (e.g., “near” linear separability), or an unrealistic hidden layer with $\Omega\left(N\right)$ units. Results: We examine a MNN with one hidden layer of piecewise linear units, a single output, and a quadratic loss. We prove that, with high probability in the limit of $N\rightarrow\infty$ datapoints, the volume of differentiable regions of the empiric loss containing sub-optimal differentiable local minima is exponentially vanishing in comparison with the same volume of global minima, given standard normal input of dimension $d_{0}=\tilde{\Omega}\left(\sqrt{N}\right)$, and a more realistic number of $d_{1}=\tilde{\Omega}\left(N/d_{0}\right)$ hidden units. We demonstrate our results numerically: for example, $0%$ binary classification training error on CIFAR with only $N/d_{0}\approx 16$ hidden neurons. |
| Tasks | |
| Published | 2017-02-19 |
| URL | http://arxiv.org/abs/1702.05777v5 |
| http://arxiv.org/pdf/1702.05777v5.pdf | |
| PWC | https://paperswithcode.com/paper/exponentially-vanishing-sub-optimal-local |
| Repo | |
| Framework | |
Prediction of the progression of subcortical brain structures in Alzheimer’s disease from baseline
| Title | Prediction of the progression of subcortical brain structures in Alzheimer’s disease from baseline |
| Authors | Alexandre Bône, Maxime Louis, Alexandre Routier, Jorge Samper, Michael Bacci, Benjamin Charlier, Olivier Colliot, Stanley Durrleman |
| Abstract | We propose a method to predict the subject-specific longitudinal progression of brain structures extracted from baseline MRI, and evaluate its performance on Alzheimer’s disease data. The disease progression is modeled as a trajectory on a group of diffeomorphisms in the context of large deformation diffeomorphic metric mapping (LDDMM). We first exhibit the limited predictive abilities of geodesic regression extrapolation on this group. Building on the recent concept of parallel curves in shape manifolds, we then introduce a second predictive protocol which personalizes previously learned trajectories to new subjects, and investigate the relative performances of two parallel shifting paradigms. This design only requires the baseline imaging data. Finally, coefficients encoding the disease dynamics are obtained from longitudinal cognitive measurements for each subject, and exploited to refine our methodology which is demonstrated to successfully predict the follow-up visits. |
| Tasks | |
| Published | 2017-11-23 |
| URL | http://arxiv.org/abs/1711.08716v1 |
| http://arxiv.org/pdf/1711.08716v1.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-of-the-progression-of-subcortical |
| Repo | |
| Framework | |
Genetic Algorithm Based Floor Planning System
| Title | Genetic Algorithm Based Floor Planning System |
| Authors | Hamide Ozlem Dalgic, Erkan Bostanci, Mehmet Serdar Guzel |
| Abstract | Genetic Algorithms are widely used in many different optimization problems including layout design. The layout of the shelves play an important role in the total sales metrics for superstores since this affects the customers’ shopping behaviour. This paper employed a genetic algorithm based approach to design shelf layout of superstores. The layout design problem was tackled by using a novel chromosome representation which takes many different parameters to prevent dead-ends and improve shelf visibility into consideration. Results show that the approach can produce reasonably good layout designs in very short amounts of time. |
| Tasks | |
| Published | 2017-04-20 |
| URL | http://arxiv.org/abs/1704.06016v1 |
| http://arxiv.org/pdf/1704.06016v1.pdf | |
| PWC | https://paperswithcode.com/paper/genetic-algorithm-based-floor-planning-system |
| Repo | |
| Framework | |
On the Ontological Modeling of Trees
| Title | On the Ontological Modeling of Trees |
| Authors | David Carral, Pascal Hitzler, Hilmar Lapp, Sebastian Rudolph |
| Abstract | Trees – i.e., the type of data structure known under this name – are central to many aspects of knowledge organization. We investigate some central design choices concerning the ontological modeling of such trees. In particular, we consider the limits of what is expressible in the Web Ontology Language, and provide a reusable ontology design pattern for trees. |
| Tasks | |
| Published | 2017-10-13 |
| URL | http://arxiv.org/abs/1710.05096v1 |
| http://arxiv.org/pdf/1710.05096v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-ontological-modeling-of-trees |
| Repo | |
| Framework | |
Anomaly detection and motif discovery in symbolic representations of time series
| Title | Anomaly detection and motif discovery in symbolic representations of time series |
| Authors | Fabio Guigou, Pierre Collet, Pierre Parrend |
| Abstract | The advent of the Big Data hype and the consistent recollection of event logs and real-time data from sensors, monitoring software and machine configuration has generated a huge amount of time-varying data in about every sector of the industry. Rule-based processing of such data has ceased to be relevant in many scenarios where anomaly detection and pattern mining have to be entirely accomplished by the machine. Since the early 2000s, the de-facto standard for representing time series has been the Symbolic Aggregate approXimation (SAX).In this document, we present a few algorithms using this representation for anomaly detection and motif discovery, also known as pattern mining, in such data. We propose a benchmark of anomaly detection algorithms using data from Cloud monitoring software. |
| Tasks | Anomaly Detection, Time Series |
| Published | 2017-04-18 |
| URL | http://arxiv.org/abs/1704.05325v1 |
| http://arxiv.org/pdf/1704.05325v1.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-and-motif-discovery-in |
| Repo | |
| Framework | |
Stochastic Recursive Gradient Algorithm for Nonconvex Optimization
| Title | Stochastic Recursive Gradient Algorithm for Nonconvex Optimization |
| Authors | Lam M. Nguyen, Jie Liu, Katya Scheinberg, Martin Takáč |
| Abstract | In this paper, we study and analyze the mini-batch version of StochAstic Recursive grAdient algoritHm (SARAH), a method employing the stochastic recursive gradient, for solving empirical loss minimization for the case of nonconvex losses. We provide a sublinear convergence rate (to stationary points) for general nonconvex functions and a linear convergence rate for gradient dominated functions, both of which have some advantages compared to other modern stochastic gradient algorithms for nonconvex losses. |
| Tasks | |
| Published | 2017-05-20 |
| URL | http://arxiv.org/abs/1705.07261v1 |
| http://arxiv.org/pdf/1705.07261v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-recursive-gradient-algorithm-for |
| Repo | |
| Framework | |
Estimating Nonlinear Dynamics with the ConvNet Smoother
| Title | Estimating Nonlinear Dynamics with the ConvNet Smoother |
| Authors | Luca Ambrogioni, Umut Güçlü, Eric Maris, Marcel van Gerven |
| Abstract | Estimating the state of a dynamical system from a series of noise-corrupted observations is fundamental in many areas of science and engineering. The most well-known method, the Kalman smoother (and the related Kalman filter), relies on assumptions of linearity and Gaussianity that are rarely met in practice. In this paper, we introduced a new dynamical smoothing method that exploits the remarkable capabilities of convolutional neural networks to approximate complex non-linear functions. The main idea is to generate a training set composed of both latent states and observations from an ensemble of simulators and to train the deep network to recover the former from the latter. Importantly, this method only requires the availability of the simulators and can therefore be applied in situations in which either the latent dynamical model or the observation model cannot be easily expressed in closed form. In our simulation studies, we show that the resulting ConvNet smoother has almost optimal performance in the Gaussian case even when the parameters are unknown. Furthermore, the method can be successfully applied to extremely non-linear and non-Gaussian systems. Finally, we empirically validate our approach via the analysis of measured brain signals. |
| Tasks | |
| Published | 2017-02-17 |
| URL | http://arxiv.org/abs/1702.05243v3 |
| http://arxiv.org/pdf/1702.05243v3.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-nonlinear-dynamics-with-the |
| Repo | |
| Framework | |
Cascade one-vs-rest detection network for fine-grained recognition without part annotations
| Title | Cascade one-vs-rest detection network for fine-grained recognition without part annotations |
| Authors | Long Chen, Junyu Dong, ShengKe Wang, Kin-Man Lam, Muwei Jian, Hua Zhang, XiaoChun Cao |
| Abstract | Fine-grained recognition is a challenging task due to the small intra-category variances. Most of top-performing fine-grained recognition methods leverage parts of objects for better performance. Therefore, part annotations which are extremely computationally expensive are required. In this paper, we propose a novel cascaded deep CNN detection framework for fine-grained recognition which is trained to detect the whole object without considering parts. Nevertheless, most of current top-performing detection networks use the N+1 class (N object categories plus background) softmax loss, and the background category with much more training samples dominates the feature learning progress so that the features are not good for object categories with fewer samples. To bridge this gap, we introduce a cascaded structure to eliminate background and exploit a one-vs-rest loss to capture more minute variances among different subordinate categories. Experiments show that our proposed recognition framework achieves comparable performance with state-of-the-art, part-free, fine-grained recognition methods on the CUB-200-2011 Bird dataset. Moreover, our method even outperforms most of part-based methods while does not need part annotations at the training stage and is free from any annotations at test stage. |
| Tasks | |
| Published | 2017-02-28 |
| URL | http://arxiv.org/abs/1702.08692v2 |
| http://arxiv.org/pdf/1702.08692v2.pdf | |
| PWC | https://paperswithcode.com/paper/cascade-one-vs-rest-detection-network-for |
| Repo | |
| Framework | |
A Comparison of Feature-Based and Neural Scansion of Poetry
| Title | A Comparison of Feature-Based and Neural Scansion of Poetry |
| Authors | Manex Agirrezabal, Iñaki Alegria, Mans Hulden |
| Abstract | Automatic analysis of poetic rhythm is a challenging task that involves linguistics, literature, and computer science. When the language to be analyzed is known, rule-based systems or data-driven methods can be used. In this paper, we analyze poetic rhythm in English and Spanish. We show that the representations of data learned from character-based neural models are more informative than the ones from hand-crafted features, and that a Bi-LSTM+CRF-model produces state-of-the art accuracy on scansion of poetry in two languages. Results also show that the information about whole word structure, and not just independent syllables, is highly informative for performing scansion. |
| Tasks | |
| Published | 2017-11-02 |
| URL | http://arxiv.org/abs/1711.00938v1 |
| http://arxiv.org/pdf/1711.00938v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparison-of-feature-based-and-neural |
| Repo | |
| Framework | |
Making Sense of Word Embeddings
| Title | Making Sense of Word Embeddings |
| Authors | Maria Pelevina, Nikolay Arefyev, Chris Biemann, Alexander Panchenko |
| Abstract | We present a simple yet effective approach for learning word sense embeddings. In contrast to existing techniques, which either directly learn sense representations from corpora or rely on sense inventories from lexical resources, our approach can induce a sense inventory from existing word embeddings via clustering of ego-networks of related words. An integrated WSD mechanism enables labeling of words in context with learned sense vectors, which gives rise to downstream applications. Experiments show that the performance of our method is comparable to state-of-the-art unsupervised WSD systems. |
| Tasks | Word Embeddings |
| Published | 2017-08-10 |
| URL | http://arxiv.org/abs/1708.03390v1 |
| http://arxiv.org/pdf/1708.03390v1.pdf | |
| PWC | https://paperswithcode.com/paper/making-sense-of-word-embeddings |
| Repo | |
| Framework | |
Interaction-Based Distributed Learning in Cyber-Physical and Social Networks
| Title | Interaction-Based Distributed Learning in Cyber-Physical and Social Networks |
| Authors | Francesco Sasso, Angelo Coluccia, Giuseppe Notarstefano |
| Abstract | In this paper we consider a network scenario in which agents can evaluate each other according to a score graph that models some physical or social interaction. The goal is to design a distributed protocol, run by the agents, allowing them to learn their unknown state among a finite set of possible values. We propose a Bayesian framework in which scores and states are associated to probabilistic events with unknown parameters and hyperparameters respectively. We prove that each agent can learn its state by means of a local Bayesian classifier and a (centralized) Maximum-Likelihood (ML) estimator of the parameter-hyperparameter that combines plain ML and Empirical Bayes approaches. By using tools from graphical models, which allow us to gain insight on conditional dependences of scores and states, we provide two relaxed probabilistic models that ultimately lead to ML parameter-hyperparameter estimators amenable to distributed computation. In order to highlight the appropriateness of the proposed relaxations, we demonstrate the distributed estimators on a machine-to-machine testing set-up for anomaly detection and on a social interaction set-up for user profiling. |
| Tasks | Anomaly Detection |
| Published | 2017-06-13 |
| URL | http://arxiv.org/abs/1706.04081v1 |
| http://arxiv.org/pdf/1706.04081v1.pdf | |
| PWC | https://paperswithcode.com/paper/interaction-based-distributed-learning-in |
| Repo | |
| Framework | |
Can you find a face in a HEVC bitstream?
| Title | Can you find a face in a HEVC bitstream? |
| Authors | Saeed Ranjbar Alvar, Hyomin Choi, Ivan V. Bajic |
| Abstract | Finding faces in images is one of the most important tasks in computer vision, with applications in biometrics, surveillance, human-computer interaction, and other areas. In our earlier work, we demonstrated that it is possible to tell whether or not an image contains a face by only examining the HEVC syntax, without fully reconstructing the image. In the present work we move further in this direction by showing how to localize faces in HEVC-coded images, without full reconstruction. We also demonstrate the benefits that such approach can have in privacy-friendly face localization. |
| Tasks | |
| Published | 2017-10-30 |
| URL | http://arxiv.org/abs/1710.10736v2 |
| http://arxiv.org/pdf/1710.10736v2.pdf | |
| PWC | https://paperswithcode.com/paper/can-you-find-a-face-in-a-hevc-bitstream |
| Repo | |
| Framework | |
Forecasting and Granger Modelling with Non-linear Dynamical Dependencies
| Title | Forecasting and Granger Modelling with Non-linear Dynamical Dependencies |
| Authors | Magda Gregorová, Alexandros Kalousis, Stéphane Marchand-Maillet |
| Abstract | Traditional linear methods for forecasting multivariate time series are not able to satisfactorily model the non-linear dependencies that may exist in non-Gaussian series. We build on the theory of learning vector-valued functions in the reproducing kernel Hilbert space and develop a method for learning prediction functions that accommodate such non-linearities. The method not only learns the predictive function but also the matrix-valued kernel underlying the function search space directly from the data. Our approach is based on learning multiple matrix-valued kernels, each of those composed of a set of input kernels and a set of output kernels learned in the cone of positive semi-definite matrices. In addition to superior predictive performance in the presence of strong non-linearities, our method also recovers the hidden dynamic relationships between the series and thus is a new alternative to existing graphical Granger techniques. |
| Tasks | Time Series |
| Published | 2017-06-27 |
| URL | http://arxiv.org/abs/1706.08811v1 |
| http://arxiv.org/pdf/1706.08811v1.pdf | |
| PWC | https://paperswithcode.com/paper/forecasting-and-granger-modelling-with-non |
| Repo | |
| Framework | |
Contour Detection from Deep Patch-level Boundary Prediction
| Title | Contour Detection from Deep Patch-level Boundary Prediction |
| Authors | Teck Wee Chua, Li Shen |
| Abstract | In this paper, we present a novel approach for contour detection with Convolutional Neural Networks. A multi-scale CNN learning framework is designed to automatically learn the most relevant features for contour patch detection. Our method uses patch-level measurements to create contour maps with overlapping patches. We show the proposed CNN is able to to detect large-scale contours in an image efficienly. We further propose a guided filtering method to refine the contour maps produced from large-scale contours. Experimental results on the major contour benchmark databases demonstrate the effectiveness of the proposed technique. We show our method can achieve good detection of both fine-scale and large-scale contours. |
| Tasks | Contour Detection |
| Published | 2017-05-09 |
| URL | http://arxiv.org/abs/1705.03159v1 |
| http://arxiv.org/pdf/1705.03159v1.pdf | |
| PWC | https://paperswithcode.com/paper/contour-detection-from-deep-patch-level |
| Repo | |
| Framework | |
