Paper Group ANR 90
Neural Network-Based Abstract Generation for Opinions and Arguments. Visual Saliency Detection Based on Multiscale Deep CNN Features. Extracting Arabic Relations from the Web. Experimental Assessment of Aggregation Principles in Argumentation-enabled Collective Intelligence. Supervised multiway factorization. Mouse Movement and Probabilistic Graphi …
Neural Network-Based Abstract Generation for Opinions and Arguments
| Title | Neural Network-Based Abstract Generation for Opinions and Arguments |
| Authors | Lu Wang, Wang Ling |
| Abstract | We study the problem of generating abstractive summaries for opinionated text. We propose an attention-based neural network model that is able to absorb information from multiple text units to construct informative, concise, and fluent summaries. An importance-based sampling method is designed to allow the encoder to integrate information from an important subset of input. Automatic evaluation indicates that our system outperforms state-of-the-art abstractive and extractive summarization systems on two newly collected datasets of movie reviews and arguments. Our system summaries are also rated as more informative and grammatical in human evaluation. |
| Tasks | |
| Published | 2016-06-09 |
| URL | http://arxiv.org/abs/1606.02785v1 |
| http://arxiv.org/pdf/1606.02785v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-based-abstract-generation-for |
| Repo | |
| Framework | |
Visual Saliency Detection Based on Multiscale Deep CNN Features
| Title | Visual Saliency Detection Based on Multiscale Deep CNN Features |
| Authors | Guanbin Li, Yizhou Yu |
| Abstract | Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks (CNNs), which have had many successes in visual recognition tasks. For learning such saliency models, we introduce a neural network architecture, which has fully connected layers on top of CNNs responsible for feature extraction at three different scales. The penultimate layer of our neural network has been confirmed to be a discriminative high-level feature vector for saliency detection, which we call deep contrast feature. To generate a more robust feature, we integrate handcrafted low-level features with our deep contrast feature. To promote further research and evaluation of visual saliency models, we also construct a new large database of 4447 challenging images and their pixelwise saliency annotations. Experimental results demonstrate that our proposed method is capable of achieving state-of-the-art performance on all public benchmarks, improving the F- measure by 6.12% and 10.0% respectively on the DUT-OMRON dataset and our new dataset (HKU-IS), and lowering the mean absolute error by 9% and 35.3% respectively on these two datasets. |
| Tasks | Saliency Detection |
| Published | 2016-09-07 |
| URL | http://arxiv.org/abs/1609.02077v1 |
| http://arxiv.org/pdf/1609.02077v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-saliency-detection-based-on-multiscale |
| Repo | |
| Framework | |
Extracting Arabic Relations from the Web
| Title | Extracting Arabic Relations from the Web |
| Authors | Shimaa M. Abd El-salam, Enas M. F. El Houby, A. K. Al Sammak, T. A. El-Shishtawy |
| Abstract | The goal of this research is to extract a large list or table from named entities and relations in a specific domain. A small set of a handful of instance relations is required as input from the user. The system exploits summaries from Google search engine as a source text. These instances are used to extract patterns. The output is a set of new entities and their relations. The results from four experiments show that precision and recall varies according to relation type. Precision ranges from 0.61 to 0.75 while recall ranges from 0.71 to 0.83. The best result is obtained for (player, club) relationship, 0.72 and 0.83 for precision and recall respectively. |
| Tasks | |
| Published | 2016-03-08 |
| URL | http://arxiv.org/abs/1603.02488v1 |
| http://arxiv.org/pdf/1603.02488v1.pdf | |
| PWC | https://paperswithcode.com/paper/extracting-arabic-relations-from-the-web |
| Repo | |
| Framework | |
Experimental Assessment of Aggregation Principles in Argumentation-enabled Collective Intelligence
| Title | Experimental Assessment of Aggregation Principles in Argumentation-enabled Collective Intelligence |
| Authors | Edmond Awad, Jean-François Bonnefon, Martin Caminada, Thomas Malone, Iyad Rahwan |
| Abstract | On the Web, there is always a need to aggregate opinions from the crowd (as in posts, social networks, forums, etc.). Different mechanisms have been implemented to capture these opinions such as “Like” in Facebook, “Favorite” in Twitter, thumbs-up/down, flagging, and so on. However, in more contested domains (e.g. Wikipedia, political discussion, and climate change discussion) these mechanisms are not sufficient since they only deal with each issue independently without considering the relationships between different claims. We can view a set of conflicting arguments as a graph in which the nodes represent arguments and the arcs between these nodes represent the defeat relation. A group of people can then collectively evaluate such graphs. To do this, the group must use a rule to aggregate their individual opinions about the entire argument graph. Here, we present the first experimental evaluation of different principles commonly employed by aggregation rules presented in the literature. We use randomized controlled experiments to investigate which principles people consider better at aggregating opinions under different conditions. Our analysis reveals a number of factors, not captured by traditional formal models, that play an important role in determining the efficacy of aggregation. These results help bring formal models of argumentation closer to real-world application. |
| Tasks | |
| Published | 2016-04-03 |
| URL | http://arxiv.org/abs/1604.00681v2 |
| http://arxiv.org/pdf/1604.00681v2.pdf | |
| PWC | https://paperswithcode.com/paper/experimental-assessment-of-aggregation |
| Repo | |
| Framework | |
Supervised multiway factorization
| Title | Supervised multiway factorization |
| Authors | Eric F. Lock, Gen Li |
| Abstract | We describe a probabilistic PARAFAC/CANDECOMP (CP) factorization for multiway (i.e., tensor) data that incorporates auxiliary covariates, SupCP. SupCP generalizes the supervised singular value decomposition (SupSVD) for vector-valued observations, to allow for observations that have the form of a matrix or higher-order array. Such data are increasingly encountered in biomedical research and other fields. We describe a likelihood-based latent variable representation of the CP factorization, in which the latent variables are informed by additional covariates. We give conditions for identifiability, and develop an EM algorithm for simultaneous estimation of all model parameters. SupCP can be used for dimension reduction, capturing latent structures that are more accurate and interpretable due to covariate supervision. Moreover, SupCP specifies a full probability distribution for a multiway data observation with given covariate values, which can be used for predictive modeling. We conduct comprehensive simulations to evaluate the SupCP algorithm. We apply it to a facial image database with facial descriptors (e.g., smiling / not smiling) as covariates, and to a study of amino acid fluorescence. Software is available at https://github.com/lockEF/SupCP . |
| Tasks | Dimensionality Reduction |
| Published | 2016-09-11 |
| URL | http://arxiv.org/abs/1609.03228v2 |
| http://arxiv.org/pdf/1609.03228v2.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-multiway-factorization |
| Repo | |
| Framework | |
Mouse Movement and Probabilistic Graphical Models Based E-Learning Activity Recognition Improvement Possibilistic Model
| Title | Mouse Movement and Probabilistic Graphical Models Based E-Learning Activity Recognition Improvement Possibilistic Model |
| Authors | Anis Elbahi, Mohamed Nazih Omri, Mohamed Ali Mahjoub, Kamel Garrouch |
| Abstract | Automatically recognizing the e-learning activities is an important task for improving the online learning process. Probabilistic graphical models such as hidden Markov models and conditional random fields have been successfully used in order to identify a Web users activity. For such models, the sequences of observation are crucial for training and inference processes. Despite the efficiency of these probabilistic graphical models in segmenting and labeling stochastic sequences, their performance is adversely affected by the imperfect quality of data used for the construction of sequences of observation. In this paper, a formalism of the possibilistic theory will be used in order to propose a new approach for observation sequences preparation. The eminent contribution of our approach is to evaluate the effect of possibilistic reasoning during the generation of observation sequences on the effectiveness of hidden Markov models and conditional random fields models. Using a dataset containing 51 real manipulations related to three types of learners tasks, the preliminary experiments demonstrate that the sequences of observation obtained based on possibilistic reasoning significantly improve the performance of hidden Marvov models and conditional random fields models in the automatic recognition of the e-learning activities. |
| Tasks | Activity Recognition |
| Published | 2016-08-08 |
| URL | http://arxiv.org/abs/1608.02659v1 |
| http://arxiv.org/pdf/1608.02659v1.pdf | |
| PWC | https://paperswithcode.com/paper/mouse-movement-and-probabilistic-graphical |
| Repo | |
| Framework | |
Tight Performance Bounds for Compressed Sensing With Conventional and Group Sparsity
| Title | Tight Performance Bounds for Compressed Sensing With Conventional and Group Sparsity |
| Authors | Shashank Ranjan, Mathukumalli Vidyasagar |
| Abstract | In this paper, we study the problem of recovering a group sparse vector from a small number of linear measurements. In the past the common approach has been to use various “group sparsity-inducing” norms such as the Group LASSO norm for this purpose. By using the theory of convex relaxations, we show that it is also possible to use $\ell_1$-norm minimization for group sparse recovery. We introduce a new concept called group robust null space property (GRNSP), and show that, under suitable conditions, a group version of the restricted isometry property (GRIP) implies the GRNSP, and thus leads to group sparse recovery. When all groups are of equal size, our bounds are less conservative than known bounds. Moreover, our results apply even to situations where where the groups have different sizes. When specialized to conventional sparsity, our bounds reduce to one of the well-known “best possible” conditions for sparse recovery. This relationship between GRNSP and GRIP is new even for conventional sparsity, and substantially streamlines the proofs of some known results. Using this relationship, we derive bounds on the $\ell_p$-norm of the residual error vector for all $p \in [1,2]$, and not just when $p = 2$. When the measurement matrix consists of random samples of a sub-Gaussian random variable, we present bounds on the number of measurements, which are less conservative than currently known bounds. |
| Tasks | |
| Published | 2016-06-19 |
| URL | http://arxiv.org/abs/1606.05889v2 |
| http://arxiv.org/pdf/1606.05889v2.pdf | |
| PWC | https://paperswithcode.com/paper/tight-performance-bounds-for-compressed |
| Repo | |
| Framework | |
The DARPA Twitter Bot Challenge
| Title | The DARPA Twitter Bot Challenge |
| Authors | V. S. Subrahmanian, Amos Azaria, Skylar Durst, Vadim Kagan, Aram Galstyan, Kristina Lerman, Linhong Zhu, Emilio Ferrara, Alessandro Flammini, Filippo Menczer, Andrew Stevens, Alexander Dekhtyar, Shuyang Gao, Tad Hogg, Farshad Kooti, Yan Liu, Onur Varol, Prashant Shiralkar, Vinod Vydiswaran, Qiaozhu Mei, Tim Hwang |
| Abstract | A number of organizations ranging from terrorist groups such as ISIS to politicians and nation states reportedly conduct explicit campaigns to influence opinion on social media, posing a risk to democratic processes. There is thus a growing need to identify and eliminate “influence bots” - realistic, automated identities that illicitly shape discussion on sites like Twitter and Facebook - before they get too influential. Spurred by such events, DARPA held a 4-week competition in February/March 2015 in which multiple teams supported by the DARPA Social Media in Strategic Communications program competed to identify a set of previously identified “influence bots” serving as ground truth on a specific topic within Twitter. Past work regarding influence bots often has difficulty supporting claims about accuracy, since there is limited ground truth (though some exceptions do exist [3,7]). However, with the exception of [3], no past work has looked specifically at identifying influence bots on a specific topic. This paper describes the DARPA Challenge and describes the methods used by the three top-ranked teams. |
| Tasks | |
| Published | 2016-01-20 |
| URL | http://arxiv.org/abs/1601.05140v2 |
| http://arxiv.org/pdf/1601.05140v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-darpa-twitter-bot-challenge |
| Repo | |
| Framework | |
Stroke Sequence-Dependent Deep Convolutional Neural Network for Online Handwritten Chinese Character Recognition
| Title | Stroke Sequence-Dependent Deep Convolutional Neural Network for Online Handwritten Chinese Character Recognition |
| Authors | Baotian Hu, Xin Liu, Xiangping Wu, Qingcai Chen |
| Abstract | In this paper, we propose a novel model, named Stroke Sequence-dependent Deep Convolutional Neural Network (SSDCNN), using the stroke sequence information and eight-directional features for Online Handwritten Chinese Character Recognition (OLHCCR). On one hand, SSDCNN can learn the representation of Online Handwritten Chinese Character (OLHCC) by incorporating the natural sequence information of the strokes. On the other hand, SSDCNN can incorporate eight-directional features in a natural way. In order to train SSDCNN, we divide the process of training into two stages: 1) The training data is used to pre-train the whole architecture until the performance tends to converge. 2) Fully-connected neural network which is used to combine the stroke sequence-dependent representation with eight-directional features and softmax layer are further trained. Experiments were conducted on the OLHCCR competition tasks of ICDAR 2013. Results show that, SSDCNN can reduce the recognition error by 50% (5.13% vs 2.56%) compared to the model which only use eight-directional features. The proposed SSDCNN achieves 97.44% accuracy which reduces the recognition error by about 1.9% compared with the best submitted system on ICDAR2013 competition. These results indicate that SSDCNN can exploit the stroke sequence information to learn high-quality representation of OLHCC. It also shows that the learnt representation and the classical eight-directional features complement each other within the SSDCNN architecture. |
| Tasks | |
| Published | 2016-10-13 |
| URL | http://arxiv.org/abs/1610.04057v1 |
| http://arxiv.org/pdf/1610.04057v1.pdf | |
| PWC | https://paperswithcode.com/paper/stroke-sequence-dependent-deep-convolutional |
| Repo | |
| Framework | |
Evolutionary Projection Selection for Radon Barcodes
| Title | Evolutionary Projection Selection for Radon Barcodes |
| Authors | Hamid R. Tizhoosh, Shahryar Rahnamayan |
| Abstract | Recently, Radon transformation has been used to generate barcodes for tagging medical images. The under-sampled image is projected in certain directions, and each projection is binarized using a local threshold. The concatenation of the thresholded projections creates a barcode that can be used for tagging or annotating medical images. A small number of equidistant projections, e.g., 4 or 8, is generally used to generate short barcodes. However, due to the diverse nature of digital images, and since we are only working with a small number of projections (to keep the barcode short), taking equidistant projections may not be the best course of action. In this paper, we proposed to find $n$ optimal projections, whereas $n!<!180$, in order to increase the expressiveness of Radon barcodes. We show examples for the exhaustive search for the simple case when we attempt to find 4 best projections out of 16 equidistant projections and compare it with the evolutionary approach in order to establish the benefit of the latter when operating on a small population size as in the case of micro-DE. We randomly selected 10 different classes from IRMA dataset (14,400 x-ray images in 58 classes) and further randomly selected 5 images per class for our tests. |
| Tasks | |
| Published | 2016-04-16 |
| URL | http://arxiv.org/abs/1604.04673v1 |
| http://arxiv.org/pdf/1604.04673v1.pdf | |
| PWC | https://paperswithcode.com/paper/evolutionary-projection-selection-for-radon |
| Repo | |
| Framework | |
Online Machine Learning Techniques for Predicting Operator Performance
| Title | Online Machine Learning Techniques for Predicting Operator Performance |
| Authors | Ahmet Anil Pala |
| Abstract | This thesis explores a number of online machine learning algorithms. From a theoret- ical perspective, it assesses their employability for a particular function approximation problem where the analytical models fall short. Furthermore, it discusses the applica- tion of theoretically suitable learning algorithms to the function approximation problem at hand through an efficient implementation that exploits various computational and mathematical shortcuts. Finally, this thesis work evaluates the implemented learning algorithms according to various evaluation criteria through rigorous testing. |
| Tasks | |
| Published | 2016-05-03 |
| URL | http://arxiv.org/abs/1605.01029v1 |
| http://arxiv.org/pdf/1605.01029v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-machine-learning-techniques-for |
| Repo | |
| Framework | |
The Interaction of Memory and Attention in Novel Word Generalization: A Computational Investigation
| Title | The Interaction of Memory and Attention in Novel Word Generalization: A Computational Investigation |
| Authors | Erin Grant, Aida Nematzadeh, Suzanne Stevenson |
| Abstract | People exhibit a tendency to generalize a novel noun to the basic-level in a hierarchical taxonomy – a cognitively salient category such as “dog” – with the degree of generalization depending on the number and type of exemplars. Recently, a change in the presentation timing of exemplars has also been shown to have an effect, surprisingly reversing the prior observed pattern of basic-level generalization. We explore the precise mechanisms that could lead to such behavior by extending a computational model of word learning and word generalization to integrate cognitive processes of memory and attention. Our results show that the interaction of forgetting and attention to novelty, as well as sensitivity to both type and token frequencies of exemplars, enables the model to replicate the empirical results from different presentation timings. Our results reinforce the need to incorporate general cognitive processes within word learning models to better understand the range of observed behaviors in vocabulary acquisition. |
| Tasks | |
| Published | 2016-02-18 |
| URL | http://arxiv.org/abs/1602.05944v1 |
| http://arxiv.org/pdf/1602.05944v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-interaction-of-memory-and-attention-in |
| Repo | |
| Framework | |
Towards Bin Packing (preliminary problem survey, models with multiset estimates)
| Title | Towards Bin Packing (preliminary problem survey, models with multiset estimates) |
| Authors | Mark Sh. Levin |
| Abstract | The paper described a generalized integrated glance to bin packing problems including a brief literature survey and some new problem formulations for the cases of multiset estimates of items. A new systemic viewpoint to bin packing problems is suggested: (a) basic element sets (item set, bin set, item subset assigned to bin), (b) binary relation over the sets: relation over item set as compatibility, precedence, dominance; relation over items and bins (i.e., correspondence of items to bins). A special attention is targeted to the following versions of bin packing problems: (a) problem with multiset estimates of items, (b) problem with colored items (and some close problems). Applied examples of bin packing problems are considered: (i) planning in paper industry (framework of combinatorial problems), (ii) selection of information messages, (iii) packing of messages/information packages in WiMAX communication system (brief description). |
| Tasks | |
| Published | 2016-05-24 |
| URL | http://arxiv.org/abs/1605.07574v1 |
| http://arxiv.org/pdf/1605.07574v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-bin-packing-preliminary-problem |
| Repo | |
| Framework | |
Stability and Structural Properties of Gene Regulation Networks with Coregulation Rules
| Title | Stability and Structural Properties of Gene Regulation Networks with Coregulation Rules |
| Authors | Jonathan H. Warrell, Musa M. Mhlanga |
| Abstract | Coregulation of the expression of groups of genes has been extensively demonstrated empirically in bacterial and eukaryotic systems. Such coregulation can arise through the use of shared regulatory motifs, which allow the coordinated expression of modules (and module groups) of functionally related genes across the genome. Coregulation can also arise through the physical association of multi-gene complexes through chromosomal looping, which are then transcribed together. We present a general formalism for modeling coregulation rules in the framework of Random Boolean Networks (RBN), and develop specific models for transcription factor networks with modular structure (including module groups, and multi-input modules (MIM) with autoregulation) and multi-gene complexes (including hierarchical differentiation between multi-gene complex members). We develop a mean-field approach to analyse the stability of large networks incorporating coregulation, and show that autoregulated MIM and hierarchical gene-complex models can achieve greater stability than networks without coregulation whose rules have matching activation frequency. We provide further analysis of the stability of small networks of both kinds through simulations. We also characterize several general properties of the transients and attractors in the hierarchical coregulation model, and show using simulations that the steady-state distribution factorizes hierarchically as a Bayesian network in a Markov Jump Process analogue of the RBN model. |
| Tasks | |
| Published | 2016-02-28 |
| URL | http://arxiv.org/abs/1602.08753v2 |
| http://arxiv.org/pdf/1602.08753v2.pdf | |
| PWC | https://paperswithcode.com/paper/stability-and-structural-properties-of-gene |
| Repo | |
| Framework | |
Limit theorems for eigenvectors of the normalized Laplacian for random graphs
| Title | Limit theorems for eigenvectors of the normalized Laplacian for random graphs |
| Authors | Minh Tang, Carey E. Priebe |
| Abstract | We prove a central limit theorem for the components of the eigenvectors corresponding to the $d$ largest eigenvalues of the normalized Laplacian matrix of a finite dimensional random dot product graph. As a corollary, we show that for stochastic blockmodel graphs, the rows of the spectral embedding of the normalized Laplacian converge to multivariate normals and furthermore the mean and the covariance matrix of each row are functions of the associated vertex’s block membership. Together with prior results for the eigenvectors of the adjacency matrix, we then compare, via the Chernoff information between multivariate normal distributions, how the choice of embedding method impacts subsequent inference. We demonstrate that neither embedding method dominates with respect to the inference task of recovering the latent block assignments. |
| Tasks | |
| Published | 2016-07-28 |
| URL | http://arxiv.org/abs/1607.08601v1 |
| http://arxiv.org/pdf/1607.08601v1.pdf | |
| PWC | https://paperswithcode.com/paper/limit-theorems-for-eigenvectors-of-the |
| Repo | |
| Framework | |
