Paper Group ANR 28
Character-based Neural Machine Translation. Machine-based Multimodal Pain Assessment Tool for Infants: A Review. Knowledge Representation on the Web revisited: Tools for Prototype Based Ontologies. KGEval: Estimating Accuracy of Automatically Constructed Knowledge Graphs. On Context-Dependent Clustering of Bandits. Dopamine modulation of prefrontal …
Character-based Neural Machine Translation
| Title | Character-based Neural Machine Translation |
| Authors | Marta R. Costa-Jussà, José A. R. Fonollosa |
| Abstract | Neural Machine Translation (MT) has reached state-of-the-art results. However, one of the main challenges that neural MT still faces is dealing with very large vocabularies and morphologically rich languages. In this paper, we propose a neural MT system using character-based embeddings in combination with convolutional and highway layers to replace the standard lookup-based word representations. The resulting unlimited-vocabulary and affix-aware source word embeddings are tested in a state-of-the-art neural MT based on an attention-based bidirectional recurrent neural network. The proposed MT scheme provides improved results even when the source language is not morphologically rich. Improvements up to 3 BLEU points are obtained in the German-English WMT task. |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2016-03-02 |
| URL | http://arxiv.org/abs/1603.00810v3 |
| http://arxiv.org/pdf/1603.00810v3.pdf | |
| PWC | https://paperswithcode.com/paper/character-based-neural-machine-translation |
| Repo | |
| Framework | |
Machine-based Multimodal Pain Assessment Tool for Infants: A Review
| Title | Machine-based Multimodal Pain Assessment Tool for Infants: A Review |
| Authors | Ghada Zamzmi, Dmitry Goldgof, Rangachar Kasturi, Yu Sun, Terri Ashmeade |
| Abstract | Bedside caregivers assess infants’ pain at constant intervals by observing specific behavioral and physiological signs of pain. This standard has two main limitations. The first limitation is the intermittent assessment of pain, which might lead to missing pain when the infants are left unattended. Second, it is inconsistent since it depends on the observer’s subjective judgment and differs between observers. The intermittent and inconsistent assessment can induce poor treatment and, therefore, cause serious long-term consequences. To mitigate these limitations, the current standard can be augmented by an automated system that monitors infants continuously and provides quantitative and consistent assessment of pain. Several automated methods have been introduced to assess infants’ pain automatically based on analysis of behavioral or physiological pain indicators. This paper comprehensively reviews the automated approaches (i.e., approaches to feature extraction) for analyzing infants’ pain and the current efforts in automatic pain recognition. In addition, it reviews the databases available to the research community and discusses the current limitations of the automated pain assessment. |
| Tasks | |
| Published | 2016-07-01 |
| URL | http://arxiv.org/abs/1607.00331v3 |
| http://arxiv.org/pdf/1607.00331v3.pdf | |
| PWC | https://paperswithcode.com/paper/machine-based-multimodal-pain-assessment-tool |
| Repo | |
| Framework | |
Knowledge Representation on the Web revisited: Tools for Prototype Based Ontologies
| Title | Knowledge Representation on the Web revisited: Tools for Prototype Based Ontologies |
| Authors | Michael Cochez, Stefan Decker, Eric Prud’hommeaux |
| Abstract | In recent years RDF and OWL have become the most common knowledge representation languages in use on the Web, propelled by the recommendation of the W3C. In this paper we present a practical implementation of a different kind of knowledge representation based on Prototypes. In detail, we present a concrete syntax easily and effectively parsable by applications. We also present extensible implementations of a prototype knowledge base, specifically designed for storage of Prototypes. These implementations are written in Java and can be extended by using the implementation as a library. Alternatively, the software can be deployed as such. Further, results of benchmarks for both local and web deployment are presented. This paper augments a research paper, in which we describe the more theoretical aspects of our Prototype system. |
| Tasks | |
| Published | 2016-07-16 |
| URL | http://arxiv.org/abs/1607.04809v1 |
| http://arxiv.org/pdf/1607.04809v1.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-representation-on-the-web-revisited |
| Repo | |
| Framework | |
KGEval: Estimating Accuracy of Automatically Constructed Knowledge Graphs
| Title | KGEval: Estimating Accuracy of Automatically Constructed Knowledge Graphs |
| Authors | Prakhar Ojha, Partha Talukdar |
| Abstract | Automatic construction of large knowledge graphs (KG) by mining web-scale text datasets has received considerable attention recently. Estimating accuracy of such automatically constructed KGs is a challenging problem due to their size and diversity. This important problem has largely been ignored in prior research we fill this gap and propose KGEval. KGEval binds facts of a KG using coupling constraints and crowdsources the facts that infer correctness of large parts of the KG. We demonstrate that the objective optimized by KGEval is submodular and NP-hard, allowing guarantees for our approximation algorithm. Through extensive experiments on real-world datasets, we demonstrate that KGEval is able to estimate KG accuracy more accurately compared to other competitive baselines, while requiring significantly lesser number of human evaluations. |
| Tasks | Knowledge Graphs |
| Published | 2016-10-21 |
| URL | http://arxiv.org/abs/1610.06912v2 |
| http://arxiv.org/pdf/1610.06912v2.pdf | |
| PWC | https://paperswithcode.com/paper/kgeval-estimating-accuracy-of-automatically |
| Repo | |
| Framework | |
On Context-Dependent Clustering of Bandits
| Title | On Context-Dependent Clustering of Bandits |
| Authors | Claudio Gentile, Shuai Li, Purushottam Kar, Alexandros Karatzoglou, Evans Etrue, Giovanni Zappella |
| Abstract | We investigate a novel cluster-of-bandit algorithm CAB for collaborative recommendation tasks that implements the underlying feedback sharing mechanism by estimating the neighborhood of users in a context-dependent manner. CAB makes sharp departures from the state of the art by incorporating collaborative effects into inference as well as learning processes in a manner that seamlessly interleaving explore-exploit tradeoffs and collaborative steps. We prove regret bounds under various assumptions on the data, which exhibit a crisp dependence on the expected number of clusters over the users, a natural measure of the statistical difficulty of the learning task. Experiments on production and real-world datasets show that CAB offers significantly increased prediction performance against a representative pool of state-of-the-art methods. |
| Tasks | |
| Published | 2016-08-06 |
| URL | http://arxiv.org/abs/1608.03544v2 |
| http://arxiv.org/pdf/1608.03544v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-context-dependent-clustering-of-bandits |
| Repo | |
| Framework | |
Dopamine modulation of prefrontal delay activity-reverberatory activity and sharpness of tuning curves
| Title | Dopamine modulation of prefrontal delay activity-reverberatory activity and sharpness of tuning curves |
| Authors | Gabriele Scheler, Jean-Marc Fellous |
| Abstract | Recent electrophysiological experiments have shown that dopamine (D1) modulation of pyramidal cells in prefrontal cortex reduces spike frequency adaptation and enhances NMDA transmission. Using four models, from multicompartmental to integrate and fire, we examine the effects of these modulations on sustained (delay) activity in a reverberatory network. We find that D1 modulation may enable robust network bistability yielding selective reverberation among cells that code for a particular item or location. We further show that the tuning curve of such cells is sharpened, and that signal-to-noise ratio is increased. We postulate that D1 modulation affects the tuning of “memory fields” and yield efficient distributed dynamic representations. |
| Tasks | |
| Published | 2016-08-16 |
| URL | http://arxiv.org/abs/1608.04540v1 |
| http://arxiv.org/pdf/1608.04540v1.pdf | |
| PWC | https://paperswithcode.com/paper/dopamine-modulation-of-prefrontal-delay |
| Repo | |
| Framework | |
Decision trees unearth return sign correlation in the S&P 500
| Title | Decision trees unearth return sign correlation in the S&P 500 |
| Authors | Lucas Fievet, Didier Sornette |
| Abstract | Technical trading rules and linear regressive models are often used by practitioners to find trends in financial data. However, these models are unsuited to find non-linearly separable patterns. We propose a decision tree forecasting model that has the flexibility to capture arbitrary patterns. To illustrate, we construct a binary Markov process with a deterministic component that cannot be predicted with an autoregressive process. A simulation study confirms the robustness of the trees and limitation of the autoregressive model. Finally, adjusting for multiple testing, we show that some tree based strategies achieve trading performance significant at the 99% confidence level on the S&P 500 over the past 20 years. The best strategy breaks even with the buy-and-hold strategy at 21 bps in transaction costs per round trip. A four-factor regression analysis shows significant intercept and correlation with the market. The return anomalies are strongest during the bursts of the dotcom bubble, financial crisis, and European debt crisis. The correlation of the return signs during these periods confirms the theoretical model. |
| Tasks | |
| Published | 2016-10-12 |
| URL | http://arxiv.org/abs/1610.03724v2 |
| http://arxiv.org/pdf/1610.03724v2.pdf | |
| PWC | https://paperswithcode.com/paper/decision-trees-unearth-return-sign |
| Repo | |
| Framework | |
TorontoCity: Seeing the World with a Million Eyes
| Title | TorontoCity: Seeing the World with a Million Eyes |
| Authors | Shenlong Wang, Min Bai, Gellert Mattyus, Hang Chu, Wenjie Luo, Bin Yang, Justin Liang, Joel Cheverie, Sanja Fidler, Raquel Urtasun |
| Abstract | In this paper we introduce the TorontoCity benchmark, which covers the full greater Toronto area (GTA) with 712.5 $km^2$ of land, 8439 $km$ of road and around 400,000 buildings. Our benchmark provides different perspectives of the world captured from airplanes, drones and cars driving around the city. Manually labeling such a large scale dataset is infeasible. Instead, we propose to utilize different sources of high-precision maps to create our ground truth. Towards this goal, we develop algorithms that allow us to align all data sources with the maps while requiring minimal human supervision. We have designed a wide variety of tasks including building height estimation (reconstruction), road centerline and curb extraction, building instance segmentation, building contour extraction (reorganization), semantic labeling and scene type classification (recognition). Our pilot study shows that most of these tasks are still difficult for modern convolutional neural networks. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2016-12-01 |
| URL | http://arxiv.org/abs/1612.00423v1 |
| http://arxiv.org/pdf/1612.00423v1.pdf | |
| PWC | https://paperswithcode.com/paper/torontocity-seeing-the-world-with-a-million |
| Repo | |
| Framework | |
e-Distance Weighted Support Vector Regression
| Title | e-Distance Weighted Support Vector Regression |
| Authors | Yan Wang, Ge Ou, Wei Pang, Lan Huang, George Macleod Coghill |
| Abstract | We propose a novel support vector regression approach called e-Distance Weighted Support Vector Regression (e-DWSVR).e-DWSVR specifically addresses two challenging issues in support vector regression: first, the process of noisy data; second, how to deal with the situation when the distribution of boundary data is different from that of the overall data. The proposed e-DWSVR optimizes the minimum margin and the mean of functional margin simultaneously to tackle these two issues. In addition, we use both dual coordinate descent (CD) and averaged stochastic gradient descent (ASGD) strategies to make e-DWSVR scalable to large scale problems. We report promising results obtained by e-DWSVR in comparison with existing methods on several benchmark datasets. |
| Tasks | |
| Published | 2016-07-21 |
| URL | http://arxiv.org/abs/1607.06657v4 |
| http://arxiv.org/pdf/1607.06657v4.pdf | |
| PWC | https://paperswithcode.com/paper/e-distance-weighted-support-vector-regression |
| Repo | |
| Framework | |
Recursive Sampling for the Nyström Method
| Title | Recursive Sampling for the Nyström Method |
| Authors | Cameron Musco, Christopher Musco |
| Abstract | We give the first algorithm for kernel Nystr"om approximation that runs in linear time in the number of training points and is provably accurate for all kernel matrices, without dependence on regularity or incoherence conditions. The algorithm projects the kernel onto a set of $s$ landmark points sampled by their ridge leverage scores, requiring just $O(ns)$ kernel evaluations and $O(ns^2)$ additional runtime. While leverage score sampling has long been known to give strong theoretical guarantees for Nystr"om approximation, by employing a fast recursive sampling scheme, our algorithm is the first to make the approach scalable. Empirically we show that it finds more accurate, lower rank kernel approximations in less time than popular techniques such as uniformly sampled Nystr"om approximation and the random Fourier features method. |
| Tasks | |
| Published | 2016-05-24 |
| URL | http://arxiv.org/abs/1605.07583v5 |
| http://arxiv.org/pdf/1605.07583v5.pdf | |
| PWC | https://paperswithcode.com/paper/recursive-sampling-for-the-nystrom-method |
| Repo | |
| Framework | |
Domain Control for Neural Machine Translation
| Title | Domain Control for Neural Machine Translation |
| Authors | Catherine Kobus, Josep Crego, Jean Senellart |
| Abstract | Machine translation systems are very sensitive to the domains they were trained on. Several domain adaptation techniques have been deeply studied. We propose a new technique for neural machine translation (NMT) that we call domain control which is performed at runtime using a unique neural network covering multiple domains. The presented approach shows quality improvements when compared to dedicated domains translating on any of the covered domains and even on out-of-domain data. In addition, model parameters do not need to be re-estimated for each domain, making this effective to real use cases. Evaluation is carried out on English-to-French translation for two different testing scenarios. We first consider the case where an end-user performs translations on a known domain. Secondly, we consider the scenario where the domain is not known and predicted at the sentence level before translating. Results show consistent accuracy improvements for both conditions. |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2016-12-19 |
| URL | http://arxiv.org/abs/1612.06140v2 |
| http://arxiv.org/pdf/1612.06140v2.pdf | |
| PWC | https://paperswithcode.com/paper/domain-control-for-neural-machine-translation |
| Repo | |
| Framework | |
Symbolic Representation and Classification of Logos
| Title | Symbolic Representation and Classification of Logos |
| Authors | D. S. Guru, N. Vinay Kumar |
| Abstract | In this paper, a model for classification of logos based on symbolic representation of features is presented. The proposed model makes use of global features of logo images such as color, texture, and shape features for classification. The logo images are broadly classified into three different classes, viz., logo image containing only text, an image with only symbol, and an image with both text and a symbol. In each class, the similar looking logo images are clustered using K-means clustering algorithm. The intra-cluster variations present in each cluster corresponding to each class are then preserved using symbolic interval data. Thus referenced logo images are represented in the form of interval data. A sample logo image is then classified using suitable symbolic classifier. For experimentation purpose, relatively large amount of color logo images is created consisting of 5044 logo images. The classification results are validated with the help of accuracy, precision, recall, F-measure, and time. To check the efficacy of the proposed model, the comparative analyses are given against the other models. The results show that the proposed model outperforms the other models with respect to time and F-measure. |
| Tasks | |
| Published | 2016-12-28 |
| URL | http://arxiv.org/abs/1612.08796v1 |
| http://arxiv.org/pdf/1612.08796v1.pdf | |
| PWC | https://paperswithcode.com/paper/symbolic-representation-and-classification-of |
| Repo | |
| Framework | |
Psychologically inspired planning method for smart relocation task
| Title | Psychologically inspired planning method for smart relocation task |
| Authors | Aleksandr I. Panov, Konstantin Yakovlev |
| Abstract | Behavior planning is known to be one of the basic cognitive functions, which is essential for any cognitive architecture of any control system used in robotics. At the same time most of the widespread planning algorithms employed in those systems are developed using only approaches and models of Artificial Intelligence and don’t take into account numerous results of cognitive experiments. As a result, there is a strong need for novel methods of behavior planning suitable for modern cognitive architectures aimed at robot control. One such method is presented in this work and is studied within a special class of navigation task called smart relocation task. The method is based on the hierarchical two-level model of abstraction and knowledge representation, e.g. symbolic and subsymbolic. On the symbolic level sign world model is used for knowledge representation and hierarchical planning algorithm, PMA, is utilized for planning. On the subsymbolic level the task of path planning is considered and solved as a graph search problem. Interaction between both planners is examined and inter-level interfaces and feedback loops are described. Preliminary experimental results are presented. |
| Tasks | |
| Published | 2016-07-27 |
| URL | http://arxiv.org/abs/1607.08181v1 |
| http://arxiv.org/pdf/1607.08181v1.pdf | |
| PWC | https://paperswithcode.com/paper/psychologically-inspired-planning-method-for |
| Repo | |
| Framework | |
Influential Node Detection in Implicit Social Networks using Multi-task Gaussian Copula Models
| Title | Influential Node Detection in Implicit Social Networks using Multi-task Gaussian Copula Models |
| Authors | Qunwei Li, Bhavya Kailkhura, Jayaraman J. Thiagarajan, Zhenliang Zhang, Pramod K. Varshney |
| Abstract | Influential node detection is a central research topic in social network analysis. Many existing methods rely on the assumption that the network structure is completely known \textit{a priori}. However, in many applications, network structure is unavailable to explain the underlying information diffusion phenomenon. To address the challenge of information diffusion analysis with incomplete knowledge of network structure, we develop a multi-task low rank linear influence model. By exploiting the relationships between contagions, our approach can simultaneously predict the volume (i.e. time series prediction) for each contagion (or topic) and automatically identify the most influential nodes for each contagion. The proposed model is validated using synthetic data and an ISIS twitter dataset. In addition to improving the volume prediction performance significantly, we show that the proposed approach can reliably infer the most influential users for specific contagions. |
| Tasks | Time Series, Time Series Prediction |
| Published | 2016-11-30 |
| URL | http://arxiv.org/abs/1611.10305v1 |
| http://arxiv.org/pdf/1611.10305v1.pdf | |
| PWC | https://paperswithcode.com/paper/influential-node-detection-in-implicit-social |
| Repo | |
| Framework | |
Fast and Provably Accurate Bilateral Filtering
| Title | Fast and Provably Accurate Bilateral Filtering |
| Authors | Kunal N. Chaudhury, Swapnil D. Dabhade |
| Abstract | The bilateral filter is a non-linear filter that uses a range filter along with a spatial filter to perform edge-preserving smoothing of images. A direct computation of the bilateral filter requires $O(S)$ operations per pixel, where $S$ is the size of the support of the spatial filter. In this paper, we present a fast and provably accurate algorithm for approximating the bilateral filter when the range kernel is Gaussian. In particular, for box and Gaussian spatial filters, the proposed algorithm can cut down the complexity to $O(1)$ per pixel for any arbitrary $S$. The algorithm has a simple implementation involving $N+1$ spatial filterings, where $N$ is the approximation order. We give a detailed analysis of the filtering accuracy that can be achieved by the proposed approximation in relation to the target bilateral filter. This allows us to to estimate the order $N$ required to obtain a given accuracy. We also present comprehensive numerical results to demonstrate that the proposed algorithm is competitive with state-of-the-art methods in terms of speed and accuracy. |
| Tasks | |
| Published | 2016-03-26 |
| URL | http://arxiv.org/abs/1603.08109v1 |
| http://arxiv.org/pdf/1603.08109v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-provably-accurate-bilateral |
| Repo | |
| Framework | |
