PyTorchKR Papers

최신 논문

총 3,383편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1606.03335

WordNet2Vec: Corpora Agnostic Word Vectorization Method

A complex nature of big data resources demands new methods for structuring especially for textual content. WordNet is a good knowledge source for comprehensive abstraction of natural language as its good implementations exist for many languages. Since WordNet embeds natural language in the form of a complex network, a transformation mechanism WordNet2Vec is proposed in the paper. It creates vectors for each word from WordNet. These vectors encapsulate general position - role of a given word towards all other words in the natural language. Any list or set of such vectors contains knowledge about the context of its component within the whole language. Such word representation can be easily applied to many analytic tasks like classification or clustering. The usefulness of the WordNet2Vec method was demonstrated in sentiment analysis, i.e. classification with transfer learning for the real Amazon opinion textual dataset.

arXiv:1606.01623

Position-Indexed Formulations for Kidney Exchange

A kidney exchange is an organized barter market where patients in need of a kidney swap willing but incompatible donors. Determining an optimal set of exchanges is theoretically and empirically hard. Traditionally, exchanges took place in cycles, with each participating patient-donor pair both giving and receiving a kidney. The recent introduction of chains, where a donor without a paired patient triggers a sequence of donations without requiring a kidney in return, increased the efficacy of fielded kidney exchanges---while also dramatically raising the empirical computational hardness of clearing the market in practice. While chains can be quite long, unbounded-length chains are not desirable: planned donations can fail before transplant for a variety of reasons, and the failure of a single donation causes the rest of that chain to fail, so parallel shorter chains are better in practice. In this paper, we address the tractable clearing of kidney exchanges with short cycles and chains that are long but bounded. This corresponds to the practice at most modern fielded kidney exchanges. We introduce three new integer programming formulations, two of which are compact. Furthermore, one of these models has a linear programming relaxation that is exactly as tight as the previous tightest formulation (which was not compact) for instances in which each donor has a paired patient. On real data from the UNOS nationwide exchange in the United States and the NLDKSS nationwide exchange in the United Kingdom, as well as on generated realistic large-scale data, we show that our new models are competitive with all existing solvers---in many cases outperforming all other solvers by orders of magnitude.

arXiv:1606.05110

Machine Learning meets Data-Driven Journalism: Boosting International Understanding and Transparency in News Coverage

Migration crisis, climate change or tax havens: Global challenges need global solutions. But agreeing on a joint approach is difficult without a common ground for discussion. Public spheres are highly segmented because news are mainly produced and received on a national level. Gain- ing a global view on international debates about important issues is hindered by the enormous quantity of news and by language barriers. Media analysis usually focuses only on qualitative re- search. In this position statement, we argue that it is imperative to pool methods from machine learning, journalism studies and statistics to help bridging the segmented data of the international public sphere, using the Transatlantic Trade and Investment Partnership (TTIP) as a case study.

arXiv:1605.05860

False Discovery Rate Control and Statistical Quality Assessment of Annotators in Crowdsourced Ranking

With the rapid growth of crowdsourcing platforms it has become easy and relatively inexpensive to collect a dataset labeled by multiple annotators in a short time. However due to the lack of control over the quality of the annotators, some abnormal annotators may be affected by position bias which can potentially degrade the quality of the final consensus labels. In this paper we introduce a statistical framework to model and detect annotator's position bias in order to control the false discovery rate (FDR) without a prior knowledge on the amount of biased annotators - the expected fraction of false discoveries among all discoveries being not too high, in order to assure that most of the discoveries are indeed true and replicable. The key technical development relies on some new knockoff filters adapted to our problem and new algorithms based on the Inverse Scale Space dynamics whose discretization is potentially suitable for large scale crowdsourcing data analysis. Our studies are supported by experiments with both simulated examples and real-world data. The proposed framework provides us a useful tool for quantitatively studying annotator's abnormal behavior in crowdsourcing data arising from machine learning, sociology, computer vision, multimedia, etc.

arXiv:1606.06274

A Data-Driven Approach for Semantic Role Labeling from Induced Grammar Structures in Language

Semantic roles play an important role in extracting knowledge from text. Current unsupervised approaches utilize features from grammar structures, to induce semantic roles. The dependence on these grammars, however, makes it difficult to adapt to noisy and new languages. In this paper we develop a data-driven approach to identifying semantic roles, the approach is entirely unsupervised up to the point where rules need to be learned to identify the position the semantic role occurs. Specifically we develop a modified-ADIOS algorithm based on ADIOS Solan et al. (2005) to learn grammar structures, and use these grammar structures to learn the rules for identifying the semantic roles based on the context in which the grammar structures appeared. The results obtained are comparable with the current state-of-art models that are inherently dependent on human annotated data.

arXiv:1606.05994

The Role of CNL and AMR in Scalable Abstractive Summarization for Multilingual Media Monitoring

In the era of Big Data and Deep Learning, there is a common view that machine learning approaches are the only way to cope with the robust and scalable information extraction and summarization. It has been recently proposed that the CNL approach could be scaled up, building on the concept of embedded CNL and, thus, allowing for CNL-based information extraction from e.g. normative or medical texts that are rather controlled by nature but still infringe the boundaries of CNL. Although it is arguable if CNL can be exploited to approach the robust wide-coverage semantic parsing for use cases like media monitoring, its potential becomes much more obvious in the opposite direction: generation of story highlights from the summarized AMR graphs, which is in the focus of this position paper.

arXiv:1606.05593

Introspective Agents: Confidence Measures for General Value Functions

Agents of general intelligence deployed in real-world scenarios must adapt to ever-changing environmental conditions. While such adaptive agents may leverage engineered knowledge, they will require the capacity to construct and evaluate knowledge themselves from their own experience in a bottom-up, constructivist fashion. This position paper builds on the idea of encoding knowledge as temporally extended predictions through the use of general value functions. Prior work has focused on learning predictions about externally derived signals about a task or environment (e.g. battery level, joint position). Here we advocate that the agent should also predict internally generated signals regarding its own learning process - for example, an agent's confidence in its learned predictions. Finally, we suggest how such information would be beneficial in creating an introspective agent that is able to learn to make good decisions in a complex, changing world.

arXiv:1607.00186

Throwing fuel on the embers: Probability or Dichotomy, Cognitive or Linguistic?

Prof. Robert Berwick's abstract for his forthcoming invited talk at the ACL2016 workshop on Cognitive Aspects of Computational Language Learning revives an ancient debate. Entitled "Why take a chance?", Berwick seems to refer implicitly to Chomsky's critique of the statistical approach of Harris as well as the currently dominant paradigms in CoNLL. Berwick avoids Chomsky's use of "innate" but states that "the debate over the existence of sophisticated mental grammars was settled with Chomsky's Logical Structure of Linguistic Theory (1957/1975)", acknowledging that "this debate has often been revived". This paper agrees with the view that this debate has long since been settled, but with the opposite outcome! Given the embers have not yet died away, and the questions remain fundamental, perhaps it is appropriate to refuel the debate, so I would like to join Bob in throwing fuel on this fire by reviewing the evidence against the Chomskian position!

arXiv:1607.02235

From Collective Adaptive Systems to Human Centric Computation and Back: Spatial Model Checking for Medical Imaging

Recent research on formal verification for Collective Adaptive Systems (CAS) pushed advancements in spatial and spatio-temporal model checking, and as a side result provided novel image analysis methodologies, rooted in logical methods for topological spaces. Medical Imaging (MI) is a field where such technologies show potential for ground-breaking innovation. In this position paper, we present a preliminary investigation centred on applications of spatial model checking to MI. The focus is shifted from pure logics to a mixture of logical, statistical and algorithmic approaches, driven by the logical nature intrinsic to the specification of the properties of interest in the field. As a result, novel operators are introduced, that could as well be brought back to the setting of CAS.

arXiv:1607.04566

Spectral Echolocation via the Wave Embedding

Spectral embedding uses eigenfunctions of the discrete Laplacian on a weighted graph to obtain coordinates for an embedding of an abstract data set into Euclidean space. We propose a new pre-processing step of first using the eigenfunctions to simulate a low-frequency wave moving over the data and using both position as well as change in time of the wave to obtain a refined metric to which classical methods of dimensionality reduction can then applied. This is motivated by the behavior of waves, symmetries of the wave equation and the hunting technique of bats. It is shown to be effective in practice and also works for other partial differential equations -- the method yields improved results even for the classical heat equation.

arXiv:1607.07983

A Continuous Optimization Approach for Efficient and Accurate Scene Flow

We propose a continuous optimization method for solving dense 3D scene flow problems from stereo imagery. As in recent work, we represent the dynamic 3D scene as a collection of rigidly moving planar segments. The scene flow problem then becomes the joint estimation of pixel-to-segment assignment, 3D position, normal vector and rigid motion parameters for each segment, leading to a complex and expensive discrete-continuous optimization problem. In contrast, we propose a purely continuous formulation which can be solved more efficiently. Using a fine superpixel segmentation that is fixed a-priori, we propose a factor graph formulation that decomposes the problem into photometric, geometric, and smoothing constraints. We initialize the solution with a novel, high-quality initialization method, then independently refine the geometry and motion of the scene, and finally perform a global non-linear refinement using Levenberg-Marquardt. We evaluate our method in the challenging KITTI Scene Flow benchmark, ranking in third position, while being 3 to 30 times faster than the top competitors.

arXiv:1607.07939

A Sensorimotor Reinforcement Learning Framework for Physical Human-Robot Interaction

Modeling of physical human-robot collaborations is generally a challenging problem due to the unpredictive nature of human behavior. To address this issue, we present a data-efficient reinforcement learning framework which enables a robot to learn how to collaborate with a human partner. The robot learns the task from its own sensorimotor experiences in an unsupervised manner. The uncertainty of the human actions is modeled using Gaussian processes (GP) to implement action-value functions. Optimal action selection given the uncertain GP model is ensured by Bayesian optimization. We apply the framework to a scenario in which a human and a PR2 robot jointly control the ball position on a plank based on vision and force/torque data. Our experimental results show the suitability of the proposed method in terms of fast and data-efficient model learning, optimal action selection under uncertainties and equal role sharing between the partners.

arXiv:1608.01372

Permutation NMF

Nonnegative Matrix Factorization(NMF) is a common used technique in machine learning to extract features out of data such as text documents and images thanks to its natural clustering properties. In particular, it is popular in image processing since it can decompose several pictures and recognize common parts if they're located in the same position over the photos. This paper's aim is to present a way to add the translation invariance to the classical NMF, that is, the algorithms presented are able to detect common features, even when they're shifted, in different original images.

arXiv:1604.07866

Learning by tracking: Siamese CNN for robust target association

This paper introduces a novel approach to the task of data association within the context of pedestrian tracking, by introducing a two-stage learning scheme to match pairs of detections. First, a Siamese convolutional neural network (CNN) is trained to learn descriptors encoding local spatio-temporal structures between the two input image patches, aggregating pixel values and optical flow information. Second, a set of contextual features derived from the position and size of the compared input patches are combined with the CNN output by means of a gradient boosting classifier to generate the final matching probability. This learning approach is validated by using a linear programming based multi-person tracker showing that even a simple and efficient tracker may outperform much more complex models when fed with our learned matching probabilities. Results on publicly available sequences show that our method meets state-of-the-art standards in multiple people tracking.

arXiv:1608.02824

Camera Pose Estimation from Lines using Plücker Coordinates

Correspondences between 3D lines and their 2D images captured by a camera are often used to determine position and orientation of the camera in space. In this work, we propose a novel algebraic algorithm to estimate the camera pose. We parameterize 3D lines using Pl\"ucker coordinates that allow linear projection of the lines into the image. A line projection matrix is estimated using Linear Least Squares and the camera pose is then extracted from the matrix. An algebraic approach to handle mismatched line correspondences is also included. The proposed algorithm is an order of magnitude faster yet comparably accurate and robust to the state-of-the-art, it does not require initialization, and it yields only one solution. The described method requires at least 9 lines and is particularly suitable for scenarios with 25 and more lines, as also shown in the results.

arXiv:1505.05668

Locally Adaptive Dynamic Networks

Our focus is on realistically modeling and forecasting dynamic networks of face-to-face contacts among individuals. Important aspects of such data that lead to problems with current methods include the tendency of the contacts to move between periods of slow and rapid changes, and the dynamic heterogeneity in the actors' connectivity behaviors. Motivated by this application, we develop a novel method for Locally Adaptive DYnamic (LADY) network inference. The proposed model relies on a dynamic latent space representation in which each actor's position evolves in time via stochastic differential equations. Using a state space representation for these stochastic processes and P\'olya-gamma data augmentation, we develop an efficient MCMC algorithm for posterior inference along with tractable procedures for online updating and forecasting of future networks. We evaluate performance in simulation studies, and consider an application to face-to-face contacts among individuals in a primary school.

arXiv:1608.07949

Learning-Based Resource Allocation Scheme for TDD-Based CRAN System

Explosive growth in the use of smart wireless devices has necessitated the provision of higher data rates and always-on connectivity, which are the main motivators for designing the fifth generation (5G) systems. To achieve higher system efficiency, massive antenna deployment with tight coordination is one potential strategy for designing 5G systems, but has two types of associated system overhead. First is the synchronization overhead, which can be reduced by implementing a cloud radio access network (CRAN)-based architecture design, that separates the baseband processing and radio access functionality to achieve better system synchronization. Second is the overhead for acquiring channel state information (CSI) of the users present in the system, which, however, increases tremendously when instantaneous CSI is used to serve high-mobility users. To serve a large number of users, a CRAN system with a dense deployment of remote radio heads (RRHs) is considered, such that each user has a line-of-sight (LOS) link with the corresponding RRH. Since, the trajectory of movement for high-mobility users is predictable; therefore, fairly accurate position estimates for those users can be obtained, and can be used for resource allocation to serve the considered users. The resource allocation is dependent upon various correlated system parameters, and these correlations can be learned using well-known \emph{machine learning} algorithms. This paper proposes a novel \emph{learning-based resource allocation scheme} for time division duplex (TDD) based 5G CRAN systems with dense RRH deployment, by using only the users' position estimates for resource allocation, thus avoiding the need for CSI acquisition. This reduces the overall system overhead significantly, while still achieving near-optimal system performance; thus, better (effective) system efficiency is achieved. (See the paper for full abstract)

arXiv:1609.00514

On Horizontal and Vertical Separation in Hierarchical Text Classification

Hierarchy is a common and effective way of organizing data and representing their relationships at different levels of abstraction. However, hierarchical data dependencies cause difficulties in the estimation of "separable" models that can distinguish between the entities in the hierarchy. Extracting separable models of hierarchical entities requires us to take their relative position into account and to consider the different types of dependencies in the hierarchy. In this paper, we present an investigation of the effect of separability in text-based entity classification and argue that in hierarchical classification, a separation property should be established between entities not only in the same layer, but also in different layers. Our main findings are the followings. First, we analyse the importance of separability on the data representation in the task of classification and based on that, we introduce a "Strong Separation Principle" for optimizing expected effectiveness of classifiers decision based on separation property. Second, we present Hierarchical Significant Words Language Models (HSWLM) which capture all, and only, the essential features of hierarchical entities according to their relative position in the hierarchy resulting in horizontally and vertically separable models. Third, we validate our claims on real-world data and demonstrate that how HSWLM improves the accuracy of classification and how it provides transferable models over time. Although discussions in this paper focus on the classification problem, the models are applicable to any information access tasks on data that has, or can be mapped to, a hierarchical structure.

arXiv:1609.00096

Image segmentation based on histogram of depth and an application in driver distraction detection

This study proposes an approach to segment human object from a depth image based on histogram of depth values. The region of interest is first extracted based on a predefined threshold for histogram regions. A region growing process is then employed to separate multiple human bodies with the same depth interval. Our contribution is the identification of an adaptive growth threshold based on the detected histogram region. To demonstrate the effectiveness of the proposed method, an application in driver distraction detection was introduced. After successfully extracting the driver's position inside the car, we came up with a simple solution to track the driver motion. With the analysis of the difference between initial and current frame, a change of cluster position or depth value in the interested region, which cross the preset threshold, is considered as a distracted activity. The experiment results demonstrated the success of the algorithm in detecting typical distracted driving activities such as using phone for calling or texting, adjusting internal devices and drinking in real time.

arXiv:1609.01958

Object Tracking via Dynamic Feature Selection Processes

DFST proposes an optimized visual tracking algorithm based on the real-time selection of locally and temporally discriminative features. A feature selection mechanism is embedded in the Adaptive colour Names (CN) tracking system that adaptively selects the top-ranked discriminative features for tracking. DFST provides a significant gain in accuracy and precision allowing the use of a dynamic set of features that results in an increased system flexibility. DFST is based on the unsupervised method "Infinite Feature Selection" (Inf-FS), which ranks features according with their "redundancy" without using class labels. By using a fast online algorithm for learning dictionaries the size of the box is adapted during the processing. At each update, we use multiple examples around the target (at different positions and scales). DFST also improved the CN by adding micro-shift at the predicted position and bounding box adaptation.