Paper Group ANR 188
An Encoder-Decoder Framework Translating Natural Language to Database Queries. Personalized word representations Carrying Personalized Semantics Learned from Social Network Posts. Living a discrete life in a continuous world: Reference with distributed representations. SFCN-OPI: Detection and Fine-grained Classification of Nuclei Using Sibling FCN …
An Encoder-Decoder Framework Translating Natural Language to Database Queries
| Title | An Encoder-Decoder Framework Translating Natural Language to Database Queries |
| Authors | Ruichu Cai, Boyan Xu, Xiaoyan Yang, Zhenjie Zhang, Zijian Li, Zhihao Liang |
| Abstract | Machine translation is going through a radical revolution, driven by the explosive development of deep learning techniques using Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). In this paper, we consider a special case in machine translation problems, targeting to convert natural language into Structured Query Language (SQL) for data retrieval over relational database. Although generic CNN and RNN learn the grammar structure of SQL when trained with sufficient samples, the accuracy and training efficiency of the model could be dramatically improved, when the translation model is deeply integrated with the grammar rules of SQL. We present a new encoder-decoder framework, with a suite of new approaches, including new semantic features fed into the encoder, grammar-aware states injected into the memory of decoder, as well as recursive state management for sub-queries. These techniques help the neural network better focus on understanding semantics of operations in natural language and save the efforts on SQL grammar learning. The empirical evaluation on real world database and queries show that our approach outperform state-of-the-art solution by a significant margin. |
| Tasks | Machine Translation |
| Published | 2017-11-16 |
| URL | http://arxiv.org/abs/1711.06061v2 |
| http://arxiv.org/pdf/1711.06061v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-encoder-decoder-framework-translating |
| Repo | |
| Framework | |
Personalized word representations Carrying Personalized Semantics Learned from Social Network Posts
| Title | Personalized word representations Carrying Personalized Semantics Learned from Social Network Posts |
| Authors | Zih-Wei Lin, Tzu-Wei Sung, Hung-Yi Lee, Lin-Shan Lee |
| Abstract | Distributed word representations have been shown to be very useful in various natural language processing (NLP) application tasks. These word vectors learned from huge corpora very often carry both semantic and syntactic information of words. However, it is well known that each individual user has his own language patterns because of different factors such as interested topics, friend groups, social activities, wording habits, etc., which may imply some kind of personalized semantics. With such personalized semantics, the same word may imply slightly differently for different users. For example, the word “Cappuccino” may imply “Leisure”, “Joy”, “Excellent” for a user enjoying coffee, by only a kind of drink for someone else. Such personalized semantics of course cannot be carried by the standard universal word vectors trained with huge corpora produced by many people. In this paper, we propose a framework to train different personalized word vectors for different users based on the very successful continuous skip-gram model using the social network data posted by many individual users. In this framework, universal background word vectors are first learned from the background corpora, and then adapted by the personalized corpus for each individual user to learn the personalized word vectors. We use two application tasks to evaluate the quality of the personalized word vectors obtained in this way, the user prediction task and the sentence completion task. These personalized word vectors were shown to carry some personalized semantics and offer improved performance on these two evaluation tasks. |
| Tasks | |
| Published | 2017-10-29 |
| URL | http://arxiv.org/abs/1710.10574v1 |
| http://arxiv.org/pdf/1710.10574v1.pdf | |
| PWC | https://paperswithcode.com/paper/personalized-word-representations-carrying |
| Repo | |
| Framework | |
Living a discrete life in a continuous world: Reference with distributed representations
| Title | Living a discrete life in a continuous world: Reference with distributed representations |
| Authors | Gemma Boleda, Sebastian Padó, Nghia The Pham, Marco Baroni |
| Abstract | Reference is a crucial property of language that allows us to connect linguistic expressions to the world. Modeling it requires handling both continuous and discrete aspects of meaning. Data-driven models excel at the former, but struggle with the latter, and the reverse is true for symbolic models. This paper (a) introduces a concrete referential task to test both aspects, called cross-modal entity tracking; (b) proposes a neural network architecture that uses external memory to build an entity library inspired in the DRSs of DRT, with a mechanism to dynamically introduce new referents or add information to referents that are already in the library. Our model shows promise: it beats traditional neural network architectures on the task. However, it is still outperformed by Memory Networks, another model with external memory. |
| Tasks | |
| Published | 2017-02-06 |
| URL | http://arxiv.org/abs/1702.01815v2 |
| http://arxiv.org/pdf/1702.01815v2.pdf | |
| PWC | https://paperswithcode.com/paper/living-a-discrete-life-in-a-continuous-world-1 |
| Repo | |
| Framework | |
SFCN-OPI: Detection and Fine-grained Classification of Nuclei Using Sibling FCN with Objectness Prior Interaction
| Title | SFCN-OPI: Detection and Fine-grained Classification of Nuclei Using Sibling FCN with Objectness Prior Interaction |
| Authors | Yanning Zhou, Qi Dou, Hao Chen, Jing Qin, Pheng-Ann Heng |
| Abstract | Cell nuclei detection and fine-grained classification have been fundamental yet challenging problems in histopathology image analysis. Due to the nuclei tiny size, significant inter-/intra-class variances, as well as the inferior image quality, previous automated methods would easily suffer from limited accuracy and robustness. In the meanwhile, existing approaches usually deal with these two tasks independently, which would neglect the close relatedness of them. In this paper, we present a novel method of sibling fully convolutional network with prior objectness interaction (called SFCN-OPI) to tackle the two tasks simultaneously and interactively using a unified end-to-end framework. Specifically, the sibling FCN branches share features in earlier layers while holding respective higher layers for specific tasks. More importantly, the detection branch outputs the objectness prior which dynamically interacts with the fine-grained classification sibling branch during the training and testing processes. With this mechanism, the fine-grained classification successfully focuses on regions with high confidence of nuclei existence and outputs the conditional probability, which in turn benefits the detection through back propagation. Extensive experiments on colon cancer histology images have validated the effectiveness of our proposed SFCN-OPI and our method has outperformed the state-of-the-art methods by a large margin. |
| Tasks | |
| Published | 2017-12-22 |
| URL | http://arxiv.org/abs/1712.08297v1 |
| http://arxiv.org/pdf/1712.08297v1.pdf | |
| PWC | https://paperswithcode.com/paper/sfcn-opi-detection-and-fine-grained |
| Repo | |
| Framework | |
Simultaneous Block-Sparse Signal Recovery Using Pattern-Coupled Sparse Bayesian Learning
| Title | Simultaneous Block-Sparse Signal Recovery Using Pattern-Coupled Sparse Bayesian Learning |
| Authors | Hang Xiao, Zhengli Xing, Linxiao Yang, Jun Fang, Yanlun Wu |
| Abstract | In this paper, we consider the block-sparse signals recovery problem in the context of multiple measurement vectors (MMV) with common row sparsity patterns. We develop a new method for recovery of common row sparsity MMV signals, where a pattern-coupled hierarchical Gaussian prior model is introduced to characterize both the block-sparsity of the coefficients and the statistical dependency between neighboring coefficients of the common row sparsity MMV signals. Unlike many other methods, the proposed method is able to automatically capture the block sparse structure of the unknown signal. Our method is developed using an expectation-maximization (EM) framework. Simulation results show that our proposed method offers competitive performance in recovering block-sparse common row sparsity pattern MMV signals. |
| Tasks | |
| Published | 2017-11-06 |
| URL | http://arxiv.org/abs/1711.01790v1 |
| http://arxiv.org/pdf/1711.01790v1.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-block-sparse-signal-recovery |
| Repo | |
| Framework | |
A Converse to Banach’s Fixed Point Theorem and its CLS Completeness
| Title | A Converse to Banach’s Fixed Point Theorem and its CLS Completeness |
| Authors | Constantinos Daskalakis, Christos Tzamos, Manolis Zampetakis |
| Abstract | Banach’s fixed point theorem for contraction maps has been widely used to analyze the convergence of iterative methods in non-convex problems. It is a common experience, however, that iterative maps fail to be globally contracting under the natural metric in their domain, making the applicability of Banach’s theorem limited. We explore how generally we can apply Banach’s fixed point theorem to establish the convergence of iterative methods when pairing it with carefully designed metrics. Our first result is a strong converse of Banach’s theorem, showing that it is a universal analysis tool for establishing global convergence of iterative methods to unique fixed points, and for bounding their convergence rate. In other words, we show that, whenever an iterative map globally converges to a unique fixed point, there exists a metric under which the iterative map is contracting and which can be used to bound the number of iterations until convergence. We illustrate our approach in the widely used power method, providing a new way of bounding its convergence rate through contraction arguments. We next consider the computational complexity of Banach’s fixed point theorem. Making the proof of our converse theorem constructive, we show that computing a fixed point whose existence is guaranteed by Banach’s fixed point theorem is CLS-complete. We thus provide the first natural complete problem for the class CLS, which was defined in [Daskalakis, Papadimitriou 2011] to capture the complexity of problems such as P-matrix LCP, computing KKT-points, and finding mixed Nash equilibria in congestion and network coordination games. |
| Tasks | |
| Published | 2017-02-23 |
| URL | http://arxiv.org/abs/1702.07339v3 |
| http://arxiv.org/pdf/1702.07339v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-converse-to-banachs-fixed-point-theorem-and |
| Repo | |
| Framework | |
A deep learning classification scheme based on augmented-enhanced features to segment organs at risk on the optic region in brain cancer patients
| Title | A deep learning classification scheme based on augmented-enhanced features to segment organs at risk on the optic region in brain cancer patients |
| Authors | Jose Dolz, Nicolas Reyns, Nacim Betrouni, Dris Kharroubi, Mathilde Quidet, Laurent Massoptier, Maximilien Vermandel |
| Abstract | Radiation therapy has emerged as one of the preferred techniques to treat brain cancer patients. During treatment, a very high dose of radiation is delivered to a very narrow area. Prescribed radiation therapy for brain cancer requires precisely defining the target treatment area, as well as delineating vital brain structures which must be spared from radiotoxicity. Nevertheless, delineation task is usually still manually performed, which is inefficient and operator-dependent. Several attempts of automatizing this process have reported. however, marginal results when analyzing organs in the optic region. In this work we present a deep learning classification scheme based on augmented-enhanced features to automatically segment organs at risk (OARs) in the optic region -optic nerves, optic chiasm, pituitary gland and pituitary stalk-. Fifteen MR images with various types of brain tumors were retrospectively collected to undergo manual and automatic segmentation. Mean Dice Similarity coefficients around 0.80 were reported. Incorporation of proposed features yielded to improvements on the segmentation. Compared with support vector machines, our method achieved better performance with less variation on the results, as well as a considerably reduction on the classification time. Performance of the proposed approach was also evaluated with respect to manual contours. In this case, results obtained from the automatic contours mostly lie on the variability of the observers, showing no significant differences with respect to them. These results suggest therefore that the proposed system is more accurate than other presented approaches, up to date, to segment these structures. The speed, reproducibility, and robustness of the process make the proposed deep learning-based classification system a valuable tool for assisting in the delineation task of small OARs in brain cancer. |
| Tasks | |
| Published | 2017-03-30 |
| URL | http://arxiv.org/abs/1703.10480v2 |
| http://arxiv.org/pdf/1703.10480v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-classification-scheme-based |
| Repo | |
| Framework | |
Commonsense Scene Semantics for Cognitive Robotics: Towards Grounding Embodied Visuo-Locomotive Interactions
| Title | Commonsense Scene Semantics for Cognitive Robotics: Towards Grounding Embodied Visuo-Locomotive Interactions |
| Authors | Jakob Suchan, Mehul Bhatt |
| Abstract | We present a commonsense, qualitative model for the semantic grounding of embodied visuo-spatial and locomotive interactions. The key contribution is an integrative methodology combining low-level visual processing with high-level, human-centred representations of space and motion rooted in artificial intelligence. We demonstrate practical applicability with examples involving object interactions, and indoor movement. |
| Tasks | |
| Published | 2017-09-15 |
| URL | http://arxiv.org/abs/1709.05293v1 |
| http://arxiv.org/pdf/1709.05293v1.pdf | |
| PWC | https://paperswithcode.com/paper/commonsense-scene-semantics-for-cognitive |
| Repo | |
| Framework | |
Structured Parallel Programming for Monte Carlo Tree Search
| Title | Structured Parallel Programming for Monte Carlo Tree Search |
| Authors | S. Ali Mirsoleimani, Aske Plaat, Jaap van den Herik, Jos Vermaseren |
| Abstract | In this paper, we present a new algorithm for parallel Monte Carlo tree search (MCTS). It is based on the pipeline pattern and allows flexible management of the control flow of the operations in parallel MCTS. The pipeline pattern provides for the first structured parallel programming approach to MCTS. Moreover, we propose a new lock-free tree data structure for parallel MCTS which removes synchronization overhead. The Pipeline Pattern for Parallel MCTS algorithm (called 3PMCTS), scales very well to higher numbers of cores when compared to the existing methods. |
| Tasks | |
| Published | 2017-04-02 |
| URL | http://arxiv.org/abs/1704.00325v1 |
| http://arxiv.org/pdf/1704.00325v1.pdf | |
| PWC | https://paperswithcode.com/paper/structured-parallel-programming-for-monte |
| Repo | |
| Framework | |
The mind as a computational system
| Title | The mind as a computational system |
| Authors | Christoph Adami |
| Abstract | The present document is an excerpt of an essay that I wrote as part of my application material to graduate school in Computer Science (with a focus on Artificial Intelligence), in 1986. I was not invited by any of the schools that received it, so I became a theoretical physicist instead. The essay’s full title was “Some Topics in Philosophy and Computer Science”. I am making this text (unchanged from 1985, preserving the typesetting as much as possible) available now in memory of Jerry Fodor, whose writings had influenced me significantly at the time (even though I did not always agree). |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://arxiv.org/abs/1712.01093v1 |
| http://arxiv.org/pdf/1712.01093v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-mind-as-a-computational-system |
| Repo | |
| Framework | |
Towards meaningful physics from generative models
| Title | Towards meaningful physics from generative models |
| Authors | Marco Cristoforetti, Giuseppe Jurman, Andrea I. Nardelli, Cesare Furlanello |
| Abstract | In several physical systems, important properties characterizing the system itself are theoretically related with specific degrees of freedom. Although standard Monte Carlo simulations provide an effective tool to accurately reconstruct the physical configurations of the system, they are unable to isolate the different contributions corresponding to different degrees of freedom. Here we show that unsupervised deep learning can become a valid support to MC simulation, coupling useful insights in the phases detection task with good reconstruction performance. As a testbed we consider the 2D XY model, showing that a deep neural network based on variational autoencoders can detect the continuous Kosterlitz-Thouless (KT) transitions, and that, if endowed with the appropriate constrains, they generate configurations with meaningful physical content. |
| Tasks | |
| Published | 2017-05-26 |
| URL | http://arxiv.org/abs/1705.09524v1 |
| http://arxiv.org/pdf/1705.09524v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-meaningful-physics-from-generative |
| Repo | |
| Framework | |
An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction
| Title | An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction |
| Authors | Luiza Mici, German I. Parisi, Stefan Wermter |
| Abstract | During visuomotor tasks, robots must compensate for temporal delays inherent in their sensorimotor processing systems. Delay compensation becomes crucial in a dynamic environment where the visual input is constantly changing, e.g., during the interacting with a human demonstrator. For this purpose, the robot must be equipped with a prediction mechanism for using the acquired perceptual experience to estimate possible future motor commands. In this paper, we present a novel neural network architecture that learns prototypical visuomotor representations and provides reliable predictions on the basis of the visual input. These predictions are used to compensate for the delayed motor behavior in an online manner. We investigate the performance of our method with a set of experiments comprising a humanoid robot that has to learn and generate visually perceived arm motion trajectories. We evaluate the accuracy in terms of mean prediction error and analyze the response of the network to novel movement demonstrations. Additionally, we report experiments with incomplete data sequences, showing the robustness of the proposed architecture in the case of a noisy and faulty visual sensor. |
| Tasks | |
| Published | 2017-12-22 |
| URL | http://arxiv.org/abs/1712.08521v2 |
| http://arxiv.org/pdf/1712.08521v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-incremental-self-organizing-architecture |
| Repo | |
| Framework | |
On Convergence of Epanechnikov Mean Shift
| Title | On Convergence of Epanechnikov Mean Shift |
| Authors | Kejun Huang, Xiao Fu, Nicholas D. Sidiropoulos |
| Abstract | Epanechnikov Mean Shift is a simple yet empirically very effective algorithm for clustering. It localizes the centroids of data clusters via estimating modes of the probability distribution that generates the data points, using the `optimal’ Epanechnikov kernel density estimator. However, since the procedure involves non-smooth kernel density functions, the convergence behavior of Epanechnikov mean shift lacks theoretical support as of this writing—most of the existing analyses are based on smooth functions and thus cannot be applied to Epanechnikov Mean Shift. In this work, we first show that the original Epanechnikov Mean Shift may indeed terminate at a non-critical point, due to the non-smoothness nature. Based on our analysis, we propose a simple remedy to fix it. The modified Epanechnikov Mean Shift is guaranteed to terminate at a local maximum of the estimated density, which corresponds to a cluster centroid, within a finite number of iterations. We also propose a way to avoid running the Mean Shift iterates from every data point, while maintaining good clustering accuracies under non-overlapping spherical Gaussian mixture models. This further pushes Epanechnikov Mean Shift to handle very large and high-dimensional data sets. Experiments show surprisingly good performance compared to the Lloyd’s K-means algorithm and the EM algorithm. | |
| Tasks | |
| Published | 2017-11-20 |
| URL | http://arxiv.org/abs/1711.07441v1 |
| http://arxiv.org/pdf/1711.07441v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-convergence-of-epanechnikov-mean-shift |
| Repo | |
| Framework | |
Nonsmooth Frank-Wolfe using Uniform Affine Approximations
| Title | Nonsmooth Frank-Wolfe using Uniform Affine Approximations |
| Authors | Edward Cheung, Yuying Li |
| Abstract | Frank-Wolfe methods (FW) have gained significant interest in the machine learning community due to its ability to efficiently solve large problems that admit a sparse structure (e.g. sparse vectors and low-rank matrices). However the performance of the existing FW method hinges on the quality of the linear approximation. This typically restricts FW to smooth functions for which the approximation quality, indicated by a global curvature measure, is reasonably good. In this paper, we propose a modified FW algorithm amenable to nonsmooth functions by optimizing for approximation quality over all affine approximations given a neighborhood of interest. We analyze theoretical properties of the proposed algorithm and demonstrate that it overcomes many issues associated with existing methods in the context of nonsmooth low-rank matrix estimation. |
| Tasks | |
| Published | 2017-10-16 |
| URL | http://arxiv.org/abs/1710.05776v2 |
| http://arxiv.org/pdf/1710.05776v2.pdf | |
| PWC | https://paperswithcode.com/paper/nonsmooth-frank-wolfe-using-uniform-affine |
| Repo | |
| Framework | |
Combinatorial Penalties: Which structures are preserved by convex relaxations?
| Title | Combinatorial Penalties: Which structures are preserved by convex relaxations? |
| Authors | Marwa El Halabi, Francis Bach, Volkan Cevher |
| Abstract | We consider the homogeneous and the non-homogeneous convex relaxations for combinatorial penalty functions defined on support sets. Our study identifies key differences in the tightness of the resulting relaxations through the notion of the lower combinatorial envelope of a set-function along with new necessary conditions for support identification. We then propose a general adaptive estimator for convex monotone regularizers, and derive new sufficient conditions for support recovery in the asymptotic setting. |
| Tasks | |
| Published | 2017-10-17 |
| URL | http://arxiv.org/abs/1710.06273v2 |
| http://arxiv.org/pdf/1710.06273v2.pdf | |
| PWC | https://paperswithcode.com/paper/combinatorial-penalties-which-structures-are |
| Repo | |
| Framework | |
