January 26, 2020

2950 words 14 mins read

Paper Group ANR 1554

NarrativeTime: Dense High-Speed Temporal Annotation on a Timeline. Enhancing Neural Sequence Labeling with Position-Aware Self-Attention. Generative Dialog Policy for Task-oriented Dialog Systems. Unsupervised shape and motion analysis of 3822 cardiac 4D MRIs of UK Biobank. Stochastic learning control of inhomogeneous quantum ensembles. Load Balanc …

NarrativeTime: Dense High-Speed Temporal Annotation on a Timeline


Title	NarrativeTime: Dense High-Speed Temporal Annotation on a Timeline
Authors	Anna Rogers, Gregory Smelkov, Anna Rumshisky
Abstract	We present NarrativeTime, a new timeline-based annotation scheme for temporal order of events in text, and a new densely annotated fiction corpus comparable to TimeBank-Dense. NarrativeTime is considerably faster than schemes based on event pairs such as TimeML, and it produces more temporal links between events than TimeBank-Dense, while maintaining comparable agreement on temporal links. This is achieved through new strategies for encoding vagueness in temporal relations and an annotation workflow that takes into account the annotators’ chunking and commonsense reasoning strategies. NarrativeTime comes with new specialized web-based tools for annotation and adjudication.
Tasks	Chunking
Published	2019-08-29
URL	https://arxiv.org/abs/1908.11443v1
PDF	https://arxiv.org/pdf/1908.11443v1.pdf
PWC	https://paperswithcode.com/paper/narrativetime-dense-high-speed-temporal
Repo
Framework

Enhancing Neural Sequence Labeling with Position-Aware Self-Attention


Title	Enhancing Neural Sequence Labeling with Position-Aware Self-Attention
Authors	Wei Wei, Zanbo Wang, Xianling Mao, Guangyou Zhou, Pan Zhou, Sheng Jiang
Abstract	Sequence labeling is a fundamental task in natural language processing and has been widely studied. Recently, RNN-based sequence labeling models have increasingly gained attentions. Despite superior performance achieved by learning the long short-term (i.e., successive) dependencies, the way of sequentially processing inputs might limit the ability to capture the non-continuous relations over tokens within a sentence. To tackle the problem, we focus on how to effectively model successive and discrete dependencies of each token for enhancing the sequence labeling performance. Specifically, we propose an innovative and well-designed attention-based model (called position-aware self-attention, i.e., PSA) within a neural network architecture, to explore the positional information of an input sequence for capturing the latent relations among tokens. Extensive experiments on three classical tasks in sequence labeling domain, i.e., part-of-speech (POS) tagging, named entity recognition (NER) and phrase chunking, demonstrate our proposed model outperforms the state-of-the-arts without any external knowledge, in terms of various metrics.
Tasks	Chunking, Named Entity Recognition, Part-Of-Speech Tagging
Published	2019-08-24
URL	https://arxiv.org/abs/1908.09128v1
PDF	https://arxiv.org/pdf/1908.09128v1.pdf
PWC	https://paperswithcode.com/paper/enhancing-neural-sequence-labeling-with
Repo
Framework

Generative Dialog Policy for Task-oriented Dialog Systems


Title	Generative Dialog Policy for Task-oriented Dialog Systems
Authors	Tian Lan, Xianling Mao, Heyan Huang
Abstract	There is an increasing demand for task-oriented dialogue systems which can assist users in various activities such as booking tickets and restaurant reservations. In order to complete dialogues effectively, dialogue policy plays a key role in task-oriented dialogue systems. As far as we know, the existing task-oriented dialogue systems obtain the dialogue policy through classification, which can assign either a dialogue act and its corresponding parameters or multiple dialogue acts without their corresponding parameters for a dialogue action. In fact, a good dialogue policy should construct multiple dialogue acts and their corresponding parameters at the same time. However, it’s hard for existing classification-based methods to achieve this goal. Thus, to address the issue above, we propose a novel generative dialogue policy learning method. Specifically, the proposed method uses attention mechanism to find relevant segments of given dialogue context and input utterance and then constructs the dialogue policy by a seq2seq way for task-oriented dialogue systems. Extensive experiments on two benchmark datasets show that the proposed model significantly outperforms the state-of-the-art baselines. In addition, we have publicly released our codes.
Tasks	Task-Oriented Dialogue Systems
Published	2019-09-17
URL	https://arxiv.org/abs/1909.09484v1
PDF	https://arxiv.org/pdf/1909.09484v1.pdf
PWC	https://paperswithcode.com/paper/generative-dialog-policy-for-task-oriented
Repo
Framework

Unsupervised shape and motion analysis of 3822 cardiac 4D MRIs of UK Biobank


Title	Unsupervised shape and motion analysis of 3822 cardiac 4D MRIs of UK Biobank
Authors	Qiao Zheng, Hervé Delingette, Kenneth Fung, Steffen E. Petersen, Nicholas Ayache
Abstract	We perform unsupervised analysis of image-derived shape and motion features extracted from 3822 cardiac 4D MRIs of the UK Biobank. First, with a feature extraction method previously published based on deep learning models, we extract from each case 9 feature values characterizing both the cardiac shape and motion. Second, a feature selection is performed to remove highly correlated feature pairs. Third, clustering is carried out using a Gaussian mixture model on the selected features. After analysis, we identify two small clusters which probably correspond to two pathological categories. Further confirmation using a trained classification model and dimensionality reduction tools is carried out to support this discovery. Moreover, we examine the differences between the other large clusters and compare our measures with the ground-truth.
Tasks	Dimensionality Reduction, Feature Selection
Published	2019-02-15
URL	http://arxiv.org/abs/1902.05811v1
PDF	http://arxiv.org/pdf/1902.05811v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-shape-and-motion-analysis-of
Repo
Framework

Stochastic learning control of inhomogeneous quantum ensembles


Title	Stochastic learning control of inhomogeneous quantum ensembles
Authors	Gabriel Turinici
Abstract	In quantum control, the robustness with respect to uncertainties in the system’s parameters or driving field characteristics is of paramount importance and has been studied theoretically, numerically and experimentally. We test in this paper stochastic search procedures (Stochastic gradient descent and the Adam algorithm) that sample, at each iteration, from the distribution of the parameter uncertainty, as opposed to previous approaches that use a fixed grid. We show that both algorithms behave well with respect to benchmarks and discuss their relative merits. In addition the methodology allows to address high dimensional parameter uncertainty; we implement numerically, with good results, a 3D and a 6D case.
Tasks
Published	2019-06-07
URL	https://arxiv.org/abs/1906.02991v3
PDF	https://arxiv.org/pdf/1906.02991v3.pdf
PWC	https://paperswithcode.com/paper/stochastic-learning-control-of-inhomogeneous
Repo
Framework

Load Balancing for Ultra-Dense Networks: A Deep Reinforcement Learning Based Approach


Title	Load Balancing for Ultra-Dense Networks: A Deep Reinforcement Learning Based Approach
Authors	Yue Xu, Wenjun Xu, Zhi Wang, Jiaru Lin, Shuguang Cui
Abstract	In this paper, we propose a deep reinforcement learning (DRL) based mobility load balancing (MLB) algorithm along with a two-layer architecture to solve the large-scale load balancing problem for ultra-dense networks (UDNs). Our contribution is three-fold. First, this work proposes a two-layer architecture to solve the large-scale load balancing problem in a self-organized manner. The proposed architecture can alleviate the global traffic variations by dynamically grouping small cells into self-organized clusters according to their historical loads, and further adapt to local traffic variations through intra-cluster load balancing afterwards. Second, for the intra-cluster load balancing, this paper proposes an off-policy DRL-based MLB algorithm to autonomously learn the optimal MLB policy under an asynchronous parallel learning framework, without any prior knowledge assumed over the underlying UDN environments. Moreover, the algorithm enables joint exploration with multiple behavior policies, such that the traditional MLB methods can be used to guide the learning process thereby improving the learning efficiency and stability. Third, this work proposes an offline-evaluation based safeguard mechanism to ensure that the online system can always operate with the optimal and well-trained MLB policy, which not only stabilizes the online performance but also enables the exploration beyond current policies to make full use of machine learning in a safe way. Empirical results verify that the proposed framework outperforms the existing MLB methods in general UDN environments featured with irregular network topologies, coupled interferences, and random user movements, in terms of the load balancing performance.
Tasks
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00767v3
PDF	https://arxiv.org/pdf/1906.00767v3.pdf
PWC	https://paperswithcode.com/paper/190600767
Repo
Framework

Locally Private k-Means Clustering


Title	Locally Private k-Means Clustering
Authors	Uri Stemmer
Abstract	We design a new algorithm for the Euclidean $k$-means problem that operates in the local model of differential privacy. Unlike in the non-private literature, differentially private algorithms for the $k$-means incur both additive and multiplicative errors. Our algorithm significantly reduces the additive error while keeping the multiplicative error the same as in previous state-of-the-art results. Specifically, on a database of size $n$, our algorithm guarantees $O(1)$ multiplicative error and $\approx n^{1/2+a}$ additive error for an arbitrarily small constant $a$, whereas all previous algorithms in the local model on had additive error $\approx n^{2/3+a}$. We give a simple lower bound showing that additive error of $\approx\sqrt{n}$ is necessary for $k$-means algorithms in the local model (at least for algorithms with a constant number of interaction rounds, which is the setting we consider in this paper).
Tasks
Published	2019-07-04
URL	https://arxiv.org/abs/1907.02513v1
PDF	https://arxiv.org/pdf/1907.02513v1.pdf
PWC	https://paperswithcode.com/paper/locally-private-k-means-clustering
Repo
Framework

Artificial Intelligence : from Research to Application ; the Upper-Rhine Artificial Intelligence Symposium (UR-AI 2019)


Title	Artificial Intelligence : from Research to Application ; the Upper-Rhine Artificial Intelligence Symposium (UR-AI 2019)
Authors	Andreas Christ, Franz Quint
Abstract	The TriRhenaTech alliance universities and their partners presented their competences in the field of artificial intelligence and their cross-border cooperations with the industry at the tri-national conference ‘Artificial Intelligence : from Research to Application’ on March 13th, 2019 in Offenburg. The TriRhenaTech alliance is a network of universities in the Upper Rhine Trinational Metropolitan Region comprising of the German universities of applied sciences in Furtwangen, Kaiserslautern, Karlsruhe, and Offenburg, the Baden-Wuerttemberg Cooperative State University Loerrach, the French university network Alsace Tech (comprised of 14 ‘grandes 'ecoles’ in the fields of engineering, architecture and management) and the University of Applied Sciences and Arts Northwestern Switzerland. The alliance’s common goal is to reinforce the transfer of knowledge, research, and technology, as well as the cross-border mobility of students.
Tasks
Published	2019-03-20
URL	http://arxiv.org/abs/1903.08495v1
PDF	http://arxiv.org/pdf/1903.08495v1.pdf
PWC	https://paperswithcode.com/paper/artificial-intelligence-from-research-to
Repo
Framework

Cross-view Semantic Segmentation for Sensing Surroundings


Title	Cross-view Semantic Segmentation for Sensing Surroundings
Authors	Bowen Pan, Jiankai Sun, Alex Andonian, Bolei Zhou
Abstract	Sensing surroundings is ubiquitous and effortless to humans: It takes a single glance to extract the spatial configuration of objects as well as the free space from the observation. To facilitate machine perception with such a surrounding sensing capability, we introduce a novel framework for cross-view semantic segmentation. In this framework, the View Parsing Network (VPN) is proposed to parse the first-view observations into a top-down-view semantic map indicating the spatial location of all the objects at pixel-level. The view transformer module contained in VPN is designed to aggregate the surrounding information collected from first-view observations in multiple angles and modalities. To mitigate the issue of lacking real-world annotations, we train the VPN in simulation environment and utilize the off-the-shelf domain adaptation technique to transfer it to real-world data. We evaluate our VPN on both synthetic and real-world data. The experimental results show that our model can effectively make use of the information from different views and multi-modalities. Thus the proposed VPN is able to accurately predict the top-down-view semantic mask of the visible objects as well as barely seen objects, in both synthetic and real-world environments.
Tasks	Domain Adaptation, Semantic Segmentation
Published	2019-06-09
URL	https://arxiv.org/abs/1906.03560v2
PDF	https://arxiv.org/pdf/1906.03560v2.pdf
PWC	https://paperswithcode.com/paper/cross-view-semantic-segmentation-for-sensing
Repo
Framework

Enhancing Salient Object Segmentation Through Attention


Title	Enhancing Salient Object Segmentation Through Attention
Authors	Anuj Pahuja, Avishek Majumder, Anirban Chakraborty, R. Venkatesh Babu
Abstract	Segmenting salient objects in an image is an important vision task with ubiquitous applications. The problem becomes more challenging in the presence of a cluttered and textured background, low resolution and/or low contrast images. Even though existing algorithms perform well in segmenting most of the object(s) of interest, they often end up segmenting false positives due to resembling salient objects in the background. In this work, we tackle this problem by iteratively attending to image patches in a recurrent fashion and subsequently enhancing the predicted segmentation mask. Saliency features are estimated independently for every image patch, which are further combined using an aggregation strategy based on a Convolutional Gated Recurrent Unit (ConvGRU) network. The proposed approach works in an end-to-end manner, removing background noise and false positives incrementally. Through extensive evaluation on various benchmark datasets, we show superior performance to the existing approaches without any post-processing.
Tasks	Semantic Segmentation
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11522v1
PDF	https://arxiv.org/pdf/1905.11522v1.pdf
PWC	https://paperswithcode.com/paper/190511522
Repo
Framework

Specific polysemy of the brief sapiential units


Title	Specific polysemy of the brief sapiential units
Authors	Marie-Christine Bornes-Varol, Marie-Sol Ortola, Gronoff Jean-Daniel
Abstract	In this paper we explain how we deal with the problems related to the constitution of the Aliento database, the complexity of which has to do with the type of phrases we work with, the differences between languages, the type of information we want to see emerge. The correct tagging of the specific polysemy of brief sapiential units is an important step in the preparation of the text within the corpus which will be submitted to compute similarities and posterity of the units.
Tasks
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11836v1
PDF	https://arxiv.org/pdf/1905.11836v1.pdf
PWC	https://paperswithcode.com/paper/specific-polysemy-of-the-brief-sapiential
Repo
Framework

Privacy Preserving Location Data Publishing: A Machine Learning Approach


Title	Privacy Preserving Location Data Publishing: A Machine Learning Approach
Authors	Sina Shaham, Ming Ding, Bo Liu, Shuping Dang, Zihuai Lin, Jun Li
Abstract	Publishing datasets plays an essential role in open data research and promoting transparency of government agencies. However, such data publication might reveal users’ private information. One of the most sensitive sources of data is spatiotemporal trajectory datasets. Unfortunately, merely removing unique identifiers cannot preserve the privacy of users. Adversaries may know parts of the trajectories or be able to link the published dataset to other sources for the purpose of user identification. Therefore, it is crucial to apply privacy preserving techniques before the publication of spatiotemporal trajectory datasets. In this paper, we propose a robust framework for the anonymization of spatiotemporal trajectory datasets termed as machine learning based anonymization (MLA). By introducing a new formulation of the problem, we are able to apply machine learning algorithms for clustering the trajectories and propose to use $k$-means algorithm for this purpose. A variation of $k$-means algorithm is also proposed to preserve the privacy in overly sensitive datasets. Moreover, we improve the alignment process by considering multiple sequence alignment as part of the MLA. The framework and all the proposed algorithms are applied to TDrive and Geolife location datasets. The experimental results indicate a significantly higher utility of datasets by anonymization based on MLA framework.
Tasks
Published	2019-02-24
URL	https://arxiv.org/abs/1902.08934v2
PDF	https://arxiv.org/pdf/1902.08934v2.pdf
PWC	https://paperswithcode.com/paper/machine-learning-aided-anonymization-of
Repo
Framework

Self-Supervised Representation Learning via Neighborhood-Relational Encoding


Title	Self-Supervised Representation Learning via Neighborhood-Relational Encoding
Authors	Mohammad Sabokrou, Mohammad Khalooei, Ehsan Adeli
Abstract	In this paper, we propose a novel self-supervised representation learning by taking advantage of a neighborhood-relational encoding (NRE) among the training data. Conventional unsupervised learning methods only focused on training deep networks to understand the primitive characteristics of the visual data, mainly to be able to reconstruct the data from a latent space. They often neglected the relation among the samples, which can serve as an important metric for self-supervision. Different from the previous work, NRE aims at preserving the local neighborhood structure on the data manifold. Therefore, it is less sensitive to outliers. We integrate our NRE component with an encoder-decoder structure for learning to represent samples considering their local neighborhood information. Such discriminative and unsupervised representation learning scheme is adaptable to different computer vision tasks due to its independence from intense annotation requirements. We evaluate our proposed method for different tasks, including classification, detection, and segmentation based on the learned latent representations. In addition, we adopt the auto-encoding capability of our proposed method for applications like defense against adversarial example attacks and video anomaly detection. Results confirm the performance of our method is better or at least comparable with the state-of-the-art for each specific application, but with a generic and self-supervised approach.
Tasks	Anomaly Detection, Representation Learning, Unsupervised Representation Learning
Published	2019-08-27
URL	https://arxiv.org/abs/1908.10455v1
PDF	https://arxiv.org/pdf/1908.10455v1.pdf
PWC	https://paperswithcode.com/paper/self-supervised-representation-learning-via
Repo
Framework

Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints


Title	Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints
Authors	Yan Xu, Xinge Zhu, Jianping Shi, Guofeng Zhang, Hujun Bao, Hongsheng Li
Abstract	Depth completion aims to recover dense depth maps from sparse depth measurements. It is of increasing importance for autonomous driving and draws increasing attention from the vision community. Most of existing methods directly train a network to learn a mapping from sparse depth inputs to dense depth maps, which has difficulties in utilizing the 3D geometric constraints and handling the practical sensor noises. In this paper, to regularize the depth completion and improve the robustness against noise, we propose a unified CNN framework that 1) models the geometric constraints between depth and surface normal in a diffusion module and 2) predicts the confidence of sparse LiDAR measurements to mitigate the impact of noise. Specifically, our encoder-decoder backbone predicts surface normals, coarse depth and confidence of LiDAR inputs simultaneously, which are subsequently inputted into our diffusion refinement module to obtain the final completion results. Extensive experiments on KITTI depth completion dataset and NYU-Depth-V2 dataset demonstrate that our method achieves state-of-the-art performance. Further ablation study and analysis give more insights into the proposed method and demonstrate the generalization capability and stability of our model.
Tasks	Autonomous Driving, Depth Completion
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06727v1
PDF	https://arxiv.org/pdf/1910.06727v1.pdf
PWC	https://paperswithcode.com/paper/depth-completion-from-sparse-lidar-data-with
Repo
Framework

Online Estimation of Multiple Dynamic Graphs in Pattern Sequences


Title	Online Estimation of Multiple Dynamic Graphs in Pattern Sequences
Authors	Jimmy Gaudreault, Arunabh Saxena, Hideaki Shimazaki
Abstract	Sequences of correlated binary patterns can represent many time-series data including text, movies, and biological signals. These patterns may be described by weighted combinations of a few dominant structures that underpin specific interactions among the binary elements. To extract the dominant correlation structures and their contributions to generating data in a time-dependent manner, we model the dynamics of binary patterns using the state-space model of an Ising-type network that is composed of multiple undirected graphs. We provide a sequential Bayes algorithm to estimate the dynamics of weights on the graphs while gaining the graph structures online. This model can uncover overlapping graphs underlying the data better than a traditional orthogonal decomposition method, and outperforms an original time-dependent Ising model. We assess the performance of the method by simulated data, and demonstrate that spontaneous activity of cultured hippocampal neurons is represented by dynamics of multiple graphs.
Tasks	Time Series
Published	2019-01-22
URL	http://arxiv.org/abs/1901.07298v2
PDF	http://arxiv.org/pdf/1901.07298v2.pdf
PWC	https://paperswithcode.com/paper/online-estimation-of-multiple-dynamic-graphs
Repo
Framework