July 29, 2019

2695 words 13 mins read

Paper Group ANR 66

Approches d’analyse distributionnelle pour améliorer la désambiguïsation sémantique. Optimal Vehicle Dispatching Schemes via Dynamic Pricing. Communication-Free Parallel Supervised Topic Models. Mutual Alignment Transfer Learning. Topically Driven Neural Language Model. Practical Algorithms for Best-K Identification in Multi-Armed Bandits. ClaC: Se …

Approches d’analyse distributionnelle pour améliorer la désambiguïsation sémantique


Title	Approches d’analyse distributionnelle pour améliorer la désambiguïsation sémantique
Authors	Mokhtar Billami, Núria Gala
Abstract	Word sense disambiguation (WSD) improves many Natural Language Processing (NLP) applications such as Information Retrieval, Machine Translation or Lexical Simplification. WSD is the ability of determining a word sense among different ones within a polysemic lexical unit taking into account the context. The most straightforward approach uses a semantic proximity measure between the word sense candidates of the target word and those of its context. Such a method very easily entails a combinatorial explosion. In this paper, we propose two methods based on distributional analysis which enable to reduce the exponential complexity without losing the coherence. We present a comparison between the selection of distributional neighbors and the linearly nearest neighbors. The figures obtained show that selecting distributional neighbors leads to better results.
Tasks	Information Retrieval, Lexical Simplification, Machine Translation, Word Sense Disambiguation
Published	2017-02-27
URL	http://arxiv.org/abs/1702.08451v1
PDF	http://arxiv.org/pdf/1702.08451v1.pdf
PWC	https://paperswithcode.com/paper/approches-danalyse-distributionnelle-pour
Repo
Framework

Optimal Vehicle Dispatching Schemes via Dynamic Pricing


Title	Optimal Vehicle Dispatching Schemes via Dynamic Pricing
Authors	Mengjing Chen, Weiran Shen, Pingzhong Tang, Song Zuo
Abstract	Over the past few years, ride-sharing has emerged as an effective way to relieve traffic congestion. A key problem for these platforms is to come up with a revenue-optimal (or GMV-optimal) pricing scheme and an induced vehicle dispatching policy that incorporate geographic and temporal information. In this paper, we aim to tackle this problem via an economic approach. Modeled naively, the underlying optimization problem may be non-convex and thus hard to compute. To this end, we use a so-called “ironing” technique to convert the problem into an equivalent convex optimization one via a clean Markov decision process (MDP) formulation, where the states are the driver distributions and the decision variables are the prices for each pair of locations. Our main finding is an efficient algorithm that computes the exact revenue-optimal (or GMV-optimal) randomized pricing schemes. We characterize the optimal solution of the MDP by a primal-dual analysis of a corresponding convex program. We also conduct empirical evaluations of our solution through real data of a major ride-sharing platform and show its advantages over fixed pricing schemes as well as several prevalent surge-based pricing schemes.
Tasks
Published	2017-07-06
URL	http://arxiv.org/abs/1707.01625v2
PDF	http://arxiv.org/pdf/1707.01625v2.pdf
PWC	https://paperswithcode.com/paper/optimal-vehicle-dispatching-schemes-via
Repo
Framework

Communication-Free Parallel Supervised Topic Models


Title	Communication-Free Parallel Supervised Topic Models
Authors	Lee Gao, Ronghuo Zheng
Abstract	Embarrassingly (communication-free) parallel Markov chain Monte Carlo (MCMC) methods are commonly used in learning graphical models. However, MCMC cannot be directly applied in learning topic models because of the quasi-ergodicity problem caused by multimodal distribution of topics. In this paper, we develop an embarrassingly parallel MCMC algorithm for sLDA. Our algorithm works by switching the order of sampled topics combination and labeling variable prediction in sLDA, in which it overcomes the quasi-ergodicity problem because high-dimension topics that follow a multimodal distribution are projected into one-dimension document labels that follow a unimodal distribution. Our empirical experiments confirm that the out-of-sample prediction performance using our embarrassingly parallel algorithm is comparable to non-parallel sLDA while the computation time is significantly reduced.
Tasks	Topic Models
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03052v1
PDF	http://arxiv.org/pdf/1708.03052v1.pdf
PWC	https://paperswithcode.com/paper/communication-free-parallel-supervised-topic
Repo
Framework

Mutual Alignment Transfer Learning


Title	Mutual Alignment Transfer Learning
Authors	Markus Wulfmeier, Ingmar Posner, Pieter Abbeel
Abstract	Training robots for operation in the real world is a complex, time consuming and potentially expensive task. Despite significant success of reinforcement learning in games and simulations, research in real robot applications has not been able to match similar progress. While sample complexity can be reduced by training policies in simulation, such policies can perform sub-optimally on the real platform given imperfect calibration of model dynamics. We present an approach – supplemental to fine tuning on the real robot – to further benefit from parallel access to a simulator during training and reduce sample requirements on the real robot. The developed approach harnesses auxiliary rewards to guide the exploration for the real world agent based on the proficiency of the agent in simulation and vice versa. In this context, we demonstrate empirically that the reciprocal alignment for both agents provides further benefit as the agent in simulation can adjust to optimize its behaviour for states commonly visited by the real-world agent.
Tasks	Calibration, Transfer Learning
Published	2017-07-25
URL	http://arxiv.org/abs/1707.07907v3
PDF	http://arxiv.org/pdf/1707.07907v3.pdf
PWC	https://paperswithcode.com/paper/mutual-alignment-transfer-learning
Repo
Framework

Topically Driven Neural Language Model


Title	Topically Driven Neural Language Model
Authors	Jey Han Lau, Timothy Baldwin, Trevor Cohn
Abstract	Language models are typically applied at the sentence level, without access to the broader document context. We present a neural language model that incorporates document context in the form of a topic model-like architecture, thus providing a succinct representation of the broader document context outside of the current sentence. Experiments over a range of datasets demonstrate that our model outperforms a pure sentence-based model in terms of language model perplexity, and leads to topics that are potentially more coherent than those produced by a standard LDA topic model. Our model also has the ability to generate related sentences for a topic, providing another way to interpret topics.
Tasks	Language Modelling
Published	2017-04-26
URL	http://arxiv.org/abs/1704.08012v2
PDF	http://arxiv.org/pdf/1704.08012v2.pdf
PWC	https://paperswithcode.com/paper/topically-driven-neural-language-model
Repo
Framework

Practical Algorithms for Best-K Identification in Multi-Armed Bandits


Title	Practical Algorithms for Best-K Identification in Multi-Armed Bandits
Authors	Haotian Jiang, Jian Li, Mingda Qiao
Abstract	In the Best-$K$ identification problem (Best-$K$-Arm), we are given $N$ stochastic bandit arms with unknown reward distributions. Our goal is to identify the $K$ arms with the largest means with high confidence, by drawing samples from the arms adaptively. This problem is motivated by various practical applications and has attracted considerable attention in the past decade. In this paper, we propose new practical algorithms for the Best-$K$-Arm problem, which have nearly optimal sample complexity bounds (matching the lower bound up to logarithmic factors) and outperform the state-of-the-art algorithms for the Best-$K$-Arm problem (even for $K=1$) in practice.
Tasks	Multi-Armed Bandits
Published	2017-05-19
URL	http://arxiv.org/abs/1705.06894v1
PDF	http://arxiv.org/pdf/1705.06894v1.pdf
PWC	https://paperswithcode.com/paper/practical-algorithms-for-best-k
Repo
Framework

ClaC: Semantic Relatedness of Words and Phrases


Title	ClaC: Semantic Relatedness of Words and Phrases
Authors	Reda Siblini, Leila Kosseim
Abstract	The measurement of phrasal semantic relatedness is an important metric for many natural language processing applications. In this paper, we present three approaches for measuring phrasal semantics, one based on a semantic network model, another on a distributional similarity model, and a hybrid between the two. Our hybrid approach achieved an F-measure of 77.4% on the task of evaluating the semantic similarity of words and compositional phrases.
Tasks	Semantic Similarity, Semantic Textual Similarity
Published	2017-08-19
URL	http://arxiv.org/abs/1708.05801v1
PDF	http://arxiv.org/pdf/1708.05801v1.pdf
PWC	https://paperswithcode.com/paper/clac-semantic-relatedness-of-words-and
Repo
Framework

Consideration on Example 2 of “An Algorithm of General Fuzzy InferenceWith The Reductive Property”


Title	Consideration on Example 2 of “An Algorithm of General Fuzzy InferenceWith The Reductive Property”
Authors	Son-Il Kwak, Oh-Chol Gwon, Chung-Jin Kwak
Abstract	In this paper, we will show that (1) the results about the fuzzy reasoning algoritm obtained in the paper “Computer Sciences Vol. 34, No.4, pp.145-148, 2007” according to the paper “IEEE Transactions On systems, Man and cybernetics, 18, pp.1049-1056, 1988” are correct; (2) example 2 in the paper “An Algorithm of General Fuzzy Inference With The Reductive Property” presented by He Ying-Si, Quan Hai-Jin and Deng Hui-Wen according to the paper “An approximate analogical reasoning approach based on similarity measures” presented by Tursken I.B. and Zhong zhao is incorrect; (3) the mistakes in their paper are modified and then a calculation example of FMT is supplemented.
Tasks
Published	2017-12-13
URL	http://arxiv.org/abs/1712.04596v1
PDF	http://arxiv.org/pdf/1712.04596v1.pdf
PWC	https://paperswithcode.com/paper/consideration-on-example-2-of-an-algorithm-of
Repo
Framework

Topology Estimation in Bulk Power Grids: Guarantees on Exact Recovery


Title	Topology Estimation in Bulk Power Grids: Guarantees on Exact Recovery
Authors	Deepjyoti Deka, Saurav Talukdar, Michael Chertkov, Murti Salapaka
Abstract	The topology of a power grid affects its dynamic operation and settlement in the electricity market. Real-time topology identification can enable faster control action following an emergency scenario like failure of a line. This article discusses a graphical model framework for topology estimation in bulk power grids (both loopy transmission and radial distribution) using measurements of voltage collected from the grid nodes. The graphical model for the probability distribution of nodal voltages in linear power flow models is shown to include additional edges along with the operational edges in the true grid. Our proposed estimation algorithms first learn the graphical model and subsequently extract the operational edges using either thresholding or a neighborhood counting scheme. For grid topologies containing no three-node cycles (two buses do not share a common neighbor), we prove that an exact extraction of the operational topology is theoretically guaranteed. This includes a majority of distribution grids that have radial topologies. For grids that include cycles of length three, we provide sufficient conditions that ensure existence of algorithms for exact reconstruction. In particular, for grids with constant impedance per unit length and uniform injection covariances, this observation leads to conditions on geographical placement of the buses. The performance of algorithms is demonstrated in test case simulations.
Tasks
Published	2017-07-05
URL	http://arxiv.org/abs/1707.01596v2
PDF	http://arxiv.org/pdf/1707.01596v2.pdf
PWC	https://paperswithcode.com/paper/topology-estimation-in-bulk-power-grids
Repo
Framework

Game theory models for communication between agents: a review


Title	Game theory models for communication between agents: a review
Authors	Aisha D. Farooqui, Muaz A. Niazi
Abstract	In the real world, agents or entities are in a continuous state of interactions. These inter- actions lead to various types of complexity dynamics. One key difficulty in the study of complex agent interactions is the difficulty of modeling agent communication on the basis of rewards. Game theory offers a perspective of analysis and modeling these interactions. Previously, while a large amount of literature is available on game theory, most of it is from specific domains and does not cater for the concepts from an agent- based perspective. Here in this paper, we present a comprehensive multidisciplinary state-of-the-art review and taxonomy of game theory models of complex interactions between agents.
Tasks
Published	2017-08-04
URL	http://arxiv.org/abs/1708.01636v1
PDF	http://arxiv.org/pdf/1708.01636v1.pdf
PWC	https://paperswithcode.com/paper/game-theory-models-for-communication-between
Repo
Framework

Online Interactive Collaborative Filtering Using Multi-Armed Bandit with Dependent Arms


Title	Online Interactive Collaborative Filtering Using Multi-Armed Bandit with Dependent Arms
Authors	Qing Wang, Chunqiu Zeng, Wubai Zhou, Tao Li, Larisa Shwartz, Genady Ya. Grabarnik
Abstract	Online interactive recommender systems strive to promptly suggest to consumers appropriate items (e.g., movies, news articles) according to the current context including both the consumer and item content information. However, such context information is often unavailable in practice for the recommendation, where only the users’ interaction data on items can be utilized. Moreover, the lack of interaction records, especially for new users and items, worsens the performance of recommendation further. To address these issues, collaborative filtering (CF), one of the recommendation techniques relying on the interaction data only, as well as the online multi-armed bandit mechanisms, capable of achieving the balance between exploitation and exploration, are adopted in the online interactive recommendation settings, by assuming independent items (i.e., arms). Nonetheless, the assumption rarely holds in reality, since the real-world items tend to be correlated with each other (e.g., two articles with similar topics). In this paper, we study online interactive collaborative filtering problems by considering the dependencies among items. We explicitly formulate the item dependencies as the clusters on arms, where the arms within a single cluster share the similar latent topics. In light of the topic modeling techniques, we come up with a generative model to generate the items from their underlying topics. Furthermore, an efficient online algorithm based on particle learning is developed for inferring both latent parameters and states of our model. Additionally, our inferred model can be naturally integrated with existing multi-armed selection strategies in the online interactive collaborating setting. Empirical studies on two real-world applications, online recommendations of movies and news, demonstrate both the effectiveness and efficiency of the proposed approach.
Tasks	Recommendation Systems
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03058v2
PDF	http://arxiv.org/pdf/1708.03058v2.pdf
PWC	https://paperswithcode.com/paper/online-interactive-collaborative-filtering
Repo
Framework

Distributed Algorithms for Feature Extraction Off-loading in Multi-Camera Visual Sensor Networks


Title	Distributed Algorithms for Feature Extraction Off-loading in Multi-Camera Visual Sensor Networks
Authors	Emil Eriksson, György Dán, Viktoria Fodor
Abstract	Real-time visual analysis tasks, like tracking and recognition, require swift execution of computationally intensive algorithms. Visual sensor networks can be enabled to perform such tasks by augmenting the sensor network with processing nodes and distributing the computational burden in a way that the cameras contend for the processing nodes while trying to minimize their task completion times. In this paper, we formulate the problem of minimizing the completion time of all camera sensors as an optimization problem. We propose algorithms for fully distributed optimization, analyze the existence of equilibrium allocations, evaluate the effect of the network topology and of the video characteristics, and the benefits of central coordination. Our results demonstrate that with sufficient information available, distributed optimization can provide low completion times, moreover predictable and stable performance can be achieved with additional, sparse central coordination.
Tasks	Distributed Optimization
Published	2017-05-15
URL	http://arxiv.org/abs/1705.08252v1
PDF	http://arxiv.org/pdf/1705.08252v1.pdf
PWC	https://paperswithcode.com/paper/distributed-algorithms-for-feature-extraction
Repo
Framework

Knowledge transfer for surgical activity prediction


Title	Knowledge transfer for surgical activity prediction
Authors	Olga Dergachyova, Xavier Morandi, Pierre Jannin
Abstract	Lack of training data hinders automatic recognition and prediction of surgical activities necessary for situation-aware operating rooms. We propose using knowledge transfer to compensate for data deficit and improve prediction. We used two approaches to extract and transfer surgical process knowledge. First, we encoded semantic information about surgical terms using word embedding which boosted learning process. Secondly, we passed knowledge between different clinical datasets of neurosurgical procedures using transfer learning. Transfer learning was shown to be more effective than a simple combination of data, especially for less similar procedures. The combination of two methods provided 22% improvement of activity prediction. We also made several pertinent observations about surgical practices.
Tasks	Activity Prediction, Transfer Learning
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05848v1
PDF	http://arxiv.org/pdf/1711.05848v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-transfer-for-surgical-activity
Repo
Framework

Deep Cropping via Attention Box Prediction and Aesthetics Assessment


Title	Deep Cropping via Attention Box Prediction and Aesthetics Assessment
Authors	Wenguan Wang, Jianbing Shen
Abstract	We model the photo cropping problem as a cascade of attention box regression and aesthetic quality classification, based on deep learning. A neural network is designed that has two branches for predicting attention bounding box and analyzing aesthetics, respectively. The predicted attention box is treated as an initial crop window where a set of cropping candidates are generated around it, without missing important information. Then, aesthetics assessment is employed to select the final crop as the one with the best aesthetic quality. With our network, cropping candidates share features within full-image convolutional feature maps, thus avoiding repeated feature computation and leading to higher computation efficiency. Via leveraging rich data for attention prediction and aesthetics assessment, the proposed method produces high-quality cropping results, even with the limited availability of training data for photo cropping. The experimental results demonstrate the competitive results and fast processing speed (5 fps with all steps).
Tasks
Published	2017-10-22
URL	http://arxiv.org/abs/1710.08014v1
PDF	http://arxiv.org/pdf/1710.08014v1.pdf
PWC	https://paperswithcode.com/paper/deep-cropping-via-attention-box-prediction
Repo
Framework

Lost in Time: Temporal Analytics for Long-Term Video Surveillance


Title	Lost in Time: Temporal Analytics for Long-Term Video Surveillance
Authors	Huai-Qian Khor, John See
Abstract	Video surveillance is a well researched area of study with substantial work done in the aspects of object detection, tracking and behavior analysis. With the abundance of video data captured over a long period of time, we can understand patterns in human behavior and scene dynamics through data-driven temporal analytics. In this work, we propose two schemes to perform descriptive and predictive analytics on long-term video surveillance data. We generate heatmap and footmap visualizations to describe spatially pooled trajectory patterns with respect to time and location. We also present two approaches for anomaly prediction at the day-level granularity: a trajectory-based statistical approach, and a time-series based approach. Experimentation with one year data from a single camera demonstrates the ability to uncover interesting insights about the scene and to predict anomalies reasonably well.
Tasks	Object Detection, Time Series
Published	2017-12-20
URL	http://arxiv.org/abs/1712.07322v1
PDF	http://arxiv.org/pdf/1712.07322v1.pdf
PWC	https://paperswithcode.com/paper/lost-in-time-temporal-analytics-for-long-term
Repo
Framework