Whose story is it anyway? Automatic extraction of accounts from news articles     

Hao Zhang  Frank Boons  Riza Batista-Navarro 《Information processing & management》2019,56(5):1837-1848

Narratives are comprised of stories that provide insight into social processes. To facilitate the analysis of narratives in a more efficient manner, natural language processing (NLP) methods have been employed in order to automatically extract information from textual sources, e.g., newspaper articles. Existing work on automatic narrative extraction, however, has ignored the nested character of narratives. In this work, we argue that a narrative may contain multiple accounts given by different actors. Each individual account provides insight into the beliefs and desires underpinning an actor’s actions. We present a pipeline for automatically extracting accounts, consisting of NLP methods for: (1) named entity recognition, (2) event extraction, and (3) attribution extraction. Machine learning-based models for named entity recognition were trained based on a state-of-the-art neural network architecture for sequence labelling. For event extraction, we developed a hybrid approach combining the use of semantic role labelling tools, the FrameNet repository of semantic frames, and a lexicon of event nouns. Meanwhile, attribution extraction was addressed with the aid of a dependency parser and Levin’s verb classes. To facilitate the development and evaluation of these methods, we constructed a new corpus of news articles, in which named entities, events and attributions have been manually marked up following a novel annotation scheme that covers over 20 event types relating to socio-economic phenomena. Evaluation results show that relative to a baseline method underpinned solely by semantic role labelling tools, our event extraction approach optimises recall by 12.22–14.20 percentage points (reaching as high as 92.60% on one data set). Meanwhile, the use of Levin’s verb classes in attribution extraction obtains optimal performance in terms of F-score, outperforming a baseline method by 7.64–11.96 percentage points. Our proposed approach was applied on news articles focused on industrial regeneration cases. This facilitated the generation of accounts of events that are attributed to specific actors.  相似文献   

科研论文的著者合作模式研究综述     

王新明  丁敬达 《现代情报》2018,38(8):172-177

[目的/意义]研究科研论文的著者合作模式有助于发现科研合作中存在的合作关系以及评价不同合作模式的科研绩效,为进一步的科研合作提供方法和参考。[方法/过程]从作者属性和科研众包的视角对科研论文的著者合作模式的相关研究进行梳理和归纳。[结果/结论]基于作者的机构、地域、年龄、性别、职称、研究方向等属性和科研众包对科研论文的著者合作模式的研究进行归纳和论述,并提出未来可能的研究重点：著者合作模式综合视角下的科研绩效评价;作者贡献声明视角下的著者合作模式及合作规律研究。  相似文献   

Asynchronous event-triggered observation and control of linear systems via impulsive observers     

L. Etienne  Y. Khaled  S.Di Gennaro  J.P. Barbot 《Journal of The Franklin Institute》2017,354(1):372-391

In this paper we investigate the observation and stabilization problems of a linear plant subject to network constraints and partial state knowledge, making use of the event-triggered technique. In order to address these problems, an impulsive observer is designed. Sufficient conditions are given to ensure a milder version of separation principle for linear systems controlled via an event-triggered controller. The proposed observer ensures practical state estimation, while the corresponding dynamic controller ensures practical stabilization. The sampling and the transmission of the output and the input are done asynchronously. The dynamic controller is tested in simulation on the linearized inverted pendulum.  相似文献   

Consensus disturbance rejection for Lipschitz nonlinear multi-agent systems with input delay: A DOBC approach     

Chunyan Wang  Zongyu Zuo  Junyong Sun  Jun Yang  Zhengtao Ding 《Journal of The Franklin Institute》2017,354(1):298-315

In this paper, a new predictor-based consensus disturbance rejection method is proposed for high-order multi-agent systems with Lipschitz nonlinearity and input delay. First, a distributed disturbance observer for consensus control is developed for each agent to estimate the disturbance under the delay constraint. Based on the conventional predictor feedback approach, a non-ideal predictor based control scheme is constructed for each agent by utilizing the estimate of the disturbance and the prediction of the relative state information. Then, rigorous analysis is carried out to ensure that the extra terms associated with disturbances and nonlinear functions are properly considered. Sufficient conditions for the consensus of the multi-agent systems with disturbance rejection are derived based on the analysis in the framework of Lyapunov–Krasovskii functionals. A simulation example is included to demonstrate the performance of the proposed control scheme.  相似文献   

Decoupling and robust control of velocity-varying four-wheel steering vehicles with uncertainties via solving Attenuating Diagonal Decoupling problem     

Mingxing Li  Yingmin Jia 《Journal of The Franklin Institute》2017,354(1):105-122

This paper is devoted to solve the combined problem of input–output decoupling and robust control of the four-wheel steering vehicles. A more practical three-degree-of-freedom systems covering longitudinal, lateral and yaw motions are used to improve the safety and steerability while uncertainties and external disturbances are considered. A novel decoupling conception Attenuating Diagonal Decoupling and a new index Coupling Attenuation Index are introduced and the system is divided up into two systems with a special structure. The first system is caused by uncertainties and disturbances and the second system is a certain system coupling with the first one. A control scheme composed of a coupling attention controller and a decoupling controller are explored. The influences of the uncertainties and disturbances on the output are attenuated under the coupling index by the coupling attention controller designed for the first system while the input–output decoupling is achieved by employing the decoupling controller designed for the second system. Furthermore, we prove in theory that the input–output decoupling and robust control are both established for the closed-loop system of the control scheme and the primordial vehicle system. Besides these works, a switching law is introduced such that the above excellent performances are realizable in four-wheel steering vehicles with conventional steering interfaces. Simulations show that even with a large velocity varying range, the decoupling and robust performances are guaranteed simultaneously, i.e. the handling stability and steerability are improved.  相似文献   

An adaptive iterative learning algorithm for boundary control of a coupled ODE–PDE two-link rigid–flexible manipulator     

Fangfei Cao  Jinkun Liu 《Journal of The Franklin Institute》2017,354(1):277-297

To perform repetitive tasks, this paper proposes an adaptive boundary iterative learning control (ILC) scheme for a two-link rigid–flexible manipulator with parametric uncertainties. Using Hamilton?s principle, the coupled ordinary differential equation and partial differential equation (ODE–PDE) dynamic model of the system is established. In order to drive the joints to follow desired trajectory and eliminate deformation of flexible beam simultaneously, boundary control strategy is added based on the conventional joints torque control. The adaptive iterative learning algorithm for boundary control scheme includes a proportional-derivative (PD) feedback structure and an iterative term. This novel controller is designed to deal with the unmodeled dynamics and other unknown external disturbances. Numerical simulations are provided to verify the performance of proposed controller in MATLAB.  相似文献   

Optimal beamforming-selection spatial precoding using population-based stochastic optimization for massive wireless MIMO communication systems     

Ju-Hong Lee  Jing-Yen Lee 《Journal of The Franklin Institute》2017,354(10):4247-4272

The beamforming-based spatial precoding (BBSP) method has been proposed to reduce the overheads of the downlink training and the channel state information feedback in the frequency-division duplex (FDD) massive multiple-input-multiple-output (MIMO) wireless communication systems. However, the original BBSP method suffers from the interference problem at user equipments (UEs) because of using a set of pre-defined fixed beamforming coefficients. Moreover, the BBSP method can not deal with the performance degradation due to mutual coupling (MC) effect because of massive antennas deployed at transmitter and receiver. This paper presents a precoding method that incorporates a beamforming-selection spatial precoding (BSSP) scheme with a population-based stochastic optimization algorithm such that the designed beamforming coefficients can greatly reduce the severe interference between UEs and alleviate the MC effect on the performance of massive MIMO systems. The proposed method can not only achieve better bit error rate (BER) performance than the conventional BBSP method, but also preserves the advantages of the BBSP method having lower overheads of the downlink training and the CSI feedback. In particular, we propose an appropriate fitness function based on an averaged BER formula for the population-based stochastic optimization algorithm to find the optimal beamforming coefficients. Numerical simulations are also presented for both the urban-macro and the urban-micro wireless MIMO scenarios to validate the superior BER performance of the proposed precoding method as compared to the existing BBSP method.  相似文献   

Synchronization of coupled heterogeneous complex networks     

Zhengxin Wang  Guoping Jiang  Wenwu Yu  Wangli He  Jinde Cao  Min Xiao 《Journal of The Franklin Institute》2017,354(10):4102-4125

By only designing the internal coupling, quasi synchronization of heterogeneous complex networks coupled by N nonidentical Duffing-type oscillators without any external controller is investigated in this paper. To achieve quasi synchronization, the average of states of all nodes is designed as the virtual target. Heterogeneous complex networks with two kinds of nonlinear node dynamics are analyzed firstly. Some sufficient conditions on quasi synchronization are obtained without designing any external controller. Quasi synchronization means that the states of all nonidentical nodes will keep a bounded error with the virtual target. Then the heterogeneous complex network with impulsive coupling which means the network only has coupling at some discrete impulsive instants, is further discussed. Some sufficient conditions on heterogeneous complex network with impulsive coupling are derived. Based on these results, heterogeneous complex network can still reach quasi synchronization even if its nodes are only coupled at discrete impulsive instants. Finally, two examples are provided to verify the theoretical results.  相似文献   

Design of H2 (H∞)-based optimal structured and sparse static output feedback gains     

Ahmadreza Argha  Li Li  Steven W. Su 《Journal of The Franklin Institute》2017,354(10):4156-4178

  相似文献   

Adaptive fault-tolerant shape control for nonlinear Lipschitz stochastic distribution systems     

Gang Li  Qing Zhao 《Journal of The Franklin Institute》2017,354(10):4013-4033

This paper addresses the problem of adaptive fault estimation and fault-tolerant control for a class of nonlinear non-Gaussian stochastic systems subject to time-varying loss of control effectiveness faults. In this work, time-varying faults, Lipschitz nonlinear property and general stochastic characteristics are taken into consideration in a unified framework. Instead of using the system output signal, the output distribution is adopted for shape control. Both the states and faults are simultaneously estimated by an adaptive observer. Then, a fault tolerant shape controller is designed to compensate for the faults and realize stochastic output distribution tracking. Both the fault estimation and the fault tolerant control schemes are designed based on linear matrix inequality (LMI) technique. Satisfactory performance has been obtained for a numerical simulation example. Furthermore the proposed scheme is successfully tested in a case study of particle size distribution control for an emulsion polymerization reactor.  相似文献