一种创建事件模式的新方法

信息抽取系统中,通常需要创建大量的模式,因此创建模式是信息抽取系统中的一个关键问题.文中对创建事件模式,提出了一种新方法--根据格语法变换创建事件模式.通过对一类动词(含有施事格、受事格、时间格、处所格)的变换方法的研究,给出了这种变换方法的形式化描述,从而为抽取句子层事件提出了一个通用的方法,并且该方法是与领域无关的.通过一个信息抽取系统实例,验证了该方法是可行的、有效的.     

一种基于角色匹配的事件抽取方法

事件抽取是信息抽取领域一个重要的研究方向,事件抽取模式的定义和获取是其中的一个关键问题。提出了一种基于动词论元结构层次模型,将事件元素与动词的语义角色相对应,在实体、词性、关键词层次对事件元素进行语义约束的事件抽取模式定义方法。另外,为减轻模式建设的代价,提出了一种从标注语料中自动归纳事件抽取模式的方法。在此基础上,以发布事件为实例构建了实验系统,实验结果表明该方法的F指数达到71.7%。     

面向文本的事件信息抽取方法的研究

研究面向文本的事件信息抽取工作,建立一个事件信息抽取系统。该系统首先过滤包含关键字的原始语料;然后采用层次聚类(Hierarchical,HCL)和最长公共子序列算法相结合的方法抽取事件信息,得到最初的模式;最后通过是否包含关键字进行模式获取,进而提取信息,最终得到事件要素。     

基于事件框架的信息抽取系统

信息抽取技术能够提供高质量的检索服务。本文提出一种基于框架的信息抽取模式并建立统一的灾难性事件框架,利用框架的继承-归纳特性简化系统实现过程,概括事件信息,并提出按时间流顺序的线索性文件抽取的输出方式。本文使用这种方法建立了一个灾难性事件信息抽取系统。实验证明本文中的方法是有效的。     

用规则抽取句子中事件信息

信息抽取是数据挖掘的重要课题.目前的研究主要通过机器学习的方法对信息进行抽取.但是机器学习对训练数据的质量要求高,学习过程中参数设置复杂.而利用事先构建好的规则可以简单有效的从文本中提取事件信息.提出一种基于抽取规则对句子中的事件信息进行抽取的方法,摆脱了繁杂的机器学习过程.该方法利用本体对动词与事件角色匹配规则、事件角色抽取规则、时间信息抽取规则和地点信息抽取规则进行定义,用OWL对这些抽取规则进行了描述,然后应用这些规则抽取句子中的动词词义信息、事件角色信息、时间信息和地点信息,并用本文提出的一种新评测指标对事件信息进行评测.实验表明该方法从句子中抽取事件信息是有效的.     

基于介词用法的事件信息抽取研究

事件信息抽取是目前信息抽取领域的主要研究方向,为了提高事件信息抽取的准确率,提出一种基于介词用法的事件信息抽取方法.通过对介词用法的研究,掌握了不同介词用法在语言结构中的不同作用,以介词用法信息为背景,完成抽取规则编写.针对规则,完成抽取系统的编写,以达到理想的抽取结果.采用郑州大学提供的语料,通过大量实验,结果准确率、召回率及F值分别达到90.88％、86.92％、88.86％,表明了该方法的有效性.     

基于自扩展的信息抽取模式自动获取

提出一种从未标注的中文文本中基于自扩展策略自动获取事件抽取模式的算法,该算法从少数几个种子抽取模式开始,通过一个增量迭代的过程发现新的抽取模式,在每一轮迭代中采用类似于TF/IDF的评估方法对产生的候选模式进行排序,选择最优的模式并入当前模式集.应用该方法从人民日报语料中自动获取"职务变动"类事件的抽取模式,实验结果表明,该方法产生的抽取模式在中文文本事件抽取中具有较好的抽取性能,综合指标F值达到66 3%.     

基于词汇语义模式的金融事件信息抽取方法

信息抽取是自然语言处理工作中的重要任务之一。针对由于自然语言的多样性、歧义性和结构性而导致的信息抽取困难的问题,提出了一种面向金融事件信息抽取的层次化词汇-语义模式方法。首先,定义了一个金融事件表示模型;然后应用基于深度学习的词向量方法来实现自动生成同义概念词典;最后采用基于有限状态机驱动的层次化词汇-语义规则模式实现了对各类金融事件信息自动抽取的目标。实验结果表明,所提方法可以从金融新闻文本中准确地抽取出各类金融事件信息,并且对26类金融事件的微平均识别准确率达到93.9%,微平均召回率达到86.9%,微平均F1值达到90.3%。     

一种面向公安警情领域的事件抽取方法

公安警情领域存在大量警情文本数据,如何从不同源、不同格式的警情文本中抽取出案情相关信息是公安情报信息处理工作的一个重要内容。基于公安警情领域数据特点,该文提出了一种结合无触发词事件识别和基于阅读理解的事件论元角色分类的事件抽取方法。该方法首先采用无触发词方法实现事件识别;在事件识别结果的基础上,通过阅读理解方式实现对事件论元角色的分类。实验表明,该文提出的方法在不标注触发词情况下在警情领域数据中能更好地实现事件信息抽取。     

基于依存句法分析与分类器融合的触发词抽取方法

事件检测与分类是事件抽取的关键环节,触发词抽取是完成事件检测与分类的主流方法。提出了一种事件触发词抽取方法,该方法针对单一触发词抽取方法没有充分利用依存句法分析信息且召回率不高的问题,通过综合利用依存句法分析信息和其他信息抽取触发词-实体描述对的方法来提高触发词抽取的召回率,然后将触发词-实体描述对抽取结果与单一触发词抽取结果相融合以避免召回率提高所带来的准确率下降问题。在ACE2005中文语料上进行实验,该方法在事件检测与分类任务中取得较好效果,F值分别达到了69.0%和66.2%。     

基于规则归纳的信息抽取系统实现

面对Web信息的迅猛增长,信息抽取技术非常适合于从大量的文档中抽取需要的事实数据。通过文档对象模型（DOM）解析以及检索、抽取、映射等规则的定义,设计并实现了一种具有规则归纳能力的信息抽取系统,用于Web信息的自动检索。在用于抽取规则归纳的框架下,还重点对用于生成抽取模式的WHISK学习算法进行了实验对比分析,结果表明系统对于单槽和多槽数据都具有不错的归纳学习能力。     

纺织花型准备系统

这篇论文介绍一个智能花型准备系统,简介它的硬件配置,该系统既可用于提花又可用于 印花织物的花型准备,它的花型设计特点是:对输入图案素材进行轮廓抽取,等倾压缩存入 素材库,按某一数学模型采用随机定变方法自动创作图案,创作好的图案经过计算机作工艺处 理后输出,以加工花型载体.     

网页病毒防御系统的设计

随着网络的发展,作为用户与网络交互的一个平台,IE的应用已经非常广泛。而基于IE传播的网页病毒已经成为影响网络安全的主要问题之一。首先介绍了基于IE传播的网页病毒的特点,并与其他木马病毒的传播模式进行了比较;然后提出了一种针对网页病毒的防御系统设计,并将免疫防护的思想应用到病毒检测系统中,该防御系统的设计对未来的网页病毒防御具有一定的参考价值;最后对将来需要进一步研究的工作提出了一些建议和设想。     

3D IEM formulation with an IEM/FEM coupling scheme for solving elastostatic problems

In this paper, a detailed three-dimensional infinite element methodology (IEM) formulation with an infinite element (IE)–finite element (FE) coupling scheme for investigating elastostatic problems is presented. This method is equally well suited for a regular perfect domain and a domain with geometric singularity; for example, domains with cracks. In this method, the primary problem domain is subdivided into two sub-domains modeled separately using IEM and finite element method (FEM), respectively. All degrees of freedom related to the IE sub-domain, except for those associated with the coupling interface, are condensed and transformed to form a finite master IE with the master nodes on the sub-domain boundary. Finally, a symmetrical IE stiffness matrix containing only master node degrees of freedom is assembled into the system stiffness matrix for the FE sub-domain. A very fine mesh pattern can be established using these efficient numerical techniques without increasing the d.o.f.'s of the global FEM solution. Numerical examples are presented and compared with the corresponding analytical or numerical solutions to show the performance of the proposed methodology.     

一种跨语句汉语事件信息抽取方法

提出了一种“知网”支持下的跨语句汉语事件信息抽取(1E)方法。该方法的基本思想是：从经过标注的描述某类事件的一个事件实例集合中,学习出事件的各个角色的特征义原集合和角色所属的语义类集合。然后,对于一个新的该类事件的实例句群,使用每个角色的特征义原集合来定位角色所在的单句,并通过该角色所属的语义类集合从定位后的单句中进行该角色的识别和抽取。实验表明,该方法能够完成从不同领域中对不同类别汉语事件的IE任务,并得到较高的抽全率和抽准率。     

On the design of more secure software-intensive systems by use of attack patterns

Retrofitting security implementations to a released software-intensive system or to a system under development may require significant architectural or coding changes. These late changes can be difficult and more costly than if performed early in the software process. We have created regular expression-based attack patterns that show the sequential events that occur during an attack. By performing a Security Analysis for Existing Threats (SAFE-T), software engineers can match the symbols of a regular expression to their system design. An architectural analysis that identifies security vulnerabilities early in the software process can prepare software engineers for which security implementations are necessary when coding starts. A case study involving students in an upper-level undergraduate security course suggests that SAFE-T can be performed by relatively inexperienced engineers who are not experts in security. Data from the case study also suggest that the attack patterns do not restrict themselves to vulnerabilities in specific environments.     

A Fuzzy Logic intelligent agent for Information Extraction: Introducing a new Fuzzy Logic-based term weighting scheme

In this paper, we propose a novel method for Information Extraction (IE) in a set of knowledge in order to answer to user consultations using natural language. The system is based on a Fuzzy Logic engine, which takes advantage of its flexibility for managing sets of accumulated knowledge. These sets may be built in hierarchic levels by a tree structure. The aim of this system is to design and implement an intelligent agent to manage any set of knowledge where information is abundant, vague or imprecise. The method was applied to the case of a major university web portal, University of Seville web portal, which contains a huge amount of information. Besides, we also propose a novel method for term weighting (TW). This method also is based on Fuzzy Logic, and replaces the classical TF-IDF method, usually used for TW, for its flexibility.     

信息抽取模式自动生成方法的研究

模式匹配是信息抽取系统通常使用的方法,如何生成信息抽取模式就成为信息抽取的关键问题。由于手工编写模式的代价太大,本文尝试采用聚类方法自动生成针对中文文本的信息抽取模式。通过计算模式实例间的相似度,采用单链法聚类,将模式实例划分为不同的类别,每个类别对应一个模式,将同一类别中的模式实例进行合并就可以得到最终的信息抽取模式。以农作物信息文本为实验语料,进行了聚类测试,错分率与漏分率分别为0.21%和1.07%,合并后的模式覆盖了人工分析提出的25类中的24类。     

Automatic generation of instructional hypermedia with APHID

This research investigates the use of patterns in designing adaptable, flexible hypermedia applications. While patterns are particularly applicable to software design, they can also be used to assist designers of other types of applications. We have developed a method (APHID) that guides a hypermedia creator through the analysis and design process. The method ensures that good design principles are followed, both for the hypermedia application and for the interface that presents the hypermedia application. Our method uses a concept map, constraints, and patterns (instructional and presentation) to support partial automation for creating hypermedia applications. We also present a prototype software system that uses the APHID method to create instructional hypermedia applications semi-automatically. The applications created using APHID are tailored to specific types of learners. We conclude with a claim that this approach is applicable not just to instructional hypermedia, but to the larger problem of generating adaptable interfaces.     

Cellular ants: A method to create collision free trajectories for a cooperative robot team

Creating collision-free trajectories for mobile robots, known as the path planning problem, is considered to be one of the basic problems in robotics. In case of multiple robotic systems, the complexity of such systems increases proportionally with the number of robots, due to the fact that all robots must act as one unit to complete one composite task, such as retaining a specific formation. The proposed path planner employs a combination of Cellular Automata (CA) and Ant Colony Optimization (ACO) techniques in order to create collision-free trajectories for every robot of a team while their formation is kept immutable. The method reacts with obstacle distribution changes and therefore can be used in dynamical or unknown environments, without the need of a priori knowledge of the space. The team is divided into subgroups and all the desired pathways are created with the combined use of a CA path planner and an ACO algorithm. In case of lack of pheromones, paths are created using the CA path planner. Compared to other methods, the proposed method can create accurate collision-free paths in real time with low complexity while the implemented system is completely autonomous. A simulation environment was created to test the effectiveness of the applied CA rules and ACO principles. Moreover, the proposed method was implemented in a system using a real world simulation environment, called Webots. The CA and ACO combined algorithm was applied to a team of multiple simulated robots without the interference of a central control. Simulation and experimental results indicate that accurate collision free paths could be created with low complexity, confirming the robustness of the method.