基于双语主题和因子图模型的汉语-越南语双语事件关联分析

随着“一带一路”国家战略实施,我国与越南的交流与合作日益密切,及时掌握两国新闻事件动态意义重大。该文针对汉越双语新闻事件关联分析所面临的跨语言关联问题,研究汉越双语新闻事件关联分析方法。汉越双语新闻事件分析其实质是多语言多文本的理解问题。其主要难点是要解决多语言多文本下的新闻事件理解问题。该文提出了基于因子图模型的局部密切度传播算法。首先使用双语主题概率模型,从双语文档中获得双语主题及主题概率分布,然后基于新闻事件的文本相似度构建事件因子图模型,在因子图上对相互关联的事件使用局部密切度传播算法计算某一主题下所有相互关联的事件间的影响力。最后得到不同主题下事件间的影响力拓扑图。实验结果表明该方法相比相似度计算和词语共现的方法取得了不错效果。     

面向CPS复杂事件流的不确定性研究

信息物理融合系统CPS获得广泛应用需要解决的一个关键问题是软件中的信息处理部分,而复杂事件处理是CPS中信息处理的核心任务之一。CPS环境下的事件具有异构、分散、海量和不确定性等特征。在CPS实际应用中,因噪声、传感器误差、通讯技术等原因而造成的事件不确定性急需解决。为了解决CPS系统中存在的海量不确定事件流问题,提出一种处理不确定事件流的复杂事件处理方法USCEP,该方法不仅可以实时有效地处理海量不确定事件流,还可以有效计算复杂事件的概率。USCEP对现有RFID复杂事件监测方法 RCEDA进行了改进,提供了历史概率事件查询处理的支持,提出一种事件概率模型进行概率计算,并通过关联查询表来提高效率。实验表明,在处理不确定事件流时,该方法比传统方法具有更好的性能。     

基于实体画像增强网络的事件检测方法

事件检测任务旨在从非结构化的文本中自动识别并分类事件触发词。挖掘和表示实体的属性特征(即实体画像)有助于事件检测,其基本原理在于“实体本身的属性往往暗示了其参与的事件类型”(例如,“警察”往往参与“Arrest-Jail”类的事件)。现有研究已利用编码信息实现实体表示,并借此优化事件检测模型。然而,其表示学习过程仅仅纳入局部的句子级语境信息,使得实体画像的信息覆盖率偏低。为此,该文提出基于全局信息和实体交互信息的画像增强方法,其借助图注意力神经网络,不仅在文档级的语境范围内捕捉实体的高注意力背景信息,也同时纳入了局部相关实体的交互信息。特别地,该文开发了基于共现图的注意力遮蔽模型,用于降低噪声信息对实体表示学习过程的干扰。在此基础上,该文联合上述实体画像增强网络、BERT语义编码网络和GAT聚合网络,形成了总体的事件检测模型。该文在通用数据集ACE 2005上进行实验,结果表明实体画像增强方法能够进一步优化事件检测的性能,在触发词分类任务上的F₁值达到76.2%,较基线模型提升了2.2%。     

基于四元数门控图神经网络的脚本事件预测

脚本事件预测需要考虑两类信息来源:事件间的关联与事件内的交互。针对于事件间的关联,采用门控图神经网络对其进行建模。而对于事件内的交互,采用四元数对事件进行表征,接着通过四元数的哈密顿乘积来捕捉事件4个组成部分之间的交互。提出结合四元数和门控图神经网络来学习事件表示,它既考虑了外部事件图的交互作用,又考虑了事件内部的依赖关系。得到事件表示后,利用注意机制学习上下文事件表示和每个候选上下文表示的相对权值。然后通过权重计算上下文事件表示的和,再计算其与候选事件表示的欧氏距离。最后选择距离最小的候选事件作为正确的候选事件。在纽约时报语库上进行了实验,结果表明,通过多项选择叙事完形填空评价,本文的模型优于现有的基线模型     

基于ESU图的活动社交网络用户参加活动推荐

活动社交网络(EBSNs)为用户提供了方便的组织、参加和分享社交活动的平台。该文面向EBSNs活动推荐问题,提出了包含活动(Event)、主办方(Sponsor)和用户(User)的ESU图模型,深入揭示了EBSNs的实体及其社交关系。因为用户参加活动受多个因素影响,我们提出了基于ESU图的活动推荐多因素决策模型,包括社交影响力、活动内容、活动地点及活动时间。根据ESU图特点,提出了基于双向重启随机游走算法BD-RWR的实体重要度计算方法。选取真实的EBSNs平台—豆瓣同城验证所提方法的有效性。实验结果表明,该文提出的ESU图模型及融合了多因素的活动推荐模型,与已有最新方法相比,有效地提升了用户参加活动的推荐效果。     

Specifying and enforcing high-level semantic obligation policies

Obligation policies specify management actions that must be performed when a particular kind of event occurs and certain conditions are satisfied. Large scale distributed systems often produce event streams containing large volumes of low-level events. In many cases, these streams also contain multimedia data (consisting of text, audio or video). Hence, a key challenge is to allow policy writers to specify obligation policies based on high-level events, that may be derived after performing appropriate processing on raw, low-level events. In this paper, we propose a semantic obligation policy specification language called Eagle, which is based on patterns of high-level events, represented as RDF graph patterns. Our policy enforcement architecture uses a compiler that builds a workflow for producing a stream of events, which match the high-level event pattern specified in a policy. This workflow consists of a number of event sources and event processing components, which are described semantically. We present the policy language and enforcement architecture in this paper.     

Temporal event searches based on event maps and relationships

To satisfy a user’s need to find and understand the whole picture of an event effectively and efficiently, in this paper we formalize the problem of temporal event searches and propose a framework of event relationship analysis for search events based on user queries. We define three kinds of event relationships: temporal, content dependence, and event reference, that can be used to identify to what extent a component event is dependent on another in the evolution of a target event (i.e., the query event). The search results are organized as a temporal event map (TEM) that serves as the whole picture about an event’s evolution or development by showing the dependence relationships among events. Based on the event relationships in the TEM, we further propose a method to measure the degrees of importance of events, so as to discover the important component events for a query, as well as the several algebraic operators involved in the TEM, that allow users to view the target event. Experiments conducted on a real data set show that our method outperforms the baseline method Event Evolution Graph (EEG), and it can help discover certain new relationships missed by previous methods and even by human annotators.     

基于事件元素无向图的查询扩展方法

借助新闻事件元素之间的关联特性,提出了基于事件元素无向图的查询扩展方法,利用新闻事件元素之间的关联关系进行查询扩展提升新闻事件检索效果。首先分析候选事件文档与查询项的关系,确定待扩展的元素;然后利用事件元素之间的关联关系构建无向图,通过事件向量空间计算边的权重;最后,利用无向图节点权重模型计算事件元素权重,依据权重进行事件元素扩展。在新闻事件查询扩展方面进行了对比试验,结果表明该文提出的查询扩展方法取得了较好的效果。     

Discovering Event Evolution Graphs From News Corpora

Given the advance of Internet technologies, we can now easily extract hundreds or thousands of news stories of any ongoing incidents from newswires such as CNN.com, but the volume of information is too large for us to capture the blueprint. Information retrieval techniques such as topic detection and tracking are able to organize news stories as events, in a flat hierarchical structure, within a topic. However, they are incapable of presenting the complex evolution relationships between the events. We are interested to learn not only what the major events are but also how they develop within the topic. It is beneficial to identify the seminal events, the intermediary and ending events, and the evolution of these events. In this paper, we propose to utilize the event timestamp, event content similarity, temporal proximity, and document distributional proximity to model the event evolution relationships between events in an incident. An event evolution graph is constructed to present the underlying structure of events for efficient browsing and extracting of information. Case study and experiments are presented to illustrate and show the performance of our proposed technique. It is found that our proposed technique outperforms the baseline technique and other comparable techniques in previous work.     

基于概率超图的视频事件语义检测

视频事件类别的归属具有模糊性和不确定性,将超图的点边射入矩阵拓展成概率形式的软超图进行关联关系分析和语义分析,将会更有利于提高多事件检索检测的精准率和召回率。提出基于概率超图模型的视频事件语义检测算法（PHVESD）。 该方法首先将颜色、灰度共生矩阵、Tchebichef矩、局部二值模式（LBP）等四种底层视觉特征进行融合; 然后定义视频段的亲密度函数并利用亲密度的信息构建概率超图模型,其中每条超边对应一种事件语义;采用随机游走过程来预测视频段属于每条超边的概率;最后结合阈值采用条件概率模型对视频段进行事件语义分类。将该方法用于交通突发事件多语义检测中并与其他的识别算法相比较,实验结果表明,与基于超图模型的多标签随机游走算法（MLRW）相比,PHVESD的算法使多语义事件检测的准确率提高了10%,召回率提高了8%。     

基于字词联合表示的中文事件检测方法

事件检测作为事件抽取的一个子任务,是当前信息抽取的研究热点之一。它在构建知识图谱、问答系统的意图识别和阅读理解等应用中有着重要的作用。与英文字母不同,中文中的字在很多场合作为单字词具有特定的语义信息,且中文词语内部也存在特定的结构形式。根据中文的这一特点,文中提出了一种基于字词联合表示的图卷积模型JRCW-GCN(Joint Representation of Characters and Words by Graph Convolution Neural Network),用于中文事件检测。JRCW-GCN首先通过最新的BERT预训练语言模型以及Transformer模型分别编码字和词的语义信息,然后利用词和字之间的关系构建对应的边,最后使用图卷积模型同时融合字词级别的语义信息进行事件句中触发词的检测。在ACE2005中文语料库上的实验结果表明,JRCW-GCN的性能明显优于目前性能最好的基准模型。     

Event detection over twitter social media streams

In recent years, microblogs have become an important source for reporting real-world events. A real-world occurrence reported in microblogs is also called a social event. Social events may hold critical materials that describe the situations during a crisis. In real applications, such as crisis management and decision making, monitoring the critical events over social streams will enable watch officers to analyze a whole situation that is a composite event, and make the right decision based on the detailed contexts such as what is happening, where an event is happening, and who are involved. Although there has been significant research effort on detecting a target event in social networks based on a single source, in crisis, we often want to analyze the composite events contributed by different social users. So far, the problem of integrating ambiguous views from different users is not well investigated. To address this issue, we propose a novel framework to detect composite social events over streams, which fully exploits the information of social data over multiple dimensions. Specifically, we first propose a graphical model called location-time constrained topic (LTT) to capture the content, time, and location of social messages. Using LTT, a social message is represented as a probability distribution over a set of topics by inference, and the similarity between two messages is measured by the distance between their distributions. Then, the events are identified by conducting efficient similarity joins over social media streams. To accelerate the similarity join, we also propose a variable dimensional extendible hash over social streams. We have conducted extensive experiments to prove the high effectiveness and efficiency of the proposed approach.     

基于句法语义依存分析的中文金融事件抽取

事件抽取在自然语言处理应用中扮演着重要的角色,如股票市场趋势预测.传统事件抽取较为关注触发词和论元所属类型的正确性,较少地结合应用需求去分析研究事件抽取效果及使用价值.在财经领域,事件作用对象及动作是关注的重点.因此,本文聚焦于金融事件,抽取三元组事件ET(Sub,Pred,Obj).在中文财经新闻中,存在大量事件嵌套...     

Detection and removal of infrequent behavior from event streams of business processes

Process mining aims at gaining insights into business processes by analyzing the event data that is generated and recorded during process execution. The vast majority of existing process mining techniques works offline, i.e. using static, historical data, stored in event logs. Recently, the notion of online process mining has emerged, in which techniques are applied on live event streams, i.e. as the process executions unfold. Analyzing event streams allows us to gain instant insights into business processes. However, most online process mining techniques assume the input stream to be completely free of noise and other anomalous behavior. Hence, applying these techniques to real data leads to results of inferior quality. In this paper, we propose an event processor that enables us to filter out infrequent behavior from live event streams. Our experiments show that we are able to effectively filter out events from the input stream and, as such, improve online process mining results.     

面向政治领域的事理图谱构建

事理图谱是一种描述事件之间顺承、因果等关系的事理演化逻辑有向图,它蕴含了丰富的事件间关系,在各领域都具有重要的研究意义和应用价值。当前研究主要集中于公开域的事件抽取上,而在特定领域,如政治领域,因其事件类型和事件内容较为复杂,相关研究十分有限。该文旨在构建面向政治领域的事理图谱,针对政治事件抽取中存在的语料匮乏、标准缺失等问题,制定了一套面向政治领域的事件分类标准,构建了一套政治领域的事件语料库。同时,该文分别提出了一种融合注意力机制的字嵌入修正神经网络的Pipeline模型和一种基于BERT+BiLSTM的Joint模型进行事件触发词和论元抽取,并在该语料库上进行实验。实验结果表明,两种模型在事件触发词与论元抽取任务中,F₁指标较基线模型均有较大提升。     

一种基于形式概念分析的事件演化分析算法

针对传统基于内容相似度的事件关系计算方法不能分析出事件间的潜在关系的问题,提出了基于FCA的事件关系计算方法。该方法利用根据话题的三层结构模型,对话题中的事件进行属性提取,并依据特征频率因子进行属性选择。利用两个事件之间的属性关系建立形式背景,以此为基础形成概念格。用基于概念格的相似度分析发现事件之间潜在。实验证明了这种方法的有效性。     

基于事理知识图谱的舆情推演方法

一直以来舆情态势发展的多元性、复杂性使其难以有效管控,一些负面舆情会激化矛盾,给社会安定带来不利影响.提出了一种基于事理知识图谱的舆情事件推演方法,通过神经网络挖掘事件因果逻辑,连接因果事件构成事理知识图谱.向量化事件节点以融合归并相似节点降低图谱冗余,增强图谱泛化性.根据事理知识图谱反映的发展逻辑对目标舆情事件的演化趋势进行预测.以自然灾害舆情事件为例,实验结果表明提出的方法能够有效预测舆情事件发展方向,可以为舆情监管提供一定支持.     

基于连续聚类与组合分类的RFID事件探测

RFID数据流随着时间而不断变化,捕捉其中蕴含的变化可以用于检测有意义事件的发生.提出了一种捕获数据流事件的算法--CECD,通过分析聚类结果分布变化和值域中产生的偏差检测数据流中蕴含的变化,同时采用组合分类技术对变化进行分类,捕获观察到的事件或现象的特性,建立事件与响应的映射关系.实验证明提出的框架可以高效检测数据流上的变化,与不借助变化检测的单纯基于规则的事件检测方法相比可以更准确地捕获事件.     

面向海量新闻简报的事件演变轨迹构建方法

在故事森林模型基础上提出了事件演变轨迹模型。对比故事森林模型,事件演变轨迹模型具备在涵盖不同主题和包含大量冗余信息的海量新闻简报中准确、快速提取热点事件的能力。同时,在分析和理解上下文语义的基础上,以实时在线的方式描述事件的演变过程,在不破坏已有演变结构的基础上,确保用户的浏览体验。基于32 GB的中文新闻简报数据对模型进行了评估和试点用户体验研究。结果表明,事件演变轨迹在准确识别热点事件并将新闻简报组织成符合读者阅读逻辑方面具有更强的能力。     

音乐领域典型事件抽取方法研究

事件抽取是信息抽取领域一个重要的研究方向。该文从音乐领域的事件抽取出发,通过领域事件词聚类的方法自动发现音乐领域具有代表性的事件,然后采用基于关键词与触发词相结合的过滤方法简化了事件类型的识别过程。在事件元素识别中,该文采用了基于最大熵的事件元素识别方法。在该文构建的语料库下,最终事件类型识别的平均F值达到82.82%,事件元素识别的平均F值达到75.79%。