语义网研究的基本问题

概述目前我国语义网的研究现状，在简要介绍语义网概念和模型的基础上，着重分析当前我国语义网的四大研究热点，即语义网描述语言比较研究、元数据研究、本体层开发研究和智能信息检索研究，并阐述语义网的发展对数字图书馆建设带来的若干启示。     

Analysis of Statistical Question Classification for Fact-Based Questions

Question classification systems play an important role in question answering systems and can be used in a wide range of other domains. The goal of question classification is to accurately assign labels to questions based on expected answer type. Most approaches in the past have relied on matching questions against hand-crafted rules. However, rules require laborious effort to create and often suffer from being too specific. Statistical question classification methods overcome these issues by employing machine learning techniques. We empirically show that a statistical approach is robust and achieves good performance on three diverse data sets with little or no hand tuning. Furthermore, we examine the role different syntactic and semantic features have on performance. We find that semantic features tend to increase performance more than purely syntactic features. Finally, we analyze common causes of misclassification error and provide insight into ways they may be overcome.     

基于词向量扩展的学术资源语义检索技术

[目的/意义] 尝试以统计的方法为指导思想,探究基于词向量扩展的语义检索技术来提升学术资源的语义检索能力。[方法/过程] 利用自然语言处理、文本挖掘技术,对采集来的学术资源（主要是学术论文）元数据进行预处理,结合word2vec词向量生成工具和elasticsearch全文检索引擎搭建语义检索系统,对学术资源进行语义检索的探索研究。[结果/结论] 本文提出的方法能够有效提升学术信息的检索效果,一定程度上实现学术资源的语义检索,并为后续语义检索的进一步研究提供借鉴。     

基于SKOS的学术期刊文本资源多粒度语义标注方法研究

[目的/意义] 针对学术期刊文本资源语义标注仍存在的通用本体难以构建、标注粒度单一两大问题,提出基于SKOS的学术期刊多粒度语义标注方法,从而进一步推进语义标注的应用发展,更好满足用户的多粒度学术信息需求。[方法/过程] 在对《中国汉语主题词表》进行SKOS描述的基础上,以学术期刊文本资源为对象,实现其多粒度语义标注,并通过实证研究验证该方法的可行性。[结果/结论] 利用SKOS实现对学术期刊文本资源进行多粒度语义标注,较之当前学术检索系统中的标注结果,在"查全"查准"内部特征检索入口"检索结果反馈形式"4个方面具有一定优势。     

网络舆情场中信息受众观点测度的机理及路径分析

[目的/意义]整合定性与定量的舆情研究视角,统一多模态研究对象,实现网络舆情信息受众的观点测度,可修复网络舆情分析与治理的理论与实践裂痕。[方法/过程]通过引入网络舆情场的概念,对网络舆情信息受众、受众观点测度的内涵进行诠释,就网络舆情场与信息受众观点测度的逻辑关系加以辩证讨论。[结果/结论]提出网络舆情场内舆情受众观点测度机理和具体测度路径,为后续网络舆情场中的网络舆情信息分析、多维度信息受众观点测度,受众认知规律发现,网络舆情监督和管控限制等层面的研究做相应铺垫。     

Spatial Discovery of Linked Research Datasets and Documents at a Spatially Enabled Research Library

Current publishing practices in academia tend to result in datasets that are difficult to discover. This is because datasets are not well-integrated across academic domains and they are often not linked to the documents that reference them. For these reasons, discovering datasets across domains can be challenging; for example, discovering archeological observations and biological specimens using the same search is not widely supported, even if both datasets share a similar spatial extent, like Mesoamerica. It is also challenging to retrieve relevant documents that reference datasets; for example, retrieving a series of field reports that reference archeological observations is typically not supported. Our work develops an extensible method for: (1) geographically integrating collections across disciplinary repositories and (2) connecting datasets to related documents. We describe a collection of spatially-referenced researcher datasets, capturing their metadata elements and encoding them as linked open data. We then leverage existing library services to formalize links from datasets to documents. The system described in this work has been deployed, resulting in an experimental open data site for the UCSB campus. Results indicate that this system can be scaled-up with support from an institutional repository in the near future.     

中文电子病历的分词及实体识别研究

[目的/意义]健康医疗大数据是我国重要的基础性战略资源，本研究对中文电子病历分词与实体识别的探讨与实证较好地完成了医疗数据的信息抽取任务，对今后医疗大数据在语义层面的应用发展具有重要意义。[方法/过程]本研究首先融合权威词表、官方标准、健康网站数据及其他医学补充词库构建了词语数量级达到10万的医学词表；然后对电子病历的字段进行分词，对比了jieba工具、导入词典后的jieba、无监督学习及AC自动机4种模型的分词效果；最后，以自动分词和人工标注结果为语料，实现基于条件随机场的电子病历实体识别研究，并比较不同实体类别以及不同文本特征下的实体识别效果，选出最优模板。[结果/结论]分词结果显示，AC自动机的效果最好，F值可达82%；实体识别结果表明，"检查"和"疾病"实体的识别效果最好，而"症状"的识别效果不太理想。     

基于野外测量生成GIS数据方法分析

地理信息系统的核心,就是获取数据。搜集精准数据,才能描画完备的测量图。为满足测量需求,应不断深入解析,提供实时特性的精准数据。获取的GIS数据,被用在野外范畴的测量之中。确认数据生成特有的路径,提升GIS测定的精准性,便利后续的导入数据。     

控制系统中相关性能指标之间关系分析

本文比较详尽地推导和分析了二阶控制系统频域指标谐振频率及频宽与时域指标之间的关系，即ωr与ξ的关系、ωr与Mr的关系、ωb与ξ的关系、ωb与Mr的关系，并编写了MATLAB程序，画出了关系曲线；从而对分析和设计控制系统带来了极大的方便。