基于领域本体和语块分析的信息抽取的研究与实现

为了提高信息抽取过程中的语义深层次的理解和准确率,本文提出了一种基于领域本体和语块分析的语义信息抽取方法,在详细说明其信息抽取模型的基础上,重点针对命名实体识别、词性组合模板、基于本体的三元组和二元组规则等关键问题进行了深入的分析和研究,提出了相应的解决方法,并进行了相关试验性研究.结果表明:采用本文所述的系统结构及其技术构建文本信息抽取系统是可行的,其能在深层次语义理解的基础上进一步提高信息抽取的准确率.     

企业竞争弱信号的特征提取与定量识别研究

[目的/意义] 针对当前对企业弱信号定量研究不足的现状,通过层次分析和隶属度函数构建新方法对其进行定量识别,为企业战略决策管理和危机预警提供服务。[方法/过程] 首先,基于波特的五力模型构建七力模型,结合实证分析提取企业竞争弱信号的特征;其次,结合层次分析法构建影响因素指标体系,并计算各指标的具体权重;最后,结合隶属度函数对弱信号进行定量识别。[结果/结论] 通过层次分析法和隶属度函数,构建了企业竞争弱信号的定量识别方法,为企业战略决策管理和危机管理提供服务。     

试论分句法与合句法中"句"的概念

到底汉语中“句“的概念是如何界定的?英语句子和汉语句子在划分上有何区别?对上述两个问题的回答和理解是否影响到英汉互译的实践?本文尝试为上述问题提供答案,旨在进一步加深对“句“这一英语和汉语共有的语言表达形式的理解,并以期服务于英汉翻译实践。     

基于机器学习的Web链接的抽取

互联网网页是通过超链接连接起来的,为人们的日常生活和商务用途提供了非常丰富的信息资源。链接结构分析在万维网的很多研究领域发挥着越来越重要的作用。然而存在着许多与主题无关的链接,造成了主题漂移。本文分析了链接本身的特点,介绍了一种有监督机器学习方法自动地抽取网页中的相关链接。试验结果表明该算法具有实用的价值。     

Extraction of novel features for emotion recognition

Hilbert-Huang transform method has been widely utilized from its inception because of the superiority in varieties of areas. The Hilbert spectrum thus obtained is able to reflect the distribution of the signal energy in a number of scales accurately. In this paper, a novel feature called ECC is proposed via feature extraction of the Hilbert energy spectrum which describes the distribution of the instantaneous energy. The experimental results conspicuously demonstrate that ECC outperforms the traditional short-term average energy. Combination of the ECC with mel frequency cepstral coefficients (MFCC) delineates the distribution of energy in the time domain and frequency domain, and the features of this group achieve a better recognition effect compared with the feature combination of the short-term average energy, pitch and MFCC. Afterwards, further improvements of ECC are developed. TECC is gained by combining ECC with the teager energy operator, and EFCC is obtained by introducing the instantaneous frequency to the energy. In the experiments, seven status of emotion are selected to be recognized and the highest recognition rate 83.57% is achieved within the classification accuracy of boredom reaching 100%. The numerical results indicate that the proposed features ECC, TECC and EFCC can improve the performance of speech emotion recognition substantially.     

超临界二氧化碳在日用化工中的应用

介绍了超临界流体的特性、萃取原理，超临界二氧化碳作为SFE溶剂萃取精油、油脂和色素及作为化学反应介质在日用化工中的应用。     

"有没有VP"与"VP没有"的比较研究

一种新句式叙述性“有没有VP”的出现,势必对普通话句式的格局产生一定的影响。它与普通话传统用语“VP没有”都是选择问句,表达的基本意义相近,使用时,人们往往把这两种形式看成是完全等同的。本文着眼于这两种句式的“微殊”,试从形成模式、问话期待、语义重心和回答方式、句式特点和变换方式上作一些探讨,以期更好地指导人们的言语实践。     

Building parallel corpora by automatic title alignment using length-based and text-based approaches

Cross-lingual semantic interoperability has drawn significant attention in recent digital library and World Wide Web research as the information in languages other than English has grown exponentially. Cross-lingual information retrieval (CLIR) across different European languages, such as English, Spanish, and French, has been widely explored; however, CLIR across European languages and Oriental languages is still in the initial stage. To cross language boundary, corpus-based approach is promising to overcome the limitation of the knowledge-based and controlled vocabulary approaches but collecting parallel corpora between European language and Oriental language is not an easy task. Length-based and text-based approaches are two major approaches to align parallel documents. In this paper, we investigate several techniques using these approaches and compare their performances in aligning English and Chinese titles of parallel documents available on the Web.     

面向查询的观点摘要模型研究:以Debatepedia为数据源

本文系统性地研究面向查询的观点摘要任务,旨在构建一种查询式观点摘要模型框架,探究不同的摘要方法对摘要效果的影响。通过综合考虑情感倾向与句子相似度,从待检文档中抽取出待摘要语句,再结合神经网络和词嵌入技术生成摘要,进而构建面向查询的观点摘要框架。从Debatepedia网站上爬取议题和论述内容构建观点摘要实验数据集,将本文方法应用到该数据集上,以检验不同模型的效果。实验结果表明,在该数据集上,仅使用基于抽取式的方法生成的观点摘要质量更高,取得了最高的平均ROUGE分数、深度语义相似度分数和情感分数,较生成式方法分别提高6.58%、1.79%和11.52%,而比组合式方法提高了8.33%、2.80%和13.86%;同时,本文提出的句子深度语义相似度和情感分数评估指标有助于更好地评估面向查询的观点摘要模型效果。研究结果对于提升面向查询的观点摘要效果,促进观点摘要模型在情报学领域的应用具有重要意义。     

杏仁油提取的各种工艺方法与研究

杏仁油是一种应用广泛的植物基础油,基础油和精油一起应用于芳香疗法中。大多数的植物精油具有强烈的刺激性,无法直接被人体吸收,只有在基础油中稀释后才能使用。基础油是在低温条件下制取的,温度不高于60℃,这就使得油脂中的矿物质、维生素以及脂肪酸等保存良好,具有优越的滋润滋养特质。本文利用杏仁提取杏仁油,主要综述了水代法、水酶法、冷压榨法、浸出法、超临界萃取法、超声波提取法等主要提取方法。