搜索结果: 61-75 共查到“知识库 自然语言处理”相关记录311条 . 查询时间(4.604 秒)
A user-centric model of voting intention from Social Media
Vasileios Lampos Daniel Preot¸ iuc-Pietro Trevor Cohn
2013/3/20
Social Media contain a multitude of user opinions which can be used to predict realworld phenomena in many domains including politics, finance and health. Most existing methods treat these problems as...
A temporal model of text periodicities using Gaussian Processes
A temporal model of text periodicities Gaussian Processes
2013/3/20
Temporal variations of text are usually ignored in NLP applications. However, text use changes with time, which can affect many applications. In this paper we model periodic distributions of words ove...
QuEst - A translation quality estimation framework
QuEst - A translation quality estimation framework
2013/3/20
We describe QUEST, an open source framework for machine translation quality estimation. The framework allows the extraction of several quality indicators from source segments, their translations, exte...
Low-Power Themes Classifier (LPTC): A Human-Expert-Based Approach for Classification of Scientific Papers/Theses with Low-Power Theme
Natural Language Processing (NLP) Semantic Web Term Extraction Text Categorization Resource Description Framework (RDF) Low-Power Theme
2012/11/30
Document classification is widely applied in many scientific areas and academic environments, using NLP techniques and term extraction algorithms like CValue, TfIdf, TermEx, GlossEx, Weirdness and the...
在说话人确认系统中，由于训练和测试语音来自不同的信道，会产生信道失配现象。为此，提出一种基于扰动属性投影的说话人确认系统。利用有信道标注信息的语音训练出高维空间映射矩阵，通过映射将自适应得到的超矢量作为SVM的输入，削弱说话人特征中的信道信息。实验结果表明，该系统能降低信道失配带来的负面影响。
一种三层判决的说话人索引算法
三层判决 说话人索引 惩罚距离 模型自举法 GMM说话人超级矢量
2012/1/20
为提高说话人索引准确率，提出一种三层判决的说话人索引算法。第1层使用惩罚距离公式对说话人改变进行检测，第2层采用说话人模型自举法进行初次说话人辨认，第3层采用GMM说话人超级矢量进行判决，解决说话人模型自举法中产生的数据不匹配问题。实验结果表明，采用惩罚距离公式，与贝叶斯信息判决方法相比不需调整参数，与DISTBIC方法相比F1值提高2%，使用GMM说话人超级矢量，在说话人索引准确率和数量准确率方...
An English-to-Arabic Prototype Machine Translator for Statistical Sentences
Machine Translation Natural Language Processing Parsing Dictionary
2012/1/4
Authors of that paper proposed a prototype machine translator system to translate scientific English sentences into Ara- bic sentences. This system is based on natural language processing and machine ...
提出一种基于局部二值模式(LBP)和模糊支持向量机(FSVM)的视频文字定位方法。利用边缘信息和形态学操作进行文字粗检测，采用投影直方图和启发式规则形成候选文字区域，提取LBP作为纹理特征，用FSVM对候选文字区域进行精确定位，生成最终的文字块。实验结果表明，该方法具有较好的视频文字定位能力且鲁棒性较强。
A Process for Extracting Non-Taxonomic Relationships of Ontologies from Text
Ontology Ontology Learning Non-Taxonomic Relationships Natural Language Processing
2011/7/15
Manual construction of ontologies by domain experts and knowledge engineers is an expensive and time consuming task so, automatic and/or semiautomatic approaches are needed. Ontology learning looks fo...
Relaxed Cross-lingual Projection of Constituent Syntax
Relaxed Cross-lingual Projection Constituent Syntax
2011/4/22
We propose a relaxed correspondence as-sumption for cross-lingual projection of con-stituent syntax, which allows a supposed constituent of the target sentence to corre-spond to an unrestricted treele...
Computational Linguistics and Natural Language Processing
Computational Linguistics Natural Language Processing
2011/3/24
Researches in Computational Linguistics (CL) and Natural Language Processing (NLP) have been increasingly dissociated from each other. Empirical techniques in NLP show good performances in some tasks ...
自然辩证法研究与科学史学关系的本土化考察
自然辩证法 科学史学 本土化
2010/5/19
在中国自然辩证法研究与科学史学之间的联系可追溯到"自然辩证法"的创立之初。科学史学是马恩创立自然辩证法的重要的条件和手段。就对二者关系的本土化考察来看,它们之间的关系日趋密切,相互影响愈益明显。时下科学史学既是自然辩证法研究的基础,又引导自然辩证法研究向新的领域拓展和延伸。自然辩证法研究则对科学史学的发展有着指导性、拓展性和提升性的作用。
Sensing Semantics of RSS Feeds by Fuzzy Matchmaking
RSS Feeds Matchmaking Multi-Agent Semantics
2010/3/16
RSS feeds provide a fast and effective way to publish up-to-date information or renew outdated contents for information subscribers. So far RSS information is mostly managed by content publishers but ...
基于依存树的中文语义角色标注
最大熵分类器 语义角色标注 依存树
2010/2/10
现有中文语义角色标注主要集中在基于短语结构句法树的标注。基于此，提出一种基于依存树的中文语义角色标注方法。将中文句子转化为标准的依存树，作为实验数据集，特征选取时结合知网，将语义信息引入特征集，以提高系统的召回率，并采用最大熵分类器进行实验，获得90.68%的F值。结果表明，在标准的句法树上，当基于依存关系的标注系统中加入新特征时，该中文语义角色标注取得了比基于句法成分标注更好的成绩。