检索结果-内蒙古大学图书馆

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Cheng Xiao Dequan Zheng Yuhang Yang MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin China

This paper presents a new method to acquire domain-ontology structure and examples from semi-structured data sources. Firstly, extract domain-ontology structure, including candidate attributes extraction using certain patterns and applying a statistic method to filter out the incorrect attributes. Secondly, using domain-ontology structure as a clue, automatically generate example extraction patterns. Finally, acquire ontology examples taking advantage of the special structure feature of the Web pages. Experiments are carried out in the field of film, the precision of the ontology structure extraction is 83.7%, and the highest recall of the examples extraction reaches 90%. Experimental results demonstrate that the method developed in this paper is fairly efficient.

关键词： Ontologies Data mining natural language processing Terminology Web pages Statistical distributions Fuzzy systems Laboratories speech processing Statistics

来源：评论

学校读者我要写书评

暂无评论

Improving Chinese to English SMT with Multiple CWS Results

Improving Chinese to English SMT with Multiple CWS Results

引用

International Conference on Asian language processing (IALP)

作者： Yongliang Ma Tiejun Zhao MOE-Microsoft Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin China

In Chinese to English statistical machine translation (SMT), Chinese texts always need a pre-processing high segments sentences into words and this standard approach is Chinese word segmentation (CWS). However, CWS is not developed for SMT, its results are not necessarily optimal for SMT. In recent years, many investigations have been performed concerning making CWS suitable for SMT, but we explore it from another direction. In this paper, our basic idea is to use multiple CWS results as additional language knowledge sources and we present a simple and effective approach to use multiple CWS results for SMT. We also give experiment results over range of strategy settings, and obtain substantial improvements in performance for translation from Chinese to English. The best result shows we gain 1.89 BLEU percentage points over a state of the art HPBT baseline system without using multiple CWS results.

关键词： Surface-mount technology natural languages Interpolation Support vector machines Laboratories natural language processing speech processing White spaces Dictionaries Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Text Categorization Based on Multiple Feature Selection and Fusion of Multiple Classifiers Approaches

Hierarchical Text Categorization Based on Multiple Feature S...

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Mei-ying Jia De-quan Zheng Bing-ru Yang Qing-xuan Chen School of Information Engineering University of Science and Technology Beijing China MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology China

Hierarchical text categorization refers to assigning of one or more suitable category from a hierarchical category space to a document. In this paper, we used hierarchical feature selection method and multiple classifiers for the Hierarchical text categorization task. Experiments showed that the methods we used was effective, compared with flat classification, top-down level-based approach with the multiple feature selection method, the single classifier obtained better performance; reliability function was introduction to evaluate the determine by single classifier reliability, if the reliability function got a small value, multiple classifiers were used to give the determine which category the unlabeled document belong to, compared to single classifier, Multiple classifiers achieved better performance on flat and hierarchical corpuses, and the time cost increasing is little than using single main classifier.

关键词： Text categorization Space technology Tree graphs Classification tree analysis Knowledge engineering Laboratories natural language processing speech processing Support vector machines Support vector machine classification

来源：评论

学校读者我要写书评

暂无评论

Automatic Domain-Ontology Relation Extraction from Semi-structured Texts

Automatic Domain-Ontology Relation Extraction from Semi-stru...

引用

International Conference on Asian language processing (IALP)

作者： Cheng Xiao Dequan Zheng Yuhang Yang Guojun Shao MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin China Automatic Information Technology Company Limited Beijing Shougang Qinhuangdao China

This paper presents a new method to acquire domain-ontology relations from semi-structured data sources. First, obtain Web documents according to the co-occurrence of concept instance and attribute value. Further, define formats of relation patterns, and extract pattern instances from Web documents, including pattern clustering and pattern combining in each cluster. Finally, relation pattern instances are applied to gain attribute values of new concept instances in domain-ontology. Experiments are carried out in the field of film, the rate of pattern incorrect-division and pattern leakage are respectively 0.19% and 1.31%, the highest precision of combined relation patterns reaches 85%. Experimental results demonstrate that the method developed in this paper is fairly efficient.

关键词： Data mining Terminology natural languages natural language processing Search engines Clustering algorithms Information analysis Lattices Data analysis Laboratories

来源：评论

学校读者我要写书评

暂无评论

Automatic Ontology Construction Approaches and Its Application on Military Intelligence

Automatic Ontology Construction Approaches and Its Applicati...

引用

Asia-Pacific Conference on Information processing, APCIP

作者： Mei-ying Jia Bing-ru Yang De-quan Zheng Wei-cong Sun Li Liu Jing Yang School of Information Engineering University of Science and Technology Beijing Beijing China MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin China

Ontology is a method of expressing knowledge. Now the research on the automatic ontology construction has become very popular. In this paper, we introduce the principles of ontology construction, as well as the several methods of automatic construction and particularly analyze their characteristics. Finally, the ontology in military intelligence is constructed automatically by using the existing resources, thesaurus and database. The thesaurus provides classes information for the ontology, while the database provides the instances. The test result shows the accuracy of the semantic relations in the ontology is 86.23%, and the ontology includes the complete information on the instances.

关键词： Ontologies natural language processing Knowledge engineering Laboratories speech processing Thesauri Information processing Sun Deductive databases Testing

来源：评论

学校读者我要写书评

暂无评论

Automatic Domain Ontology Construction Based on Thesauri

Automatic Domain Ontology Construction Based on Thesauri

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Weicong Sun Meiying Jia Dequan Zheng Hongqiang Cao Bingru Yang Hao Yu MOE MS Key Laboratory of Natural Language processing and Speech Harbin Institute of Technology Harbin China School of Information Engineering University of Science and Technology Beijing China Beijing Graphics Institute Beijing China

The research on the automatic ontology construction has become very popular. It is very useful for the ontology construction to reengineer the existing knowledge resource, such as the thesauri. But many relationships in the thesauri are incorrect or are defined too broadly. Accordingly, extracting ontological relations from the thesauri becomes very important. This paper proposes the method to reengineer the thesauri to ontology, and especially the method to how to obtain the correct semantic relations. The test result shows the accuracy of the semantic relations is86.23%, and one is the hierarchical relations with 89.02%, and the other is non-hierarchical relations with 83.44%.

关键词： Ontologies Thesauri Terminology Knowledge engineering Logic Fuzzy systems Laboratories natural language processing speech processing Graphics

来源：评论

学校读者我要写书评

暂无评论

Query Expansion with Statistical Machine Translation

引用

电子学报(英文版) 2008年第1期17卷 48-52页

作者： LI Weijiang ZHAO Tiejun WANG Xiangang MOE-MS Key Laboratory of Natural Language Processing and Speech School of Computer Science and Technology Harbin Institute of Technology Harbin 150001 China

In practical applications of information retrieval, such as the search engine, the query user submitted contains only several keywords usually. This will cause unmatched issues of words between relevant files and the user's query, and result in more seriously negative effects on the performance of information retrieval. On the basis of analyzing the process of producing query, this paper puts forward a new method of query expansion based on the model of statistical machine translation. The approach extract related terms between documents and query through statistical machine translation model, then expand the query with them. The experiment on TREC data collection shows that our method achieved 4-17% of the improvement all the time more than the language model method without expanding. Compared to pseudo feedback, our method has the competitive average precision.

关键词：信息检索机器翻译查询扩展语言模型

来源：评论

学校读者我要写书评

暂无评论

RM-structure alignment based statistical machine translation model

引用

High technology Letters 2008年第3期14卷 271-275页

作者：孙加东 Zhao Tiejun MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin 150001 P.R. China

A novel model based on structure alignments is proposed for statistical machine translation in this paper. Meta-structure and sequence of meta-structure for a parse tree are defined. During the translation process, a parse tree is decomposed to deal with the structure divergence and the alignments can be constructed at different levels of recombination of meta-structure （RM）. This method can perform the structure mapping across the sub-tree structure between languages. As a result, we get not only the translation for the target language, but sequence of meta-stmctu .re of its parse tree at the same time. Experiments show that the model in the framework of log-linear model has better generative ability and significantly outperforms Pharaoh, a phrase-based system.

关键词： statistical machine translation recombination of meta-structure （ RM） structure alignment log-linear model

来源：评论

学校读者我要写书评

暂无评论

AN EFFICIENT APPROACH TO IMPORTANT BLOGGERS DISCOVERY

引用

Journal of Electronics(China) 2008年第2期25卷 218-225页

作者： Yang Yuhang Yu Hao Zhao Tiejun Tan Hongye Zheng Dequan MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin 150001 China

Popularity of blogs and the amount of information in the blogosphere increase so fast that it is difficult for Internet users to search the information they care about. Compared with conventional webs,links in the blogosphere are more abundant and conversations between bloggers are more fre-quent. This paper proposes a method of ranking bloggers based on link analysis,which can exemplify the characteristics of blogs,and reduce the influence of link spamming. This method can also bring convenience to users to read blogs,and it can supply a new methodology for information retrieval in the blogosphere. To ensure the reliability of the ranking results,some evaluation indicators of the im-portant bloggers are proposed,and the grading results of bloggers using the proposed method is compared with that using other indicators. At last,correlation analysis is used to verify the consistency between the proposed method and the evaluation indicators.

关键词： Important blogger Link analysis Evaluation indicator Correlation analysis

来源：评论

学校读者我要写书评

暂无评论

Classifiers ensemble approaches for automatic recognition of biomedical named entities

引用

Journal of Computational Information Systems 2008年第3期4卷 1001-1008页

作者： Wang, Haochang Zhao, Tiejun College of Computer and Information Technology Daqing Petroleum Institute Daqing 163318 China MOE-MS Key Laboratory of Natural Language Processing and Speech Harbin Institute of Technology Harbin 150001 China

As a new branch of data mining and knowledge discovery, the research of biomedical text mining has a rapid progress currently. Biomedical named entity recognition is a basic technique in the biomedical knowledge discovery and its performance has direct effects on further discovery and processing in biomedical texts. In this paper, we present classifiers ensemble approaches for biomedical named entity recognition. Four individual classifiers, Generalized Winnow, Conditional Random Fields, Support Vector Machine, and Maximum Entropy are combined through three different strategies. We demonstrate the effectiveness of the strategies and compare their performances with standalone classifier system. The experiments are carried on JNLPBA2004 corpus with an F-sore of 77.57%. Experimental results show that the proposed method, stacking ensemble strategy, can yield promising performances.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：