Font Size: a A A

Model And Mapping Algorithm Of Transformation From Text Cell To Knowledge Cell

Posted on:2009-07-17Degree:MasterType:Thesis
Country:ChinaCandidate:W H XuFull Text:PDF
GTID:2178360245468626Subject:Information Science
Abstract/Summary:PDF Full Text Request
As the extensive popularization and application of information technology, people's demands for knowledge service have also been increased. The majority of human existing knowledge regard the text as carrier. How to make good use of computer in automatic acquisition of knowledge from texts, has always been one of the difficult problems to be solved in the field of knowledge engineering.This paper is focusing on the acquisition of knowledge from texts with discussion and study. Firstly, we introduced the text structure analysis and ontology text learning methods and made a particular description on the physical structure and logic structure of the text, ontology learning concepts, principles and methods and presented an algorithm of Chinese text feature extraction based on TFIDF (term frequency, inverse document frequency) .Then we presented A Bootstrap Method for Ontology Learning Based on Rules of Sentence Patterns. We introduced the framework of the method, and described the detailed solution to some key technical problems within the framework, such as the Text Preprocessing, the definition of Ontology fragment, and the syntax of the rule of sentence patterns. With the analysis of Model and Mapping algorithm of the transformation from text cell to knowledge cell, we have developed a Chinese Text Knowledge Extraction System, conducted experiments and have acquired some interesting meaningful results, which has preliminarily verified the hypothesis. Besides we have analysis the factors for the quality of the results. Finally, we present the idea of the future work based on the core of the paper, i.e. the acquisition of text feature and the Bootstrap Method for Ontology Learning Based on Rules of Sentence Patterns.The innovative work and results of this thesis are mainly about:(1) Improving a Chinese automatic segmentation algorithm based on Massive Intelligent Segmentation, laying foundation for the acquisition of text feature.(2) Applying the thought that take the word weight as the features of texts and make the singular value decomposition in the acquisition of text knowledge and establishing some syntax of the rule of sentence patterns.(3) Designing and realizing the Chinese text knowledge acquisition system, which has effectively verified the methods proposed in this paper.
Keywords/Search Tags:text cell, knowledge cell, rule of sentence patterns, ontology learning
PDF Full Text Request
Related items