Dissertation > Excellent graduate degree dissertation topics show

Domain Ontology terms and upper and lower , parity relation extraction research

Author: WangHaiXiong
Tutor: GuoJianYi
School: Kunming University of Science and Technology
Course: Pattern Recognition and Intelligent Systems
Keywords: Domain terms Hyponymy Parity Relations Information Extraction
CLC: TP391.1
Type: Master's thesis
Year: 2011
Downloads: 101
Quote: 0
Read: Download Dissertation

Abstract


With the popularity of computers rapid development of Internet, knowledge acquisition in the form of source and quantity also will be changed fundamentally. Vast network of vast deposits of knowledge, but also includes a lot of junk knowledge, the use of artificial means to gain knowledge is far from able to satisfy demand, the study of the various knowledge acquisition method to reduce the manual workload is inevitable. How vast source of information the user wants to obtain the knowledge, while the mass of knowledge on access to the manner in which to manage, share, reuse, have become an important topic in artificial intelligence research. Currently, the field of knowledge of the physical good solution to manage, share, reuse, and other issues, thus automatic or semi-automatic ontology building is the current field of information retrieval and knowledge base to build a major research focus, its main tasks include the acquisition of domain terms, the relationship between acquisition, establishment hierarchy, attributes, and attribute values ??for the instance of the acquisition and subsequent maintenance of domain ontology, which is to identify the relationship hierarchy establishment services. This allows automatic or semi-automatic ontology construction in the various sub-tasks has become a hot research object of many scholars. In recent years, with natural language processing technology and the rapid development of information extraction technology, you can use these technologies to accomplish automatic or semi-automatic ontology construction in various tasks. This paper focuses on the field of terminology extraction, field terminology hyponymy extraction and parity relations and other key aspects of the implementation process carried out research and discussion, mainly to complete the work of the following aspects: (1) domain term extraction task for unregistered word term and long-term areas of the field of terminology for the problem, based CRFs areas of plain text fields term extraction method, which considering the characteristics of Chinese words and parts of speech, the realization of domain term identification, and also to the traditional areas of mutual information-based term extraction method for comparison, and the field of tourism in Yunnan to do validation, and achieved good results. (2) the field of terminology hyponymy and parity relations for the current access hyponymy and parity relationship is mainly used model approach, the key lies in patterns of access, this paper based on discrete use CRFs machine learning methods to obtain feature information, namely through feature selection, manual marking a certain amount of training to build relationships corpus classification model, and then use the model to identify upper and lower areas of the relationship between terminology and parity relations. And the field of tourism in Yunnan experiment also proved the effectiveness of the method, validated on the basis of combined features for recognition effect. (3) designed and implemented two prototype systems: the field of terminology and domain terminology extraction prototype system and parity hyponymy relation extraction prototype system, and the two systems for evaluation.

Related Dissertations

  1. Scholar Resume Automatic Generation Based on Text Mining,TP391.1
  2. Ontology-Based Hazard Information Extraction from Chinese Food Complaint Documents,TP391.1
  3. Tracking Events for Food Complaint Documents Based on Ontology,TP391.1
  4. Research on Hyperlinks Extraction Based on Hotspot Website Content Analysis,TP393.092
  5. Research and Application of Semantic-Based Information Extraction,TP393.09
  6. Printers based on natural language HCI Research and implementation,TP11
  7. Research on Information Extraction and Visualization in Program Comprehension,TP311.1
  8. Research of Information Extraction and Declaration Analysis in Program Comprehension,TP311.11
  9. Rule-based Web text information extraction technology research,TP391.1
  10. Research on Domain Entity Attribute and Event Extraction Technology,TP391.1
  11. Design and Implementation of Ontology Based Extraction and Analysis Platform of Logistics Information,TP393.09
  12. Study on Extraction of Broad-levaed Forest Information Based on Medium and High Spatial Resolution Remote Sensing Image,S771.8
  13. Study of the Scale Issues in the Information Extraction of Forest Vegetation Based on Remote Sensing,S771.8
  14. The laser detection automotive active anti-collision technology and systems research,TN247
  15. City names addresses coding Matching,P208
  16. Segmentation of Social Media Web Page and Extraction of Topic Frequent Cluster,TP391.1
  17. Design and Implementation of EDPF NT-plus Operator Station Simulation Software,TP391.9
  18. The Research of Text-based Image Retrieval Technology in Uyghur Kazak Kirgiz Search Engine,TP391.3
  19. Mobile Web Site Development Based on DOM Tree Information Extraction,TP393.092
  20. The Relation and Analysis of Relation-network Analysis Technology Based on MongoDB,TP311.13

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Text Processing
© 2012 www.DissertationTopic.Net  Mobile