Dissertation > Excellent graduate degree dissertation topics show
Chinese expert retrieval key technology research
Author: LiLiNa
Tutor: YuZhengTao
School: Kunming University of Science and Technology
Course: Control Theory and Control Engineering
Keywords: Chinese expert search Expert Home Recognition List -type web data extraction Document type web data extraction Self-organizing expert database
CLC: TP18
Type: Master's thesis
Year: 2011
Downloads: 29
Quote: 0
Read: Download Dissertation
Abstract
|
Experts retrieval is currently a hot research vertical field of information retrieval, retrieval conference TREC internationally renowned experts established in 2005 retrieval task, expert retrieval tasks defined as follows: Given a query subject, and then through a collection of databases and returns a list of relevant experts Expert details, and sort. This paper focuses on Chinese expert homepage recognition, Chinese experts unstructured web data extraction, expert database technologies such as self-organization carried out a series of research and discussion, mainly to obtain the results of the following aspects: (1) is proposed based on J48 algorithm machine learning methods for Chinese expert entity homepage for classification. The method first manual collection Chinese expert entity and the corresponding expert home page 2113, for Chinese expert entity characteristics, definitions and links to web content features and physical characteristics relevant experts, and these features were extracted to form the training data set; Then, learning algorithm using different characteristics in different home pages on the identification, classification feature to find the most effective and Home recognition learning algorithms. Finally, different characteristics, different algorithms for testing, experimental results show that the J48 algorithm, combined with web content features links, Chinese expert entity homepage recognition and achieved good results, the recognition accuracy rate of 81.05%. (2) proposed based on similarities and differences between HTML tag string matching template automatic detection method based on lists and document-based expert expert page page feature, with lattice theory, the use of HTML tags string similarities Autodig data behind web template Wrapper, freeze frame data area. Automated data extraction process, and the page is not marked in advance, is not fixed extraction format, the HTML page through the similarities and differences of the label string matching template for automatic detection of data extraction, to obtain Chinese expert web unstructured data, improved expert web Data extraction accuracy and automation. (3) propose a solution to different types of data fusion Chinese expert database self-organizing method for the list-type Chinese expert data and document data type Chinese experts to build a database of experts to solve the problem of data fusion, and Chinese experts in data cropped. While the user process by retrieving feedback optimization, optimization and editing new optimization methods such as expert database optimization improvement. (4) Using the above research, build expert retrieval experiment platform, Chinese expert retrieval prototype system.
|
Related Dissertations
- Fault Diagnosis Method Based on Support Vector Machine,TP18
- Designs and Applications of Fuzzy Synthetic Evaluation Models Based on Parallel Algorithms,TP18
- Research on Clustering Algorithm Based on Mutation Particle Swarm Optimization,TP18
- Research on Feature Selection and Construction in Emotion Speech Recognition,TP18
- Research on Fuzzy C-Mean Clustering Algorithm Based on Particle Swarm Optimization and Shuffled Frog Leaping Algorithm,TP18
- Research on Clustering Algorithm Based on Genetic Algorithm and Rough Set Theory,TP18
- Based on Rough Set of Urban Areas When Traffic Green Control System Research,TP18
- Philosophy of artificial intelligence,TP18
- Research on the Improvements and Applications of Particle Swarm Optimization,TP18
- Incremental rough set attribute reduction,TP18
- Calculation of Knowledge Granulation and Study of Its Application in Attribute Reduction,TP18
- Reduction and Rule Acquisition in Fuzzy Decision System Based on Neighborhood Relationship,TP18
- The Research and System Design of Assessment Model for Network Learning Based on Intelligent Computation,TP18
- Research on Support Vector Machine Solving Large-scale Data Set,TP18
- Reduction Algorithm for Research and Application Based on Variable Precision Rough Set,TP18
- Research and Application on Ant Clustering Algorithm,TP18
- Based on Support Vector Machine (SVM) Personal Credit Evaluation,TP18
- Classifier Research,TP18
- Research and Application of the Attribute Reduction Algorithm Based on Improved Discernibility Matrix,TP18
- The Application of Genetic Algorithm and BP Neural Network Technique in LF End Temperature Prediction of Molten Steel,TP18
- Based on rough set theory decision information system attribute reduction algorithm,TP18
CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory
© 2012 www.DissertationTopic.Net Mobile
|