Dissertation > Excellent graduate degree dissertation topics show

Research on Cross Language Information Retrieval Based on Interlingua Semantic

Author: HuangGuoBin
Tutor: WangMingWen
School: Jiangxi Normal University
Course: Computer System Architecture
Keywords: Middle semantic Cross-language information retrieval Partial Least Squares Latent Semantic variables on
CLC: TP391.3
Type: Master's thesis
Year: 2008
Downloads: 116
Quote: 2
Read: Download Dissertation


With the rapid development of the Internet, the Internet on the type and quantity of information resources are increasingly rich, the language used for increasing diversity and imbalance; same time as the number of network users and the rapid expansion of the scope of its mastered the language also diversified. Language diversity of network resources and network users to master the language differences inevitably bring to the people using the network to retrieve information language barriers, for example, more than 65% of the information in the network are English information, the use of the English network users only about 30% of users using the network information to non-English-speaking countries, which has brought great inconvenience. Not only the Internet, all at the same time there are multi-lingual information systems (such as digital libraries), this language barriers limiting effective access to the information, give full play to affect the value of multilingual information. Start from the end of the 1990s, information retrieval proposed higher requirements that are no longer satisfied to be retrieved in the same language, and contains a variety of languages ??required in the search results. System exists in all languages ??that can be easily retrieved using a language and technology researchers to solve the language of the people in the process of acquiring information from a multilingual information system disorders, called cross-language information retrieval (Cross-Language Information Retrieval, CLIR) technology. Dictionary mode and machine translation technology once become a hot research techniques for cross-language information retrieval. Dictionary-based model is the use of machine-readable dictionaries do the translation, the main problem here is the vocabulary of ambiguity, a word may have multiple meanings, resulting in the choice of words similar to the general machine translation system. Another problem is that the coverage of the dictionary itself is not enough, the dynamic proper nouns, such as names, places, institutions name with each passing day, most likely in the process of translation can not find in the dictionary. The machine translation for document translation, document translation, the disadvantage is that the execution efficiency is not high, the translation is often imprecise. To solve these problems, we propose a cross-language information retrieval method based on partial least squares theory intermediate semantics. The experimental results show that the intermediate semantics-based cross-language information retrieval method has good features. The innovation of this paper are: first, partial least squares theory using improved technology, based the middle semantic cross-language information retrieval model;, in English parallel corpus for the future expansion of the Chinese and English parallel Corpus playing down the foundation.

Related Dissertations

  1. Soft-sensing Technology in the Ethylene Distillation Process Applied Research,TQ221.211
  2. Design of Small-sized Immersed Instrument of COD Using Uy-vis Spectrophotometry,TH744.121
  3. Study the Relationship of Capital-GDP Marginal Growth Rate and the Industrial Structure,F127
  4. Quantitative Structure-Activity/Property Relationship Studies in Biomolecules Based on Partial Least Squares and Support Vector Machine,Q50
  5. Composition data based on a number of analysis methods,O212.1
  6. The Research on China Export Impact of Technical Barriers to Trade Based on PLS Regression Method,F752.62;F224
  7. The dynamic factor analysis of non-ferrous metal prices,F224
  8. Serum Metabolite Profiling of the Hepatitis B Virus Related Cirrhosis,R512.62
  9. Distributing Characteristics of Microcystins and Regression Model of Cytotoxicity/Genotoxicity on Pollution-Spectrum with Huai River Water Organic Extract from X County,R114
  10. Application of Partial Least Square and Discrimnent Analysis in Studying the Style and Influence Factors of the Scientific Personnel,G644
  11. Theoretical and Experimental Studies on the Measurement of COD in Water Using Ultraviolet Spectrum Method,X832
  12. Study on Identification of Cashmere and Wool Using Near Infrared Spectroscopy,TS131
  13. Development and Experimental Research of Near Infrared Spectroscopy Measurement System for Soil Nutrients,S158
  14. Study on Groundwater Prediction Method and Its Application in Northern Large-Scale Irrigation District,S273.4
  15. Prediction and Evaluation of Ecological Footprint of Qiandongnan Autonomous Prefecture,X22
  16. Study on Estimations of Soil Organic Carbon Content Based on Hyperspectral Measurements,S153.62
  17. Research on the Gene Regulatory Network Reconstruction Algorithm Based on Linear Regression Model,Q75
  18. Research of the Model of Enterprise Competitive Intelligence Collection System Based on Cross-Language Information Retrieval,TP391.3
  19. Research of the Ice Condition Forecasting Based on GA Artificial Neural Network,P338.4
  20. Partial Least-squares Regression Theory and Its Application in Dirt Prediction,TK227.3
  21. Association of Air Pollution with Daily Outpatient Visits to Hospital in Tianjin,R188

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