Dissertation > Excellent graduate degree dissertation topics show

Research on Similar Sentence Retrieval Technology for Patents

Author: LuYanKe
Tutor: ZhangGuiPingï¼›YinBaoSheng
School: Shenyang Institute of Aeronautical College
Course: Applied Computer Technology
Keywords: Sentences similar calculation Pseudo LCS Fuzzy aligned The term similarity calculation
CLC: TP391.1
Type: Master's thesis
Year: 2010
Downloads: 68
Quote: 0
Read: Download Dissertation

Abstract


Sentence retrieval in a wide range of applications in the field of natural language processing, has been concern for people. In answering system, automatic summarization, the EBMT, translation memory, detection of new information, the sentence retrieval retrieval quality will directly affect the performance of the above system. However, how to measure the two sentences similar to a uniform standard, starting from different areas, look at the angle of sentence similarity is different, which leads to the different metrics. In short, so far, there is no uniform metrics; such standards may not exist, because the specific measurement criteria are related to the specific application. For example: in the English-Chinese bilingual sentence search system, similar to the grammatical structure of the sentence or two, you can think that these two sentences are similar; based FAQ automatic question answering, you need two sentences mean basically the same. Meanwhile, as China's urgent need for the continuous improvement of the intellectual property awareness as well as international exchanges, by patent translators can no longer meet the sharp increase in patent literature translation needs manual translation, which to some extent hindered our and the promotion of international patent technology and exchange. In recent years, with the rapid development of machine translation technology, machine translation and human-machine collaborative translation became effective way to solve this problem. The main task of this paper is to design a sentence for human-machine collaborative translation system: patent literature retrieval algorithm to improve the performance and efficiency of the human-machine collaborative translation system. Patent literature jargon relatively more standardized form of rigorous language, sentence length longer, a pseudo-LCS sentence similarity calculation method. The method by traditional longest common substring (LCS) algorithm to improve and add lexical semantic information, it has a fuzzy alignment capabilities. Meanwhile, a term similarity calculation method patent terminology more in this article, and add it to the sentence similarity calculation; certain combination of semantic similarity and structural similarity in the calculation of sentence similarity parts of speech information. These are the proposed algorithm is more suitable for the calculation of sentence similarity in the patent literature. The experimental results show that the method the good results obtained in the patent sentence similarity computing precision rate reached 83.5%, respectively 20% and 17% higher than the improvement of the edit distance and traditional vector space model.

Related Dissertations

  1. Research on Basic Algorithms of Digital Image Processing and Implementation with FPGA,TP391.41
  2. Research on Facial Feature Extraction and Matching Algorithms for Image Retrieval,TP391.41
  3. Research of High Speed Image Pre-processing System Based on FPGA,TP391.41
  4. Research on Algorithms of 2D Face Template Protection,TP391.41
  5. Research of Visualization Technology in the Virtual Test of Missile,TP391.9
  6. The Research and Implemention of Image Retrieval Based on User Interested Feature,TP391.41
  7. Research of Image Mosaic Technology,TP391.41
  8. Research and Implementation of Exact String Matchiing Algorithms,TP391.41
  9. Research of Question Answering System Based on the Analysis of Lexical and Semantic Meanings,TP391.1
  10. Research on the Classification Based on the Reconstruction of Solder Joint,TP391.41
  11. Tongue Feature Extraction and Research of Fusion Classification,TP391.41
  12. Research on Structure Transition Technology for SMT,TP391.2
  13. The Fatigue State Recognition of the Driver Based on Eye Detection,TP391.41
  14. Syntactic Features Based Pronoun Resolution,TP391.1
  15. Research on Infrared Image Simulation for Aerial Objects and Background,TP391.41
  16. Design and Simulation of UHF RFID System Based on the Protocol of EPC C1G2,TP391.44
  17. Research on Intelligent Learning-Based Multi-Sensor Target Recognition and Tracking System,TP391.41
  18. Research on Image Compression and Implementation Using TMS320C6713 Based on SPIHT Algorithm,TP391.41
  19. Research on Joint Target Detection for Dual-Sensor Image and System Implementation,TP391.41
  20. Research of Images Enhancing Algorithms on Fog or Backlighting Conditions and Implementation with Hardwares,TP391.41
  21. Research of Multiple Emails Automatic Summarization,TP391.1

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