Dissertation > Excellent graduate degree dissertation topics show

Research on HNC Theory and Random Fuzzy and Their Application in Question Answering System

Author: ChenHaiGuang
Tutor: ChengXianYi
School: Jiangsu University
Course: Applied Computer Technology
Keywords: QA system Question classification Answer extraction HNC theory Random fuzzy theory
CLC: TP391.6
Type: Master's thesis
Year: 2009
Downloads: 81
Quote: 0
Read: Download Dissertation

Abstract


With the rapid expansion of the amount of information on the Internet, so that people become more and more difficult to find the information they need online. Although some search engines (such as Google, Baidu), which makes the people from the flood of web pages quickly find useful information tools, but most of the existing search engine information retrieval technology are based on keyword matching search results exist a large number of redundant and useless information, affecting the accuracy of the returned result. This article discusses the QA (Question Answering) system is trying to change this situation, it can not only effectively use the Internet this vast information resource base, and the use of the concept of hierarchical network (Hierarchical Network ofConcept, HNC) theory, the richer and more accurate return results. Opinion from the current research situation at home and abroad, the quality of the QA system is far from satisfying, because two aspects: First, the QA system classification inaccurate leading to the final answer questions theme deviate from; Second, the candidate answer extraction technology mostly based on statistical methods, ignoring the semantics of the sentence, affecting the accuracy of the answers. In view of these shortcomings, this paper extracted from the problem of classification and candidate answers to study two aspects, first proposed random fuzzy tree model based on the HNC theory and random fuzzy theory, thus better able to deal with the the HNC quintet ambiguity, making computer understanding of natural language more in place; Second, the proposed HNC theory-based multi-strategy answer extraction algorithm, HNC symbol conceptual level network information into the answer extraction algorithm, thus improving the quality of the generated answers. The main research results can be summarized as follows: (1) combined with random fuzzy theory and HNC theory, a random fuzzy tree. Digestion HNC quintet ambiguity by calculating the random fuzzy tree Sentence primitive opportunity, to some extent. (2) The Chinese question classification method based on the HNC theory, HNC conceptual level network information Sentence analysis Knowledge and random fuzzy semantic disambiguation knowledge to classify the Chinese problem. Adapted to the diversity and complexity of the Chinese expression. (3) The proposed the HNC theory-based multi-strategy answer extraction algorithm using semantic the synonym substitution rich candidate answers, improved statement conceptual similarity calculation method and pattern matching together. The answer extraction Get rates and accuracy is improved to some extent. (4) the application of modern, integrated business background, a Chinese QA system prototype system, compared with the traditional QA system for a comparative experiment, the initial validation of the proposed algorithm in fuzzy ambiguity resolution than traditional QA system more effective.

Related Dissertations

  1. Research of Question Answering System Based on the Analysis of Lexical and Semantic Meanings,TP391.1
  2. Domain knowledge domain question answering system answers extracted,TP391.3
  3. Based on incremental improvements in the Bayesian question classification in the field of research,TP391.3
  4. The travel ontology Knowledge Base and reasoning applied research,TP391.1
  5. Based semi - supervised learning Chinese Question Classification,TP391.1
  6. English entities answer extraction and Home Find,TP391.1
  7. Design and Implementation of Question Answering System Based on the Understanding,TP311.52
  8. Study on Key Techniques of Question Analysis in Chinese Question Answer System,TP391.1
  9. Interactive Question Answering System Based on Hybrid-structure Data Sources,TP391.3
  10. Analysis and Research of Text Orientation Based on Semantic,TP391.1
  11. Based on Support Vector Machine Classification of Chinese problems,TP18
  12. Research on a Multi-Strategy Approach to Answer Extraction in Chinese Question Answering,TP391.3
  13. Chinese-English Cross-Language Question Answer Information Retrieval Technology,TP391.3
  14. Research and Application of Intelligent Battery Fault Diagnosis System,TM910.7
  15. A Study on Chinese Question Classification Based on Chinese FrameNet,TP391.1
  16. Research and Implementation of Question Classification Technology Based on Open Domain Question Answering System,TP391.1
  17. Automatic QA System for Software Testing,TP311.53
  18. Study on Question Classification in Chinese Question Answering System,TP391.1
  19. Research on the Questions Classification in the Chinese Question Answering System,TP391.1
  20. Design and Implementation of the Chinese Question Answering System Based on the Voice Interface,TP391.1
  21. Study on Feature Selection in Chinese Question Classification,TP391.1

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