跳到主要內容

臺灣博碩士論文加值系統

(18.97.14.82) 您好!臺灣時間:2025/02/15 02:40
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:魏智強
研究生(外文):Chih-Chiang Wei
論文名稱:自動化問答系統之研製
論文名稱(外文):Development of an Automatic Question-Answering System
指導教授:曾秋蓉曾秋蓉引用關係
指導教授(外文):C.R. Tseng
學位類別:碩士
校院名稱:中華大學
系所名稱:資訊工程學系碩士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2006
畢業學年度:94
語文別:中文
論文頁數:71
中文關鍵詞:問答系統自動關鍵詞擷取文件相似度比對
外文關鍵詞:QA SystemAutomatic Keyword ExtractionDocument Similarity Matching
相關次數:
  • 被引用被引用:12
  • 點閱點閱:414
  • 評分評分:
  • 下載下載:89
  • 收藏至我的研究室書目清單書目收藏:1
在這個各式各樣資訊與知識皆迅速成長的時代,資訊檢索的相關研究成為一個值得討論的重要議題;然而傳統的資訊檢索系統通常在檢索過程中,還是必須依賴使用者分析問題的能力與經驗來尋求合適的關鍵詞,並且要在眾多結果中瀏覽並找出他們所需要的資訊。所以問答系統相關研究的興起就是為了要解決這類問題的產生。
雖然問答系統在提供使用者比較精簡答案這方面的表現優秀許多,但是仍然有以下幾項問題有待改進:(1)關鍵詞需要由人工設定耗力費時。(2)人員的知識與經驗的好壞對於關鍵詞的設定所造成的影響會直接影響到系統的準確度。(3)系統建置時的知識與經驗無法有效保留在系統中。(4)系統準確度還有可以提升的空間。
因此,本研究針對上述第(1)(2)(3)點問題提出了一套「關鍵詞自動擷取」的方法,藉由系統自動化擷取關鍵詞的動作來節省系統建置時人力與時間的花費,並可將建置時的知識與經驗保留在系統中。而針對第(4)點,本研究則提出了IMF-S的方法來進一步的提升系統的準確度。經由實驗結果證實,在關鍵詞自動擷取方法上,系統平均約可提升6.06%至6.56%之準確度;而在「文件相似度比對」方法上,系統平均約可再提升2.08%至5.12%之準確度。
The rapid growing of information and knowledge encourages the related researches of information retrieval. In the traditional information retrieval system, it relies heavily on the users’ ability and experience to find out appropriate keywords for retrieving the information for question answering. The users also need to browse the results and then search for the right information segment they need. That is not only manpower consuming but also ineffective on information retrieval. It thus leads to the researches of question-answering system that would automatically and effectively find out the answers of user’s questions..
Although the question-answering system represents better results in effectively offering answers to their users, problems still exist as: (1) The keywords have to be set by a certain personnel, and it costs much manpower and time; (2) The knowledge and experience of the personnel will absolutely influence on the quality of the keyword set as well as the quality of the answers; (3) The knowledge and experience of the personnel is not able to be efficiently kept in the system; (4)The quality and the accuracy of the answers still have potential to be improved.
In this thesis, a keyword weighting method, called IMF, is proposed. IMF is applied to develop an automatic keyword extraction system to solve the previous three problems described in the last paragraph. IMF is also applied to the answer-selecting stage of the question-answering system to slove the problem (4). It further improves the accuracy and the quality of the answer retrieved by the automatic question-answering system. The experiment results show that the accuracy is improved by 6.06% to 6.56% averagely.
摘要 i
Abstract ii
致謝 iii
目次 iv
圖目錄 vi
表目錄 viii
第一章 簡介 1
1.1 研究背景 1
1.2 研究動機 2
1.3 研究目的 3
1.4 論文架構 4
第二章 相關文獻探討 5
2.1 概述 5
2.1.1 自動問答系統 5
2.1.2 自動關鍵詞擷取 7
2.2 ACSS自動化客戶服務系統 10
2.3 WISE網路資源搜尋系統 14
第三章 研究方法 17
3.1 IMF-K關鍵詞自動擷取演算法 17
3.2 IMF-S文件相似度比對演算法 24
第四章 系統架構 29
4.1 系統模組設計 30
4.1.1 關鍵詞自動擷取模組 30
4.1.2 問題查詢模組 32
4.1.3 滿意度回覆模組 33
4.1.4 系統資料管理模組 34
4.2 系統實作 35
4.2.1 系統開發環境 35
4.2.2 系統介面 36
第五章 實驗結果與評估 42
5.1 實驗設計 42
5.2 關鍵詞自動擷取方法實驗評估 43
5.2.1 回覆準確度評估 43
5.3 文件相似度比對方法實驗評估 53
5.3.1 回覆準確度評估 53
5.4 實驗結果分析 63
第六章 結論與未來工作 65
參考文獻 67
[1]S. Abney, M. Collins, and A. Singhal, "Answer extraction", Proceedings of the sixth conference on Applied Natural Language Processing, Seattle, Washington, 2000, pp. 296-301.
[2]E. Agichtein, S. Lawrence, and L. Gravano, "Learning search engine specific query transformations for question answering", Proceedings of the 10th international conference on World Wide Web(WWW10), Hong Kong, 2001, pp. 169-178.
[3]Jiyuan An and Phoebe Yi-Ping Chen, "Keyword extraction for text categorization", Proceedings of the International Conference on Active Media Technology, May 19-21, 2005.
[4]David B. Bracewell, Fuji Ren, and Shingo Kuriowa, "Multilingual Single Document Keyword Extraction for Information Retrieval", Proceedings of IEEE International Conference on Natural Language Processing and Knowledge Engineering, Oct. 30-01, 2005, pp. 517-522.
[5]Eric Brill, Susan Dumais, and Michele Banko, "An analysis of the AskMSR question-answering system", Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing, 2002, pp. 257-264.
[6]Eric Brill, Jimmy Lin, Michele Banko, Susan Dumais, and Andrew Ng, "Data-intensive question answering", Proceedings of the Tenth Text REtrieval Conference, 2001.
[7]Sabine Buchholz, "Using grammatical relations, answer frequencies and the World Wide Web for TREC question answering", Proceedings of the Tenth Text REtrieval Conference, 2001.
[8]A. Clark and D. Filev, "Clustering Techniques for Rule Extraction from Unstructured Text Fragments", Annual Meeting of the North American Fuzzy Information Processing Society, June 26-28, 2005, pp. 793-798.
[9]Charles Clarke, Gordon Cormack, and Thomas Lynam, "Exploiting redundancy in question answering", Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, New Orleans, Louisiana, United States, 2001, pp. 358-365.
[10]S. Harabagiu, D. Moldovan, M. Pasca, R. Mihalcea, M. Surdeanu, R. Bunescu, R. Girju, V. Rus, and P. Morarescu, "FALCON: Boosting knowledge for question answering", Proceedings of the Ninth Text REtrieval Conference, 2001.
[11]A. Hulth, "Improved Automatic Keyword Extraction Given More Linguistic Knowledge", Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing, Sapporo, July, 2003, pp. 216-223.
[12]Boris Katz, "Annotating the World Wide Web using natural language", Proceedings of the 5th RIAO Conference on Computer Assisted Information Searching on the Internet, 1997.
[13]Boris Katz and Jimmy Lin, "Selectively Using Relations to Improve Precision in Question Answering", Proceedings of the EACL-2003 Workshop on Natural Language Processing for Question Answering, April 2003.
[14]Boris Katz, Sue Felshin, Deniz Yuret, Ali Ibrahim, Jimmy Lin, Gregory Marton, Alton Jerome McFarland, and Baris Temelkuran, "Omnibase:Uniform access to heterogeneous data for question answering", Proceedings of the 7th International Workshop on Applications of Natural Language to Information Systems, 2002, pp. 230-234.
[15]R. Kongachandra, C. Kimpant, T. Suwanapong, and K. Chamnongthai, "Newly-born keyword extraction under limited knowledge resources based on sentence similarity verification", IEEE International Symposium on Communications and Information Technology, Oct. 26-29, 2004, Vol. 2, pp. 1183-1187.
[16]Cody Kwok, Oren Etzioni, and Daniel S. Weld, "Scaling question answering to the Web", Proceedings of the Tenth International Conference on World Wide Web, Hong Kong, 2001, pp. 150-161.
[17]Jimmy Lin, "The Web as a resource for question answering: Perspectives and challenges", Proceedings of the Third International Conference on Language Resources and Evaluation, 2002.
[18]Jimmy Lin and Boris Katz, "Question Answering from the Web Using Knowledge Annotation and Knowledge Mining Techniques", Proceedings of the twelfth international conference on Information and knowledge management, New Orleans, Louisiana, USA, Nov. 3–8, 2003, pp. 116-123.
[19]Jimmy Lin, Dennis Quan, Vineet Sinha, Karun Bakshi, David Huynh, Boris Katz, and David R. Karger, "The role of context in question answering systems.", Proceedings of the 2003 SIGCHI Conference on Human Factors in Computing Systems, 2003.
[20]Zhou Lixin, "Research of segmentation of Chinese texts in Chinese search engine", Proceedings of 2001 IEEE International Conference on Systems, Man, and Cybernetics, Tucson, AZ , USA, Oct. 7-10, 2001, Vol. 4, pp. 2627-2631.
[21]M. Makrehchi and M. Kamel, "A fuzzy set approach to extracting keywords from abstracts", Program Committee of 23rd International Conference of the North American Fuzzy Information Processing Society, Banff, AB, Canada, June 27-30, 2004.
[22]Bill Manaris, "Natural Language Processing: A Human-Computer Interaction Perspective", In Advances in Computers (Marvin V. Zelkowitz, ed.), Academic Press, New York, 1998, Vol. 47, pp. 1-66.
[23]Y. Matsuo and M. Ishizuka, "Keyword Extraction from a Single Document using Word Co-occurrence Statistical Information", International Journal on Artificial Intelligence Tools, 2004, Vol. 13, No. 1, pp. 157-169.
[24]Zhu Mengxiao, Cai Zhi, and Cai Qingsheng, "Automatic keyword extraction with relational clustering and Levenshtein distances", Proceedings of International Conference on Natural Language Processing and Knowledge Engineering, Oct. 26-29, 2003.
[25]D. Moldovan, M. Pasca, S. Harabagiu, and M. Surdeanu, "Performance issues and error analysis in an open-domain question answering system", Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, Philadelphia, Pennsylvania, 2002, pp. 33-40.
[26]Ana-Maria Popescu, Oren Etzioni, and Henry Kautz, "Towards a theory of natural language interfaces to databases", Proceedings of the 8th international conference on Intelligent user interfaces, Miami, Jan. 2003, pp. 149-157.
[27]J. Prager, E. Brown, A. Coden, and D. Radev, "Question answering by predictive annotation", Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information, Athens, Greece, 2000, pp. 184-191.
[28]D. R. Radev, H. Qi, Z. Zheng, S. Blair-Goldensohn, Z. Zhang, W. Fan, and J. Prager, "Mining the Web for answers to natural language questions", Proceedings of the Tenth International Conference on Information and Knowledge Management, 2001.
[29]Ganesh Ramakrishnan, Soumen Chakrabarti, Deepa Paranjpe, and Pushpak Bhattacharya, "Information extraction: Is question answering an acquired skill?", Proceedings of the 13th international conference on World Wide Web, May 2004.
[30]T.A. Runkler and J.C. Bezdek, "Automatic keywords extraction of Chinese document using small world structure", Proceedings of International Conference on Natural Language Processing and Knowledge Engineering, Oct. 26-29, 2003.
[31]Y. Sakakibara, K. Misue, and T. Koshiba, "Text classification and keyword extraction by learning decision trees", Proceedings of Ninth Conference on Artificial Intelligence for Applications, March 1-5, 1993.
[32]G. Salton, and C. Buckley, "Term Weighting Approaches in Automatic Information Retrieval", Journal of Information Proceeding and Management, 1988, Vol. 24, No. 5, pp. 513-523.
[33]G. Salton and M. McGill, “Introduction to Modern Information Retrieval”, New York N.Y.: McGraw-Hill, 1983.
[34]G. Salton, A. Wong, and C.S. Yang, “A Vector Space Model for Automatic Indexing”, Communications of the ACM, Nov. 1975, Vol. 18, No. 11, pp. 613-620.
[35]M. M. Soubbotin and S. M. Soubbotin, "Patterns of potential answer expressions as clues to the right answers", Proceedings of the Tenth Text REtrieval Conference, 2001.
[36]Judy C. R. Tseng and Gwo-Jen Hwang, “Development of an Automatic Customer Service System on the Internet”, to appear in Electronic Commerce Research and Applications, 2006.
[37]Ellen M. Voorhees, "Overview of the TREC 2001 question answering track", Proceedings of the Tenth Text REtrieval Conference, 2001.
[38]Ellen M. Voorhees, "Overview of the TREC 2002 question answering track", Proceedings of the Eleventh Text REtrieval Conference, 2002.
[39]Ellen M. Voorhees and Dawn M. Tice, "Overview of the TREC-9 question answering track", Proceedings of the Ninth Text REtrieval Conference, 2000.
[40]Yan-Wen Wu, Zheng-Hong Wu, and Jin-Ling Li, "Personalized Intelligent Question Answering Algorithm in E-Learning", Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, Guangzhou, Aug. 18-21, 2005.
[41]Budi Yuwono and Dik Lun Lee, “WISE: a World Wide Web resource database system”, IEEE Transactions on Knowledge And Data Engineering, Aug. 1996, Vol. 8, No. 4, pp. 548-554.
[42]中央研究院中文詞庫小組, “CKIP中文分詞詞庫”, 中央研究院, 1999.
[43]李孟瑜, 曾秋蓉, "Development of an Intelligent Network-based Customer Service System", 私立中華大學資訊工程研究所碩士論文, 2002.
[44]林農堯, 黃國禎, "Development of an Adaptive Virtual Tutoring-Assistant System on Computer Networks", 國立暨南國際大學資訊管理研究所碩士論文, 2003.
[45]張育銘, 黃國禎, "自我調適能力之智慧型網路客戶服務系統", 全國計算機會議, 文化大學, 2001.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊