目前的對話系統，大多侷限在單一功能或單一領域的應用，且極少探討在對話系統背後知識庫的研究，因此，如何建立一個具推論功能的知識庫、與有效整合多套現存之對話系統，成為一個值得研究的主題。為了實現此一研究主題，本研究首先半自動的建立一個醫療概念模型作為對話系統的知識庫，以支援建立三個獨立的模組：分別為掛號諮詢模組、科別諮詢模組以及常見問答集模組，並藉由對話管理模組依其意圖加以整合。

本論文提出以使用雙語字典、雙語語料整合字網(WordNet)和知網(HowNet)，來建立一個完整的概念模型(Ontology)，再利用島嶼演算法半自動的抽取出醫療概念模型 (Medical Ontology)作為系統背後的知識庫，再提出以部分樣本樹來做意圖偵測，並配合語意框架來控制整個對話流程，最後以樣本基礎的方式來生成系統回應句。

為了評估本論文所提出的方法，我們請50個大專生來實際測試系統，整體意圖偵測正確率為86.2%、系統成功率為77%，每筆對話的平均長度為9.2回合，而回答自然度則為78.5%，而常見問答集模組加上推論後最終的正確率為82%，相對於純粹用關鍵字查詢則提升了15%。

Recently, most dialogue systems have been designed for a single domain. Also, few researches focused on the construction of the knowledgebase for the dialogue systems. The construction of a knowledgebase with inference and the application to multidomain become important topics and are worth researching. In order to achieve this goal, we construct a medical ontology as the knowledgebase for the system semi-automatically. The medical ontology is used to establish three related services, including registration information service, clinic information service, and FAQ (Frequency Asked Question) service. Then, this approach uses the dialogue management module to integrate the services according to the user’s intention.

In this thesis, we use the bilingual knowledge, WordNet and HowNet to establish a universal ontology first. The island-driven algorithm is then adopted to extract the medical ontology as a knowledgebase for the system. We apply the partial pattern tree (PPT) for intention detection. Finally, the detected intention and its corresponding semantic frames are filled and used to control the whole dialogue process. In addition, the generation of the responses to the input is based on the predefined templates.

In order to evaluate the system performance, we asked 50 college students to test the system. The correct rate for intention detection is 86.2% and the success rate for system operation is 77%. The average length of the dialogues is about 9.2 turns. The naturalness for the response is 78.5%. The correct rate for FAQ module with inference achieves 82% and is improved by 15% in comparison to the keyword-based approach.

[1] Michael F. McTEAR, “Spoken Dialogue Technology: Enabling the Conversational User Interface,” ACM Computer Surveys, Vol 34, No. 1, March 2002, pp.90-169.

[2] J. F. Allen, D. K. Byron, Dzikovska M. Ferguson, L. Galescu, and A. Stent, (2001) “Towards Conversational Human-Computer Interaction,” AI Magazine.

[3] Xuedong Huang, Alex Acero, Hsiao-Wuen Hon, “Spoken Language Processing”, Prentice-Hall,Inc. 2001

[4] J. Allen, (1994) “Natural Language Understanding”, The Benjamin/Cummings Publishing Company.

[5] V. Zue, et al, "JUPITER: A telephone-based conversational interface for weather information," IEEE Trans. on Speech and Audio Processing, vol. 8, no. 1, January 2000.

[6] AT&T(2002) How may I help you? http://www.research.att.com/~algot/hmihy/

[7] S. Bennacef and L.Lamel et al., “Dialogue in the RAILTEL Telephone-Based System,“ ICSLP’96 Vol. 1. pp. 550-553

[8] L. Lamel, S. Rosset, J. Gauvain, S. Bennacef, M. Garnier-Rizet , and B. Prouts, (2000) “The LIMSI Arise System,” Speech Communication, 31(4), pp. 339-353.

[9] Chun-Jen Lee, Eng-Fong Huang, and Jung-Kuei Chen, “A Multi-keyword Spotter for the Application of the TL Phone Directory Assistant Service,” Proceedings of 1997 Workshop on Distributed System Technologies & Applications, pp. 197-202

[10] Tung-Hui Chiang, Chung-Ming Peng, Yi-Chung Lin,Huei Ming Wang and Shih Chieh Chien, “The Design of a Mandarin Chinese Spoken Dialogue System,” in Proceedings of COTEC’98, Taipei 1998, pp. E2-5.1~E2-5.7

[11] Chung-Hsien Wu, Gwo-Lang Yan, and Chien-Liang Lin, “Spoken Dialogue System Using Corpus-Based Hidden Markov Model,” in Proceedings of ICSLP98, Sydney,Astralia, 1998.

[12] Steffen Staab , Rudi Studer, Hans-Peter Schnurr, York Sure, “Knowledge Processes and Ontologies”, IEEE Intelligent Systems 16 (1) January February 2001 ,pp. 26-34

[13] J. F. Sowa, Knowledge Representation: Logical, Philosophical and Computational Foundations, 1999, Brooks Cole Publishing Co.

[14] J.l, Chu-Carrol, “MIMIC” An adaptive mixed initiative spoken dialogue system for information queries,” Proceedings of the 6th ACL article on Applied Language Processing, pp. 97-104

[15] Robin D. Burke, Kristian J. Hammond, & Vladimir A. Kulyukin, “Question Answering from Frequently-Asked Question Files: Experiences with the FAQ Finder System” The University of Chicago Computer Science Department, Technical Report TR-97-05.

[16] A. Corazza, R. De Mori, R. Gretter, G. Satta, “Computation Of Probabilities For Island-Driven Parsers”, in IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989

[17] Chung-Hsien Wu, Yeou-Jiunn Chen, and Cher-Yao Yang, ”Error Recovery and Sentence Verification Using Statistical Partial Pattern Tree for Conversational Speech,” in Proceedings of ICSLP2000, Beijing, China, 2000.

[18] A. Miller, “WordNet: An On-Line Lexical Resource,” J.Lexicography, vol.3, no.4, Dec.1990.

[19] 董振東, 董強, “知網”, http://www.keenage.com/

[20] N. Fraser and G. N. Gilbert, Simulating speech system. , 1991 Computer Speech and Language 5 81~99.

[21] M. A. Walker, D. Litman, C. Kamm, and A. Abella, 1997. PARADISE: a general framework for evaluating spoken dialogue agents. In Proceedings of the 35th Annual General Meeting of the Association for Computational Linguistics, ACL/EACL (Madrid, Spain). ACL, 271–280.

[22] L. Baptist, Genesis-II: A Language Generation Module for Conversational Systems, S.M. thesis, MIT Department of Electrical Engineering and Computer Science, August 2000