近年來，由於口語對話系統已成功應用於個人語音助理服務，例如Apple Siri或是Google Now，自然口語問答的應用已成為下一階段具智慧化的人機介面。過去所提出之系統大部分偏重於問答集(QA Pairs)之比對，對於超出問答集之問題則較無法提供適切之答案。本論文提出一擴充型對話系統，以解決上述之問題。當使用者提出問句時，首先系統利用模式匹配和語句相似度的技術，尋找出語料庫中最適合使用者問句之答案。當搜尋不到適合的答案時，系統會透過主題模型和問答語意相依配對模型來幫助系統從大量的非結構化的文件中擷取出適合的答案，並回應給使用者。
在非結構化的文件處理的部分，我們選擇負向情緒諮詢當成本論文研究領域，首先我們從心理諮商網站蒐集聊天室和討論區的非結構化問答文章，並將其依據事先建立之主題模型切割成語句片段。在此我們利用監督式隱含狄利克雷分布結合差分貝式資訊法則及人工事件標記來做文章段落自動切段及事件分類處理。而後利用中研院詞庫小組所開發之機率式無語境規律剖析樹分析問句和適合該問句的所有答句片段，得到問答句的斷詞結果以及語意相依圖，再將語意相依圖中每個詞與詞之間的語意相依配對成一組語意相依配對，以建立一基於非結構性資料之語意相依配對模型做為比對回應句之依據。
最後本論文針對所提出之系統進行實驗評估。本實驗利用K-Fold交叉驗證法以及使用者滿意度測驗進行評估系統的正確性和使用者滿意度並與傳統向量空間模型方法做比較。本論文所提出的語意相依配對模型之對話系統的正確性為98.8%、傳統對話系統的正確性為23.4%，而在滿意度的各項指標測驗中，相較於傳統系統，本系統也有較優的滿意度表現。實驗結果顯示具語意相依配對模型之對話系統在回應句產生正確率及使用者滿意度上，均呈現較佳的實驗結果。本論文所提出的對話系統架構應用在負面情緒回應句產生和非結構化資料分析處理上，有顯著的幫助。

In recent years, as spoken dialogue systems have been successfully applied to personal voice assistant services, such as Apple Siri and Google Now, spoken language question-answering (QA) systems are becoming the next stage of intelligent human-machine interfaces. In the past, most of QA systems focused on keyword or sentence matching between the query sentence and the question-answer pairs (QA pairs). However, these systems are unable to provide appropriate answers to the query as the query does not appear in the question-answer pair database. This thesis presents an augmented dialogue system to eliminate the above problems. When the user make a query, the system will first try to find the most suitable answer to the user questions from the QA pair set based on QA matching. When the system is unable to find a suitable answer, the system will use a pre-trained event model and QA semantic dependency pair model to help extract the suitable answer from unstructured documents collected from related websites as the response to the user.
In unstructured document processing, question answering on negative events was selected as the research domain in this thesis. We first collected unstructured articles in the chat rooms and discussion boards from psychological consultation websites and segment the articles into fragments based on the event model. Supervised Latent Dirichlet allocation and delta Bayesian Information Criterion are employed for event detection and segmentation. Second, we use the CKIP Probabilistic Context-free Grammar to parse the questions and all the corresponding answer segments to obtain the semantic dependency graph of questions and answers. Finally, we pair the words and their semantic dependency pair in semantic dependency graph into a set of semantic dependency, and create a matrix with the correlation between question semantic dependency and answer semantic dependency extracted from the unstructured data for response comparison. The answer segment with the highest matching score is selected as the response to the user query
Performance on the proposed method was evaluated. K-Fold cross validation and user satisfaction test were employed and comparison to the traditional vector space model was also performed. The accuracy of the dialogue system with semantic dependency pair model (SDPM-based system) achieved 98.8%, and the accuracy of the traditional vector space model was only 23.4%. In user satisfaction test, the satisfaction score of the SDPM-based system is higher than the traditional system. Experimental results show that the system with semantic dependency pair model obtains better results for response generation and user satisfaction.

[1] R. Khosla and M.-T. Chu, "Embodying care in Matilda: an affective communication robot for emotional wellbeing of older people in Australian residential care facilities," ACM Transactions on Management Information Systems (TMIS), vol. 4, p. 18, 2013.
[2] R. Mashimo, T. Umetani, T. Kitamura, and A. Nadamoto, "Generating Funny Dialogue between Robots based on Japanese Traditional Comedy Entertainment," in Proceedings of the 2014 Conference on Interactive Entertainment, 2014, pp. 1-7.
[3] F. Yamaoka, T. Kanda, H. Ishiguro, and N. Hagita, "How contingent should a communication robot be?," in Proceedings of the 1st ACM SIGCHI/SIGART conference on Human-robot interaction, 2006, pp. 313-320.
[4] I. Rae, L. Takayama, and B. Mutlu, "In-body experiences: embodiment, control, and trust in robot-mediated communication," in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2013, pp. 1921-1930.
[5] M. Shiomi, D. Sakamoto, T. Kanda, C. T. Ishi, H. Ishiguro, and N. Hagita, "A semi-autonomous communication robot: a field trial at a train station," in Proceedings of the 3rd ACM/IEEE international conference on Human robot interaction, 2008, pp. 303-310.
[6] S. Sabanovic, C. C. Bennett, W.-L. Chang, and L. Huber, "PARO robot affects diverse interaction modalities in group sensory therapy for older adults with dementia," in Rehabilitation Robotics (ICORR), 2013 IEEE International Conference on, 2013, pp. 1-6.
[7] K. Darling, "'Who's Johnny?'Anthropomorphic Framing in Human-Robot Interaction, Integration, and Policy," Anthropomorphic Framing in Human-Robot Interaction, Integration, and Policy (March 23, 2015), 2015.
[8] K. M. Colby, Artificial paranoia: A computer simulation of paranoid processes vol. 49: Elsevier, 2013.
[9] J. Weizenbaum, "Computer power and human reason: From judgment to calculation," 1976.
[10] J. Weizenbaum, "ELIZA—a computer program for the study of natural language communication between man and machine," Communications of the ACM, vol. 9, pp. 36-45, 1966.
[11] R. P. Schumaker and H. Chen, "Interaction analysis of the alice chatterbot: A two-study investigation of dialog and domain questioning," Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, vol. 40, pp. 40-51, 2010.
[12] D. Perez-Marin, Conversational Agents and Natural Language Interaction: Techniques and Effective Practices: Techniques and Effective Practices: IGI Global, 2011.
[13] G. De Gasperis, "Building an AIML Chatter Bot Knowledge-Base Starting from a FAQ and a Glossary," Journal of e-Learning and Knowledge Society, vol. 6, 2010.
[14] R. Wallace, "Alice-artificial linguistic internet computer entity-the ALICE AI. foundation," Disponıvel em http://www.alicebot.org. Acesso em, vol. 18, 1995.
[15] S. Kshirsagar, "A multilayer personality model," in Proceedings of the 2nd international symposium on Smart graphics, 2002, pp. 107-115.
[16] Nivas. What Is Siri? Available: http://iphone4ssiri.org/what-is-siri
[17] G. Salton, A. Wong, and C.-S. Yang, "A vector space model for automatic indexing," Communications of the ACM, vol. 18, pp. 613-620, 1975.
[18] G. Salton and C.-S. Yang, "On the specification of term values in automatic indexing," Journal of documentation, vol. 29, pp. 351-372, 1973.
[19] W. Zhang, T. Yoshida, and X. Tang, "A comparative study of TF* IDF, LSI and multi-words for text classification," Expert Systems with Applications, vol. 38, pp. 2758-2765, 2011.
[20] C.-R. Huang, F.-Y. Chen, K.-J. Chen, Z.-m. Gao, and K.-Y. Chen, "Sinica Treebank: design criteria, annotation guidelines, and on-line interface," in Proceedings of the second workshop on Chinese language processing: held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics-Volume 12, 2000, pp. 29-37.
[21] D. M. Blei, A. Y. Ng, and M. I. Jordan, "Latent dirichlet allocation," the Journal of machine Learning research, vol. 3, pp. 993-1022, 2003.
[22] D. Ramage, D. Hall, R. Nallapati, and C. D. Manning, "Labeled LDA: A supervised topic model for credit attribution in multi-labeled corpora," in Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1-Volume 1, 2009, pp. 248-256.
[23] M. Riedl and C. Biemann, "Text segmentation with topic models," Journal for Language Technology and Computational Linguistics, vol. 27, pp. 47-69, 2012.
[24] H. Misra, F. Yvon, J. M. Jose, and O. Cappe, "Text segmentation via topic modeling: an analytical study," in Proceedings of the 18th ACM conference on Information and knowledge management, 2009, pp. 1553-1556.
[25] A. Tritschler and R. A. Gopinath, "Improved speaker segmentation and segments clustering using the bayesian information criterion," in Eurospeech, 1999, pp. 679-682.
[26] C.-H. Wu, Y.-H. Chiu, C.-J. Shia, and C.-Y. Lin, "Automatic segmentation and identification of mixed-language speech using delta-BIC and LSA-based GMMs," Audio, Speech, and Language Processing, IEEE Transactions on, vol. 14, pp. 266-276, 2006.
[27] S. Seneff, "Response planning and generation in the MERCURY flight reservation system," Computer Speech & Language, vol. 16, pp. 283-312, 2002.
[28] K. van Deemter, E. Krahmer, and M. Theune, "Real vs. Template-Based Natural Language Generation: A False Opposition," May I Speak Freely.
[29] A. M. Neves, F. A. Barros, and C. Hodges, "iAIML: A mechanism to treat intentionality in AIML chatterbots," in Tools with Artificial Intelligence, 2006. ICTAI'06. 18th IEEE International Conference on, 2006, pp. 225-231.
[30] S. Busemann and H. Horacek, "A flexible shallow approach to text generation," arXiv preprint cs/9812018, 1998.
[31] J. Jia, "CSIEC: A computer assisted English learning chatbot based on textual knowledge and reasoning," Knowledge-Based Systems, vol. 22, pp. 249-255, 2009.
[32] C. Shah and J. Pomerantz, "Evaluating and predicting answer quality in community QA," in Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval, 2010, pp. 411-418.
[33] J. A. Gliem and R. R. Gliem, "Calculating, interpreting, and reporting Cronbach’s alpha reliability coefficient for Likert-type scales," 2003.
[34] Z. Song, S. Zhang, and C. P. Clarke, "Library anxiety among Chinese students: Modification and application of LAS in the context of Chinese academic libraries," The Journal of Academic Librarianship, vol. 40, pp. 55-61, 2014.