由於直接從對話語句中建立情緒模型給對話代理人的困難性，我們提出一個兩階段的方法，藉由在對話文字語句中將詞彙對應至它們的論旨角色，再根據論旨資訊從對話語句中推理其內含的情緒。因此，在本研究中，我們著重於學習分類問題：一個是根據句法結構資訊與語句的詞彙特徵來指派論旨角色，一個是根據語句中指派的論旨角色資訊來偵測情緒。我們結合了適性提升與類神經網路的學習方法來訓練兩個分類器。實驗結果顯示適性提升在這兩項工作上都有很好的表現。

Due to the difficulties of building emotion model for a dialogue agent directly from a dialogue sentence, we propose a two stage by mapping words in a dialogue text sentence into thematic their roles and then inferring the embedded emotion from the dialogue sentence based on the thematic information. Therefore, in this thesis, we focus on the learning classification problems: one is the thematic role assignment based on syntactic structure information and features of words of a sentence and the other the emotion detection based on thematic role information assigned to a sentence. We integrate AdaBoost and neural networks learning approaches to train the two classifiers. Our experiments showed that AdaBoost makes a good performance in these two tasks.

[1] Yoav Freund and Robert E. Schapire, “A Decision-theoretic Generalization of On-line Learning and an Application to Boosting,” Journal of Computer and System Sciences, 55(1):119–139, August 1997.
[2] Y Freund and R. E. Schapire, “Game Theory, On-line Prediction and Boosting,” Proceedings of the Ninth Annual Conference on Computational Learning Theory, pages 325-332, Desenzano del Garda, Italy, 1996.
[3] Yoav Freund and Robert E. Schapire, “A Short Introduction to Boosting,” Journal of Japanese Society for Artificial Intelligence, Vol. 14, No. 5, pp771-780, September, 1999.
[4] Zhang Bin and Jin Lianwen, “Handwritten Chinese Similar Characters Recognition Based On AdaBoost,” Proceedings of the 26th Chinese Control Conference, 2007.
[5] Shao Jinbo, Li Xiu, and Liu Wenhuang, “The Application of AdaBoost in Customer Churn Prediction,” International Conference on Service Systems and Service Management, Vol. 2, 2007.
[6] Tianzhong Zhao, Jianjiang Lu, Yafei Zhang, Qi Xiao, and Weiguang Xu, “Classifier Ensemble Based-on AdaBoost and Genetic Algorithm for Automatic Image Annotation,” International Conference on Information and Automation, Vol. 4, 2008.
[7] Yuanzhong Li and Wataru Ito, “Shape Parameter Optimization for Adaboosted Active Shape Model,” Tenth IEEE International Conference on Computer Vision, Volume 1, 2005.
[8] Koong H. C. Lin and Von-Wun Soon, “Hypothesis Scoring over Theta Grids Information in Parsing Chinese Sentences with Serial Verb Constructions,” International Conference On Computational Linguistics, 1994.
[9] Tung-Bo Chen, Koong H.C. Lin, and Von-Wun Soo, “Training Recurrent Neural Networks to Learn Lexical Encoding and Thematic Role Assignment in Parsing Mandarin Chinese Sentences,” International Journal of Neurocomputing, 1997.
[10] Jeffrey L. Elman, “Finding Structure in Time,” Cognitive Science, 1990.
[11] J. L. G. Rosa, “A Hybrid Symbolic-Connectionist Processor of Natural Language Semantic Relations,” Proceedings of the IEEE Workshop on Hybrid Intelligent Models and Applications, 2009.
[12] A. S. D’avila Garcez, K. Broda, and D. M. Gabbay, “Symbolic Knowledge Extraction from Trained Neural Networks: a Sound Approach,” Artificial Intelligence, Volume 125, 2001.
[13] K.H.C. Lin, Rey-Long Liu, and Von-Wun Soo, “Interactive Acquisition of Thematic Information of Chinese Verbs for Judicial Verdict Document Understanding Using Templates, Syntactic Clues, and Heuristics,” Third International Conference on Document Analysis and Recognition, Vol. 1, 1995.
[14] R.J. Dolan. Emotion, “Cognition and Behavior,” Science, Vol. 298, No. 5596, pp. 1191-1194, 2002.
[15] Cheng-Yu Lu, Jen-Shin Hong, and Samuel Cruz-Lara, “Emotion Detection in Textual Information by Semantic Role Labeling and Web Mining Techniques,” Third Taiwanese-French Conference on Information Technology, 2006.
[16] Chung-Hsien Wu, Ze-Jing Chuang, and Yu-Chung Lin, “Emotion Recognition from Text Using Semantic Labels and Separable Mixture Models,” ACM Transactions on Asian Language Information Processing, Volume 5, 2006.
[17] Z. Teng, F. Ren, and S. Kuroiwa, “Recognition of Emotion with SVMs,” Lecture Notes in Computer Sciences, 2006.
[18] C. Yang, K. H.-Y. Lin, and H.-H. Chen, “Emotion Classification Using Web Blog Corpora,” Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence, 2007.
[19] Alena Neviarouskaya, Helmut Prendinger, and Mitsuru Ishizuka, “Recognition of Affect Conveyed by Text Messaging in Online Communication,” Proceedings of 2nd International Conference on Online Communities and Social Computing, 2007.
[20] L. Devillers, L. Lamel, and I. Vasilescu, “Emotion Detection in Task-oriented Spoken Dialogues,” Proceedings of the International Conference on Multimedia and Expo, Volume 3, 2003.
[21] Karthi, M. Rizon, Y. Sazali, R. Nagarajan, D. Hazry, M. Sugisaka, and M. Rozailan, “Fuzzy Clustering for Genetic Algorithm Based Optimized Ellipse Data in Classifying Face Emotion,” Proceedings of the International Conference on Control, Automation and Systems, 2007.
[22] Edward Chao-Chun Kao, Chun-Chieh Liu, Ting-Hao Yang, Chang-Tai Hsieh, and Von-Wun Soo, “Towards Text-based Emotion Detection,” International Conference on Information Management and Engineering, 2009.
[23] J. C. Ang, “Prosodic Cues for Emotion Recognition in Communicator Dialogs,” M.S. thesis, University of California Berkeley, 2002.
[24] Gilly Leshed and Joseph Jofish Kaye, “Understanding How Bloggers Feel: Recognizing Affect in Blog Posts,” Proceedings of CHI 2006 Extended Abstracts on Human Factors in Computing Systems, 2006.
[25] Mei et al, “TongyiciCilin Thesaurus,” Commercial Press, 1996.
[26] Academia Sinica, “Academia Sinica Balanced Corpus of Modern Chinese,” Website, 2001. http://dbo.sinica.edu.tw/SinicaCorpus/
[27] Ting-chi Tang, “漢語詞法句法四集,” 學生書局, 1992.
[28] Mark Hall, Eibe Frank, Geoffrey Holmes, Bernhard Pfahringer, Peter Reutemann, and Ian H. Witten, “The WEKA Data Mining Software,” SIGKDD Explorations, Volume 11, 2009.
[29] A. Ortony, G. Clore and A. Collins. “The Cognitive Structure of Emotions,” Cambridge: Cambridge University Press, 1988.
[30] Jaree Thongkam, Guandong Xu, and Yanchun Zhang, “AdaBoost Algorithm with Random Forests for Predicting Breast Cancer Survivability,” Proceedings of the International Joint Conference on Neural Networks, 2008.