人類在學習語言與知識過程中，建構與推論概念間的關聯是個很重要的步驟，本論文藉由觀察到幼兒學習知識概念的方式，透過本身具備的已知但少量的概念詞彙推論未知概念，得到建構概念詞彙推論流程與推論模組的靈感，進而提出三個研究問題面向進行探索，分別為：(1)概念萃取的可行性、(2)概念推論方法的適切性、(3)捕捉概念變異。依據研究問題面向的探索，本研究設計出一概念詞彙推論系統與推論邏輯對應方法，達到以運算方式來建構出類似人們對於概念詞彙聯想，延伸與跳躍等多樣化的概念詞彙。由實驗的案例可以發現，推論邏輯方法以評估方法所呈現的數值分析結果，推論平均成效為本研究提出的動態群集串聯方法(Dynamic Clustering Combination)與資訊檢索方法優於一般群集法，但若以文字概念詞彙分析結果而言，動態群集串聯方法更能夠表現出本研究目標的成果。

In the learning process of language and knowledge, the construction and inference of the relations of concepts are very important steps. This paper is motivated by observing the inferences process from that children have their own, few and known conceptual vocabulary to generate unknown concepts. Then, three aspects are included to explore this conceptual vocabulary inference module. They are (1) the feasibility of concept extraction, (2) the appropriateness of concept inference methods, and (3) the capturing of concept variations. This research has conducted a concept vocabulary inference system and inference logic correspondence method to achieve the construction of a variety of conceptual vocabulary similar to people's association, extension and jumping of conceptual vocabulary by a computational approach. In experimental results, the average performance of concept inference of the proposed Dynamic Clustering Combination and the retrieval-based combination approaches are better than the ones of general clustering methods. Moreover, our proposed approach can reach the practical diversity of concept extension.

[1] R. Kuhn, R. De Mori, “A Cache-based Natural Language Model for Speech Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 6, pp. 570-583, 1990.
[2] J. Andreas, A. Vlachos, S. Clark, “Semantic Parsing as Machine Translation,” Association for Computational Linguistics, Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics , Volume 2: Short Papers, pp. 47-52, 2013.
[3] V. Pham, et al., “Dropout Improves Recurrent Neural Networks for Handwriting Recognition,” Proceedings of the 14th International Conference on Frontiers in Handwriting Recognition, 2014.
[4] E. Cambria, B.White, “Jumping NLP Curves: A Review of Natural Language Processing Research,” IEEE ComputatIonal Intellgence Magazine, pp. 48-57, 2014.
[5] Wikipedia contributors. “林奕含. ” 維基百科, 自由的百科全書. Accessed on 15 Jun., 2015 [Internet]. Available: https://zh.wikipedia.org/wiki/%E6%9E%97%E5%A5%95%E5%90%AB
[6] G. Rickheit, W. Schnotz, H. Strohner, “The Concept of Inference in Discourse Comprehension,” Advances in Psychology, pp. 3-49, 1985.
[7] S. Hinduja, JW. Patchin, “Bullying, Cyberbullying, and Suicide,” Journal of Archives of Suicide Research, vol. 14, no. 3, pp. 206-221, 2010.
[8] R. Slonje, A. Frisen, A. Frisen, P. K Smith, “The Nature of Cyberbullying, and Strategies for Prevention,” Computers in Human Behavior, 2012
[9] G. Kwan, M. Skoric, “Facebook Bullying: An Extension of Battles in School,” Computers in Human Behavior, vol. 29, no. 1, pp. 16-25, 2013.
[10] S. Menini, G. Moretti, et al., “A System to Monitor Cyberbullying Based on Message Classification and Social Network Analysis,” Proceedings of the Third Workshop on Abusive Language Online, pages 105–110, 2019.
[11] W. He, S. Zhab, L. Lia, “Social Media Competitive Analysis and Text Mining: A Case Study in the Pizza Industry,” International Journal of Information Management, vol. 33, no. 3, pp. 464-472, 2013.
[12] M. Mostafa, “More than Words: Social Networks’ Text Mining for Consumer Brand Sentiments,” Expert Systems with Applications, vol. 40, pp. 4241-4251, 2013.
[13] R. Lu, H. Tsao, et al., “Sentiment Analysis of Brand Personality Positioning Through Text Mining,” Proceedings of Journal of Information Technology Research(JITR), vol. 12, 2019.
[14] K. Shu, A. Sliva, S. Wang, et al., “Fake News Detection on Social Media: A Data Mining Perspective,” Special Interest Group on Knowledge Discovery and Data Mining (SIGKDD) Explorations, vol. 19, no. 1, pp. 22-36, 2016.
[15] H. Allcott, M. Gentzkow, “Social Media and Fake News in the 2016 Election,” Proceedings of Journal of Economic Perspectives, vol. 31, pp. 211-236, 2017.
[16] L. Wang, Y. Wang, G. de Melo, G. Weikum, "Five Shades of Untruth: Finer-Grained Classification of Fake News," IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 593-594, 2018.
[17] S. Kai, W. Suhang, L. Huan, “Beyond News Contents: The Role of Social Context for Fake News Detection,” Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining(WSDM), pp.312-320, 2019.
[18] M. Halvey, M. Keane , “An Assessment of Tag Presentation Techniques,” Proceedings of the international conference on World Wide Web (WWW), pp.1313-1314, 2007.
[19] M. Allahyari, S. Pouriyeh, et al., “A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques,” Proceedings of Knowledge Discovery and Data Mining(KDD) Bigdas, 2017.
[20] M. Hearst, “Untangling Text Data Mining,” Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics (ACL), pp.3-10 , 1999.
[21] U. Fayyad, G. Piatetsky-Shapiro, P. Smyth, “From Data Mining to Knowledge Discovery in Databases”, AIMagazine, vol. 17, no. 3, p. 37, 1996.
[22] U. Fayyad, G. Piatetsky-Shapiro, P. Smyth, “Knowledge Discovery and Data Mining: Towards a Unifying Framework,” Proceedings of Knowledge Discovery and Data Mining(KDD), vol. 96, pp. 82-88, 1996.
[23] W. J. Frawley, G. Piatetsky-Shapiro, and C. J. Matheus, “Knowledge Discovery in Databases: An Overview”, AIMag, vol. 13, no. 3, p. 57, 1992.
[24] Z. S. Harris,” Distributional Structure”, Proceedings of Journal of WORD, vol.10, pp.146-162, 1954.
[25] Y. Fu, Y Feng, and J. Cunningham,”Paraphrase Generation with Latent Bag of Words”, Neural Information Processing Systems, 2019.
[26] E. Cambria and A. Hussain, “Sentic Computing: Techniques, Tools, and Applications”, SpringerBriefs in Cognitive Computation book series,volume 2, 2012.
[27] M. Wrzalik and D. Krechel, "Balanced Word Clusters for Interpretable Document Representation," International Conference on Document Analysis and Recognition Workshops (ICDARW), pp. 103-109, 2019.
[28] P. Li, K. Mao, Y. Xu, Q. Li, J. Zhang, “Bag-of-Concepts representation for document classification based on automatic knowledge acquisition from probabilistic knowledge base”, Knowledge-Based Systems, 2020.
[29] C. Snigdha, P. Haoruo, R. Dan, “Story Comprehension for Predicting What Happens Next,” Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP)", pp. 1603-1614, 2017.
[30] F. Michael, S. Swapna, “Sentiment Analysis and Lexical Cohesion for the Story Cloze Task,” Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics, pp. 62-67, 2017.
[31] Sun Junyi, ”jieba中文分詞”. Accessed on Sep. 23, 2015[Online]. Available: https://github.com/fxsjy/jieba
[32] W. Ma, K. Chen, “A bottom-up merging algorithm for Chinese unknown word extraction,” Proceedings of the second SIGHAN workshop on Chinese language processing, pp.31-38, 2003.
[33] S. P. Mehdi Allahyari, M. Assefi, S. Safaei, et al., “A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques,” Proceedings of Knowledge Discovery and Data Mining(KDD) Bigdas, 2017.
[34] H. Kim, H. Kyul Kim, S. Cho, “Rening Initial Points for K-Means Clustering,” Proceedings of the Fifteenth International Conference on Machine Learning(ICML), pp. 91-99, 1998.
[35] G. Hamerly, C. Elkan, “Alternatives to the K-means Algorithm that Find Better Clusterings,” Proceedings of the eleventh international conference on Information and knowledge management (CIKM), 2002.
[36] D. Lin, X. Wu, “Phrase Clustering for Discriminative Learning,” Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, vol. 2, pp. 1030-1038, 2009.
[37] C. Manning, P. Raghavan, H. Schutze, “Introduction to Information Retrieval,” Cambridge University Press, 2008.
[38] K. Chan, W. Ke, and S. Im, “Probability K-means Clustering for Neural Network Architecture,” Proceedings of International Conference on Advances in Artificial Intelligence (ICAAI), pp. 52-57, 2019.
[39] M. Rana1, R Afrin, et al., “Concept Extraction from Ambiguous Text Document using K-means”, International Research Journal of Engineering and Technology (IRJET), vol 6, pp. 5317-5330, 2019.