知識本體是一種用來保存知識的型式，在很多相關領域上，可以利用知識本體作為外部資源，幫助其他系統提高效能或是正確率。知識本體中包含許多相關的研究領域，像是知識本體擴充、知識本體充實化、知識本體衝突解析等等，這些領域統稱為知識本體學習，本論文著重於知識本體擴充，希望可以開發一個自動擴充知識本體的系統，盡可能減少人工定義獲取知識本體的規則。
本論文的主題是知識本體擴充，包含兩個部分，分別是以神經網路自動化地擴充知識本體和透過主動學習進一步評估與擴充知識本體。在自動擴充知識本體的系統中，我們透過改良字元層級編碼的命名實體辨別模型擷取一句話中會成為知識本體概念的詞彙，再利用多層的感知器網路，判斷兩兩命名實體的關係，由於各種關係和命名實體有相依的關係，所以我們分析了命名實體和關係之間的分布，藉由這個分布濾除正確率比較低的命名實體組合。主動學習的部分，本論文提出三種演算法，包含不確定性評估、規則配對和高相關性評估，藉由不確定性評估確定那些比較不確定的三元體是否正確，另外兩個方法則是對那些已經被模型認證為正確的三原體，進行推論產生三元體，然後確認推論的三元體是否正確。
本論文收集了1,268篇文章，以這些文章作為輸入，讓系統自動擴充知識本體，並且由主題偵測這個任務來評估擴充的知識本體是否有效。本論文提出的方法能自動抓出文章中蘊含有知識的三元體，這些抓下來的三元體中有74.59%是正確的。此外這些三元體對於主題偵測也有能在五次交叉驗正的設定下比有標記的隱含狄利克雷分布模型還要準確約2%。

Ontology is a kind of representation which is used to save the knowledge. It can be used as the external resource to improve the system’s performance or accuracy in many domains and research. Ontology has many related research areas, including ontology population, ontology enrichment and inconsistency resolution. These research areas have a general name, Ontology Learning. This thesis is focused on the ontology population. We aim to develop a system to populate the ontology automatically and avoid to manually define the rules.
The purpose of this thesis is the ontology population which includes two parts, automatic population of the ontology with neural networks and population based on active learning. In the system of automatic ontology population, we use the named entity recognition model with the improved character-level embedding to extract the terms from a sentence, which may be the concepts in the ontology. Then, we use a multi-layered perception network to decide the predicates between the pairs of named entities. Because of the dependency relations between the named entities and the predicates, we analyze the distribution between them. According to the distribution, we filter out the low accuracy combinations. For active learning, the study proposes three algorithms, including uncertainty estimation, rule matching, and high correlation evaluation. Using uncertainty estimation to ensure the uncertain triples. Another two methods are used to induce the triples with the certain triples and confirm the induced triples by active learning.
We collected 1,268 documents for evaluation of the proposed method. The system automatically populates the ontology based on the documents. Topic detection is selected as the task to evaluate the effectiveness of the populated ontology. From the experimental results, the proposed method can extract the triples among the documents, and 74.59% of triples are correct. In addition, the populated triples are beneficial to improve the topic detection performance. The accuracy of our system is 2 percent higher the baseline model, labeled LDA.

[1] J. Z. Pan, "Resource Description Framework," in Handbook on Ontologies Berlin, Heidelberg: Springer Berlin Heidelberg, 2009, pp. 71-90.
[2] D. Beckett. (2014). RDF 1.1 N-Triples, A line-based syntax for an RDF graph. Available: https://www.w3.org/TR/2014/REC-n-triples-20140225/
[3] P. Buitelaar, P. Cimiano, and B. Magnini, "Ontology learning from text: An overview," Ontology learning from text: Methods, evaluation and applications, vol. 123, pp. 3-12, 2005.
[4] G. Petasis, V. Karkaletsis, G. Paliouras, A. Krithara, and E. Zavitsanos, "Ontology population and enrichment: State of the art," in Knowledge-driven multimedia information extraction and ontology evolution, 2011, pp. 134-166.
[5] S. Castano, I. S. E. Peraldi, A. Ferrara, V. Karkaletsis, A. Kaya, R. Möller, S. Montanelli, G. Petasis, and M. Wessel, "Multimedia interpretation for dynamic ontology evolution," Journal of Logic and Computation, vol. 19, no. 5, pp. 859-897, 2008.
[6] O. Etzioni, M. Cafarella, D. Downey, S. Kok, A.-M. Popescu, T. Shaked, S. Soderland, D. S. Weld, and A. Yates, "Web-scale information extraction in knowitall:(preliminary results)," in Proceedings of the 13th international conference on World Wide Web, 2004, pp. 100-110.
[7] P. Haase, F. Van Harmelen, Z. Huang, H. Stuckenschmidt, and Y. Sure, "A framework for handling inconsistency in changing ontologies," in International semantic web conference, 2005, pp. 353-367.
[8] N. F. Noy and D. L. McGuinness, "Ontology Development 101: A Guide to Creating Your First Ontology," 2001, Available: http://www-ksl.stanford.edu/people/dlm/papers/ontology-tutorial-noy-mcguinness-abstract.html.
[9] Y. Jang, J. Ham, B.-J. Lee, Y. Chang, and K.-E. Kim, "Neural dialog state tracker for large ontologies by attention mechanism," in Spoken Language Technology Workshop (SLT), 2016, pp. 531-537.
[10] N. Mehta, R. Gupta, A. Raux, D. Ramachandran, and S. Krawczyk, "Probabilistic ontology trees for belief tracking in dialog systems," in Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2010, pp. 37-46.
[11] S. Auer, C. Bizer, G. Kobilarov, J. Lehmann, R. Cyganiak, and Z. Ives, "DBpedia: A Nucleus for a Web of Open Data," Berlin, Heidelberg, 2007, pp. 722-735.
[12] R. Speer and C. Havasi, "Representing General Relational Knowledge in ConceptNet 5," in LREC, 2012, pp. 3679-3686.
[13] J. P. Chiu and E. Nichols, "Named entity recognition with bidirectional LSTM-CNNs," arXiv preprint arXiv:1511.08308, 2015.
[14] G. Lample, M. Ballesteros, S. Subramanian, K. Kawakami, and C. Dyer, "Neural architectures for named entity recognition," arXiv preprint arXiv:1603.01360, 2016.
[15] E. Strubell, P. Verga, D. Belanger, and A. McCallum, "Fast and accurate entity recognition with iterated dilated convolutions," in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017, pp. 2670-2680.
[16] W. Yin, K. Kann, M. Yu, and H. Schütze, "Comparative study of cnn and rnn for natural language processing," arXiv preprint arXiv:1702.01923, 2017.
[17] F. M. H. Fernandez and R. Ponnusamy, "Automated populates and updates personalized ontology with analysis result," 2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies, pp. 580-585, 2014.
[18] J. Makki, "Ontoprima: a Prototype for Automating Ontology Population," International Journal of Web & Semantic Technology, vol. 8, no. 5, 2017.
[19] M. A. Hearst, "Automatic acquisition of hyponyms from large text corpora," in Proceedings of the 14th conference on Computational linguistics-Volume 2, 1992, pp. 539-545.
[20] B. Settles, "Active learning," Synthesis Lectures on Artificial Intelligence and Machine Learning, vol. 6, no. 1, pp. 1-114, 2012.
[21] R. D. King, K. E. Whelan, F. M. Jones, P. G. Reiser, C. H. Bryant, S. H. Muggleton, D. B. Kell, and S. G. Oliver, "Functional genomic hypothesis generation and experimentation by a robot scientist," Nature, vol. 427, no. 6971, p. 247, 2004.
[22] S. Dasgupta, D. J. Hsu, and C. Monteleoni, "A general agnostic active learning algorithm," in Advances in neural information processing systems, 2008, pp. 353-360.
[23] A. G. Hauptmann, W.-H. Lin, R. Yan, J. Yang, and M.-Y. Chen, "Extreme video retrieval: joint maximization of human and computer performance," in Proceedings of the 14th ACM international conference on Multimedia, 2006, pp. 385-394.
[24] B. Fortuna, M. Grobelnik, and D. Mladenić, "Semi-automatic data-driven ontology construction system," 2006.
[25] F. Shi, J. Li, J. Tang, G. Xie, and H. Li, "Actively learning ontology matching via user interaction," in International Semantic Web Conference, 2009, pp. 585-600.
[26] N. Astrakhantsev, D. Fedorenko, and D. Turdakov, "Automatic enrichment of informal ontology by analyzing a domain-specific text collection," in Computational Linguistics and Intellectual Technologies: Papers from the Annual International Conference “Dialogue, 2014, vol. 13, pp. 29-42.
[27] M. Yoshida and H. Nakagawa, "Automatic term extraction based on perplexity of compound words," in International Conference on Natural Language Processing, 2005, pp. 269-279.
[28] R. Iqbal, M. A. A. Murad, A. Mustapha, and N. M. Sharef, "An ontology development approach using concept maps driven by automatic term extraction," International Journal of Information and Communication Technology, vol. 10, no. 1, pp. 51-65, 2017.
[29] C. Wang and X. He, "Chinese hypernym-hyponym extraction from user generated categories," in Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, 2016, pp. 1350-1361.
[30] S. Pradhan, A. Moschitti, N. Xue, O. Uryupina, and Y. Zhang, "CoNLL-2012 shared task: Modeling Multilingual Unrestricted Coreference in OntoNotes," presented at the Joint Conference on EMNLP and CoNLL - Shared Task, Jeju, Republic of Korea, 2012.
[31] J. Sun, "‘Jieba’Chinese word segmentation tool," 2012.
[32] T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, "Distributed representations of words and phrases and their compositionality," in Advances in neural information processing systems, 2013, pp. 3111-3119.
[33] 沈紅蓮 and 朱邦復, 第五代倉頡輸入法手册. 博碩文化股份有限公司, 2006.
[34] 中文檢字表. Available: http://www.cclookup.com/
[35] F. Rosenblatt, "The perceptron: a probabilistic model for information storage and organization in the brain," Psychological review, vol. 65, no. 6, p. 386, 1958.
[36] R. Socher, D. Chen, C. D. Manning, and A. Ng, "Reasoning with neural tensor networks for knowledge base completion," in Advances in neural information processing systems, 2013, pp. 926-934.
[37] Q. Hu and Y. Luo, "The design and implementation of topic detection based on domain ontology," 2014.
[38] J.-F. Yeh, Y.-S. Tan, and C.-H. Lee, "Topic detection and tracking for conversational content by using conceptual dynamic latent Dirichlet allocation," Neurocomputing, vol. 216, pp. 310-318, 2016.