本文的研究主題為人物互動關係之探索，我們試圖識別社交媒體中提到的不同人物之間的互動關係，藉此幫助讀者建構出在某個主題下，不同人物之間的關係背景，加快讀者理解不同主題的文本內容。此研究基於 Chang et al.提出的傳統內核方法，我們以深度學習方法做改良，並將傳統的自然語言特徵與樹結構融合進神經網路模型中，其中利用了實體嵌入、豐富互動樹嵌入、詞性嵌入、句子類別和依賴特徵，藉此完成人物互動關係探索中的兩個任務－關係偵測任務與關係擷取任務，另外我們還對多任務模型進行探討，希望透過兩任務模型之間的互相輔助來提升彼此的效能，我們的方法在關係偵測任務中，最終在F1分數上超越了原作者論文約7%，達到了中文人物互動關係偵測到目前為止最好的效能表現，同時我們實作了原作者論文中所沒有實作的關係擷取任務，並且在效能方面有不錯的表現，這對於建構人物互動網絡的知識庫很有用。

The research topic of this paper is person interaction discovery. We are trying to identify interactions between different people mentioned in social media. To help readers construct a relationship between people under a certain topic, so that readers can quickly understand the text content of different topics. This study is based on the traditional kernel method proposed by Chang et al. We use the deep learning method to improve and integrate the traditional natural language features and tree structure into the neural network model. It utilizes entity embedding, rich interactive tree embedding, part of speech embedding, sentence categories, and dependency features. In this way, two tasks in the person interaction discovery - relation detection task and relation extraction task are completed. In addition, we also explore the multitasking model and hope to improve each other''s effectiveness through mutual assistance between task models. Our method in the relation detection task, eventually surpassed the original author''s paper by about 7% on the F1 score. At the same time, we have implemented a relation extraction model which the original author didn''t implement. It demonstrates superior performances on the person interaction extraction task. This is useful for building a knowledge base for people''s interactive networks.

口試委員會審定書 #
誌謝 i
摘要 iii
ABSTRACT iv
CONTENTS v
LIST OF FIGURES viii
LIST OF TABLES x
Chapter 1 緒論 1
1.1 研究目的與動機 1
1.2 研究主題 1
1.3 章節概要 3
Chapter 2 相關文獻探討 4
2.1 人物互動關係探索 4
2.2 深度學習 (Deep Learning) 6
2.2.1 遞歸神經網路 (Recurrent Neural Network, RNN) 6
2.2.2 卷積神經網路 (Convolutional Neural Network, CNN) 8
2.3 關係擷取 (Relation Extraction) 9
2.4 依賴特徵 (Dependency Feature) 11
2.5 無領域限制的資訊擷取 (Open Information Extraction, Open IE) 11
Chapter 3 人物互動關係探索模型 14
3.1 人物實體標籤取代 15
3.2 雙向長短期記憶模型 16
3.3 導入句法特徵 17
3.3.1 實體嵌入 17
3.3.2 豐富互動樹嵌入 18
3.3.3 詞性嵌入 23
3.4 結合句法相依關係之人物互動關係偵測 23
3.5 人物互動關係擷取方法 26
Chapter 4 實驗結果與討論 29
4.1 資料集與設定 29
4.1.1 人際互動關係資料集 29
4.1.2 詞嵌入 31
4.1.3 實驗評估指標 31
4.2 偵測方法實驗與討論 33
4.2.1 人物實體標籤取代 33
4.2.2 字詞過濾與遞歸神經網路 33
4.2.3 遞歸神經網路結合卷積神經網路 34
4.2.4 句法與句義特徵 36
4.2.5 門檻值調整 37
4.2.6 效能比較 37
4.3 擷取方法實驗與討論 38
4.3.1 效能比較 38
4.4 多任務模型實驗與討論 39
4.5 錯誤分析 43
Chapter 5 結論與未來展望 46
REFERENCE 47

[1]Yung-Chun Chang, C. C. Chen, and W. Hsu. 2016. SPIRIT: A tree kernel-based method for topic person interaction detection. IEEE Transactions on Knowledge and Data Engineering, 28(9):2494–2507.
[2]Yung-Chun Chang, Chien Chin Chen, and Wen-Lian Hsu, "A Composite Kernel Approach for Detecting Interactive Segments in Chinese Topic Documents," the 9th Asia Information Retrieval Societies Conference (AIRS 2013), Lecture Notes in Computer Science, pages 215-226, December 2013.
[3]Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matthew Gardner, Christopher T Clark, Kenton Lee, and Luke S. Zettlemoyer. 2018. Deep contextualized word representations. CoRR, abs/1802.05365.
[4]Cai, R., Zhang, X., Wang, H.. Bidirectional Recurrent Convolutional Neural Network for Relation Classification. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016) 2016;:756–765.
[5]Chia-Wei Wu, Shyh-Yi Jan, Tzong-Han Tsai, Wen-Lian Hsu, “On Using Ensemble Methods for Chinese Named Entity Recognition”, Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing, Sydney, July 2006, pp. 142–145.
[6]Zhiheng Huang, Wei Xu, and Kai Yu. 2015. Bidirectional lstm-crf models for sequence tagging. arXiv preprint arXiv:1508.01991.
[7]C. C. Chen and M. C. Chen. 2012. TSCAN: A content anatomy approach to temporal topic summarization. IEEE Transactions on Knowledge and Data Engineering, 24(1):170–183.
[8]Ao Feng and James Allan. 2007. Finding and linking incidents in news. In Proceedings of the Sixteenth ACM Conference on Conference on Information and Knowledge Management, CIKM ’07, pages 821–830, New York, NY, USA. ACM
[9]R. Nallapati, A. Feng, F. Peng, and J. Allan, “Event threading within news topics,” in Proc. 13th ACM Int. Conf. Inf. Knowl. Manag., 2004, pp. 446–453.
[10]Zhong-Yong Chen and Chien Chin Chen. 2016. SCIFNET: Stance community identification of topic persons using friendship network analysis. Knowledge-Based Systems, 110:30 – 48
[11]Ramesh Nallapati, Ao Feng, Fuchun Peng, and James Allan. 2004. Event threading within news topics. In Proceedings of the Thirteenth ACM International Conference on Information and Knowledge Management, CIKM ’04, pages 446–453, New York, NY, USA. ACM.
[12]Z. Dmitry, A. Chinatsu, and R. Anthony, “Kernel methods for relation extraction,” The J. Mach. Learn. Res., vol. 3, pp. 1083–1106, 2003.
[13]G. D. Zhou, J. Su, J. Zhang, and M. Zhang, “Exploring various knowledge in relation extraction,” in Proc. 43th Annu. Meeting Assoc. Comput. Linguistics, 2005, pp. 427–434.
[14]J. Jiang and C. Zhai, “A systematic exploration of the feature space for relation extraction,” in Proc. Hum. Lang. Technol.: The Conf. North Amer Ch. Assoc. Comput. Linguistics, 2007, pp. 113–120.
[15]M. Zhang, G. D. Zhou, and A. Aw, “Exploring syntactic structured features over parse trees for relation extraction using kernel methods,” Inf. Process. Manag., vol. 44, pp. 687–701, 2008.
[16]A. Moschitti, “A study on convolution kernels for shallow semantic parsing,” in Proc. 42nd Annu. Meeting Assoc. Comput. Linguistics, 2004, pp. 21–26.
[17]M. Collins and N. Duffy, “Convolution kernels for natural language,” in Proc. Annu. Conf. Neural Inf. Proc. Syst., 2001, pp. 625–632.
[18]Yang Liu, Furu Wei, Sujian Li, Heng Ji, Ming Zhou, and Houfeng Wang. 2015. A dependency-based neural network for relation classification. In Proceedings of the 53rd Annual Meeting of the Association for Computational Joint Conference on Natural Language Processing and the 7th International Joint Conference on Natural Language Processing, pages 285–290.
[19]Yan Xu, Lili Mou, Ge Li, Yunchuan Chen, Hao Peng, and Zhi Jin. 2015b. Classifying relations via long short term memory networks along shortest dependency paths. In Proceedings of Conference on Empirical Methods in Natural Language Processing,, pages 1785–1794
[20]Michele Banko, Michael J. Cafarella, Stephen Soderland, Matt Broadhead, and Oren Etzioni. 2007. Open information extraction from the web. In Proceedings of the 20th International Joint Conference on Artifical Intelligence, pages 2670–2676, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc.
[21]S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997
[22]Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, November 1998.
[23]Yoon Kim. 2014. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 1746–1751. ACL.
[24]Christina Niklaus, Matthias Cetto, André Freitas, and Siegfried Handschuh. 2018. A survey on open information extraction. In Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
[25]Asch, V.V. 2013. Macro-and micro-averaged evaluation measures [[BASIC DRAFT]].
[26]Miwa, M., & Bansal, M. 2016. End-to-end relation extraction using LSTMs on sequences and tree structures. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 1105–1116). Berlin, Germany.
[27]Cicero dos Santos, Bing Xiang, and Bowen Zhou. 2015. Classifying relations by ranking with convolutional neural networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 626–634, Beijing, China, July. ACL.
[28]Ngoc Thang Vu, Heike Adel, Pankaj Gupta, and HinrichSchutze. 2016. Combining recurrent and convolutional neural networks for relation classification. In Proceedings of NAACL-HLT 2016, pages 534–539.
[29]Anthony Fader, Stephen Soderland, and Oren Etzioni. 2011. Identifying relations for open information extraction. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pages 1535–1545, Edinburgh, Scotland, UK., July. Association for Computational Linguistics.
[30]Luciano Del Corro and Rainer Gemulla. 2013. Clausie: Clause-based open information extraction. In Proceedings of the 22Nd International Conference on World Wide Web, pages 355–366, New York, NY, USA. ACM.
[31]D. Downey, O. Etzioni, and S. Soderland. A Probabilistic Model of Redundancy in Information Extraction. In Proc. of IJCAI, 2005.
[32]Fei Wu and S. Daniel Weld. 2010. Open information extraction using wikipedia. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 118–127. Association for Computational Linguistics.
[33]Gabor Angeli, Melvin Jose Johnson Premkumar, and Christopher D. Manning. 2015. Leveraging linguistic structure for open domain information extraction. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 344–354, Beijing, China, July. Association for Computational Linguistics.
[34]Matthias Cetto, Christina Niklaus, Andre Freitas, and Siegfried Handschuh. 2018. Graphene: Semantically-linked propositions in open information extraction. In Prooceedings of COLING 2018. To appear.
[35]Yuhao Zhang, Peng Qi, and Christopher D Manning. 2018b. Graph convolution over pruned dependency trees improves relation extraction. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.
[36] Cui, Z., Ke, R., & Wang, Y. 2018. Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction. ArXiv,abs/1801.02143.