臺灣博碩士論文加值系統

隨著網際網路高度普及化，每天都有許多新知識產生。這些新知識經過整理後，以知識庫的形式儲存，如Freebase和DBpedia。有了這些豐富的資源，如何有效率地從中獲取需要的資訊是個很重要的課題。自然語言問答系統是最直接且貼近人們生活的一項應用，使用者可以用熟悉的語言提出任何問題，並透過問答系統從知識庫中獲取答案。
本研究提出一套識別知識庫中主體、類別和屬性的仿真陳述問答系統，以回答簡單類型的問題。我們首先提出數種新的特徵，使得問題中候選主體的排序更加準確。同時，我們也將知識庫中的關係分為類別和屬性，並分別以一個雙向長短期記憶模型進行識別。實驗結果顯示，我們的系統在SimpleQuestions資料集上，達到目前最好的效能。

With the popularity of the Internet, more and more new information is generated every day. The information can be stored in knowledge base, such as Freebase and DBpedia. To access the knowledge efficiently and quickly to acquire what users need, the most direct and close to people''s life is question answering system in natural language. People can ask any questions in their familiar languages, and then use the question answering system to get answers from the knowledge base.
This study presents an approach to identify subject, type and property from knowledge base for answering factoid simple questions. We propose new features to rank entity candidates in knowledge base. Besides, we split a relation in knowledge base into type and property. Each of them is modeled by a bi-directional long short-term memory for identification. Experimental results show that our model achieves the state-of-the-art performance on the SimpleQuestions dataset.

口試委員會審定書 i
誌謝 ii
中文摘要 iii
Abstract iv
Contents v
List of Figures vii
List of Tables viii
Chapter 1 Introduction 1
1.1 Knowledge Base 1
1.2 Question Answering System 2
1.2.1 Introduction 2
1.2.2 Question Classification 2
1.2.3 Challenges in Question Answering System 4
1.3 Motivation 6
1.4 Organization 7
Chapter 2 Related Work 8
2.1 Question Answering Dataset 8
2.1.1 SimpleQuestions 8
2.1.2 WebQuestions 9
2.1.3 ComplexQuestions 10
2.1.4 30M Factoid Question-Answer Corpus 11
2.1.5 WikiMovies 12
2.2 Semantic Parsing Approach 13
2.3 Information Extraction Approach 14
2.4 External Resource Assistance 16
Chapter 3 Methods 19
3.1 Overview 19
3.2 Entity Identification 20
3.2.1 Candidate Generation 20
3.2.2 Feature Calculation 21
3.2.3 Ranking 27
3.3 Type Identification 28
3.4 Property Identification 31
Chapter 4 Experiments 33
4.1 Dataset and Evaluation 33
4.2 Experimental Setup 34
4.3 Overall Result 35
4.4 Entity Identification Result 36
4.5 Importance of Entity Identification Features 37
4.5.1 Performances with Single Feature 37
4.5.2 Performances Without One of the Features 38
4.5.3 Performances Without a Group of Features 39
4.6 Importance of Type Identification 40
4.7 Error Analysis 41
Chapter 5 Conclusion 44
Reference 45

Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. Semantic parsing on freebase from question-answer pairs. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP 2013), pages 1533–1544, Seattle, Washington, USA.
Junwei Bao, Nan Duan, Zhao Yan, Ming Zhou, and Tiejun Zhao. 2016. Constraint-based question answering with knowledge graph. In Proceedings of COLING, pages 2503–2514, Osaka, Japan.
Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIGMOD international conference on Management of data (SIGMOD 2008), pages 1247–1250, Vancouver, BC, Canada.
Jonathan Berant and Percy Liang. 2014. Semantic parsing via paraphrasing. In Association for Computational Linguistics (ACL 2014), volume 7, page 92–102, Baltimore, USA.
Antoine Bordes, Nicolas Usunier, Sumit Chopra, and Jason Weston. 2015. Large-scale simple question answering with memory networks. arXiv preprint arXiv:1506.02075.
Antoine Bordes, Nicolas Usunier, Alberto Garcia-Durán, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems, pages 2787–2795.
Chih-Chung Chang and Chih-Jen Lin. 2011. LIBSVM: A library for support vector machines. ACM TIST, 2(3):27.
Zihang Dai, Lei Li, and Wei Xu. 2016. CFO: Conditional focused neural question answering with large-scale knowledge bases. In Association for Computational Linguistics (ACL 2016), pages 800–810, Berlin, Germany.
Li Dong, Furu Wei, Ming Zhou, and Ke Xu. 2015. Question answering over freebase with multi-column convolutional neural networks. In Proceedings of ACL-IJCNLP, volume 1, pages 260–269, Beijing, China.
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 (EMNLP 2011), pages 1535–1545, Edinburgh, Scotland.
Anthony Fader, Luke Zettlemoyer, and Oren Etzioni. 2013. Paraphrase-driven learning for open question answering. In Association for Computational Linguistics (ACL 2013), pages 1608–1618, Sofia, Bulgaria.
David Golub and Xiaodong He. 2016. Character-level question answering with attention. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP 2016), pages 1598–1607, Austin, Texas.
Evgeniy Gabrilovich, Michael Ringgaard, and Amarnag Subramanya. 2013. FACC1: Freebase annotation of ClueWeb corpora, Version 1 (Release date 2013-06-26, Format version 1, Correction level 0). http://lemurproject.org/clueweb09/FACC1/, June.
Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, and Larry Heck. 2013. Learning deep structured semantic models for Web search using clickthrough data. In Proceedings of the 22nd ACM international conference on Conference on information & knowledge management, pages 2333–2338, San Francisco, CA, USA.
Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735–1780.
Thorsten Joachims. 2002. Optimizing search engines using clickthrough data. In Proceedings of the ACM Conference on Knowledge Discovery and Data Mining (KDD 2002), Edmonton, Alberta, Canada.
Thorsten Joachims. 2006. Training Linear SVMs in Linear Time. In Proceedings of the ACM Conference on Knowledge Discovery and Data Mining (KDD 2006), Philadelphia, Pennsylvania, USA.
Diederik P. Kingma and Jimmy Lei Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, Chris Dyer. 2016. Neural architectures for named entity recognition. In Proceedings of NAACL-HLT 2016, pages 260–270, San Diego, California.
Denis Lukovnikov, Asja Fischer, Jens Lehmann, and Sören Auer. 2017. Neural Network-based Question Answering over Knowledge Graphs on Word and Character Level. In Proceedings of the 2017 International World Wide Web Conference (WWW 2017), pages 1211–1220, Perth, Australia.
Jens Lehmann, Robert Isele, Max Jakob, Anja Jentzsch, Dimitris Kontokostas, Pablo N. Mendes, Sebastian Hellmann, Mohamed Morsey, Patrick van Kleef, Sören Auer, and Christian Bizer. 2015. Dbpedia-a large-scale, multilingual knowledge base extracted from wikipedia. Semantic Web Journal, 6(2):167–195.
Alexander H. Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, and Jason Weston. 2016. Key-value memory networks for directly reading documents. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP 2016), pages 1400–1409, Austin, Texas.
Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), pages 1532–1543, Doha, Qatar.
Iulian Vlad Serban, Alberto García-Durán, Caglar Gulcehre, Sungjin Ahn, Sarath Chandar, Aaron Courville, and Yoshua Bengio. 2016. Generating factoid questions with recurrent neural networks: the 30M factoid question-answer corpus. In Association for Computational Linguistics (ACL 2016), pages 588–598, Berlin, Germany.
Christina Unger, André Freitas, and Philipp Cimiano. 2014. An introduction to question answering over linked data. In Reasoning Web. Reasoning on the Web in the Big Data Era, pages 100–140, Springer, Heidelberg.
Kun Xu, Siva Reddy, Yansong Feng, Songfang Huang, and Dongyan Zhao. 2016. Question answering on Freebase via relation extraction and textual evidence. In Association for Computational Linguistics (ACL 2016), pages 2326–2336, Berlin, Germany.
Wen-tau Yih, Ming-Wei Chang, Xiaodong He, and Jianfeng Gao. 2015. Semantic parsing via staged query graph generation: Question answering with knowledge base. In Association for Computational Linguistics (ACL 2015), pages 1321–1331, Beijing, China.
Pengcheng Yin, Nan Duan, Ben Kao, Junwei Bao, and Ming Zhou. 2015. Answering questions with complex semantic constraints on open knowledge bases. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pages 1301–1310, Melbourne, Australia.
Wenpeng Yin, MoYu, Bing Xiang, Bowen Zhou, and Hinrich Schütze. 2016. Simple question answering by attentive convolutional neural network. In Proceedings of COLING, pages 1746–1756, Osaka, Japan.