臺灣博碩士論文加值系統

透過資訊擷取系統以自動化方式建立知識庫，仍面臨許多挑戰。其中，對應知識在自然語言與知識庫中的字詞表示形式差異仍是一項問題。本篇論文以機器自動學習的方法，將知識三元組中的關係片語從自然語言形式的關係樣式，轉換為知識庫格式的關係謂語。我們在向量空間上訓練一個字詞表示模型，並藉此建立連結語意相等的關係樣式與關係謂語。相較於前人們的研究，我們所建立的關係片語對應表，不僅準確而且達到可觀的高覆蓋率。

Directly adding the knowledge triples obtained from open information extraction systems into a knowledge base is often impractical due to a vocabulary gap between natural language expressions and knowledge base representation. This thesis aims at learning to map relational phrases in triples from natural-language-like statement to knowledge base predicate format. We train a word representation model on a vector space and link each natural language relational pattern to semantically equivalent knowledge base predicate. Our mapping result shows not only high quality, but also promising coverage on relational phrases compared to previous researches.

口試委員會審定書 i
誌謝 ii
摘要 iii
ABSTRACT iv
CONTENTS v
LIST OF FIGURES vii
LIST OF TABLES viii
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Organization 2
Chapter 2 Related Work 3
2.1 Embedding Model 3
2.1.1 Word Embedding Model 3
2.1.2 Knowledge Base Embedding Model 4
2.2 Knowledge Base Construction 6
2.2.1 Open Information Extraction System 6
2.2.2 Relation Extraction 6
Chapter 3 Linguistic Resources 9
3.1 Terminology 9
3.2 English Datasets 10
3.3 Chinese Datasets 11
Chapter 4 Relational Mapping 13
4.1 EB: Entity Bridging with Alias Resolution 14
4.2 DR: Decompose Relational Phrases and Introduce Additional NL Text 17
4.3 TF: Filter Relational Mapping by Argument Type Constraint 20
Chapter 5 Experiments 23
5.1 Dataset and Experiment Setting 23
5.2 Triple Linking Task 26
5.3 Human Verification Task 30
5.4 Error-Case Discussion 34
Chapter 6 Conclusion and Future Work 35
References 36

Sören Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, Richard Cyganiak, and Zachary Ives. 2007. Dbpedia: A nucleus for a web of open data. In Proceedings of the 6th International the Semantic Web Conference, 722–735.
Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: A collaboratively created graph database for structuring human knowledge. In ACM SIGMOD 2008. ACM, 1247–1250.
Antoine Bordes, Nicolas Usunier, Alberto Garcia-Dura ́n. 2013. Translating Embeddings for Modeling Multi-relational Data. In NIPS 2013, 2787-2795
Andrew Carlson, Justin Betteridge, Bryan Kisiel, Burr Settles, Estevam R. Hruschka Jr., and Tom M. Mitchell. 2010. Toward an architecture for neverending language learning. In AAAI 2010, 1306-1313.
Arnab Dutta, Christian Meilicke, and Heiner Stuckenschmidt. 2015. Enriching structured knowledge with open information. In WWW 2015. ACM, 267–277.
Anthony Fader, Stephen Soderland, and Oren Etzioni. 2011. Identifying relations for open information extraction. In EMNLP 2011. ACL, 1535–1545.
Kazuma Hashimoto and Yoshimasa Tsuruoka. 2016. Adaptive Joint Learning of Compositional and Non-Compositional Phrase Embeddings. In ACL 2016.
Chu-Ren Huang. Tagged Chinese Gigaword Version 2.0 LDC2009T14. Web Download. Philadelphia: Linguistic Data Consortium, 2009.
Johannes Kirschnick, Holmer Hemsen, and Volker Mark. 2016. JEDI: Joint Entity and Relation Detection using Type Inference. In ACL 2016, pages 61–66
Yuanfei Luo, Quan Wang, Bin Wang, and Li Guo. 2015. Context-dependent knowledge graph embedding. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1656–1661.
Pablo N. Mendes, Max Jakob, Andre ́s Garc ́ıa-Silva, and Christian Bizer. 2011. Dbpedia spotlight: Shedding light on the web of documents. In Proceedings of the 7th International Conference on Semantic Systems, 1–8.
Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013a. Efficient estimation of word representations in vector space. ICLR Workshop 2013.
Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Distributed representations of words and phrases and their compositionality. In NIPS 2013. NIPSF, 3111–3119.
Ndapandula Nakashole, Gerhard Weikum, and Fabian Suchanek. 2012. Patty: A taxonomy of relational patterns with semantic types. In EMNLP 2012. ACL, 1135–1145.
Arvind Neelakantan, and Ming-Wei Chang. 2015. Inferring Missing Entity Type Instances for Knowledge Base Completion: New Dataset and Methods. In Proceedings of the 2015 Annual Conference of the North American Chapter of the ACL, pages 515–525
Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. GloVe: Global Vectors for Word Representation. In EMNLP 2014.
Fabian M. Suchanek, Gjergji Kasneci, and Gerhard Weikum. 2007. Yago: A core of semantic knowledge unifying wordnet and wikipedia. In Proceedings of the 16th international conference on World Wide Web, pages 697–706.
Nikos Voskarides, Edgar Meij, Manos Tsagkias, Maarten de Rijke, and Wouter Weerkamp. 2015. Learning to Explain Entity Relationships in Knowledge Graphs. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pages 564–574.
Sheng-Lun Wei, Yen-Pin Chiu, Hen-Hsen Huang, and Hsin-Hsi Chen. 2016. NL2KB: Resolving Vocabulary Gap between Natural Language and Knowledge Base in Knowledge Base Construction and Retrieval. In COLING 2016.
Derry Tanti Wijaya and Tom M. Mitchell. 2016. Mapping Verbs in Different Languages to Knowledge Base Relations using Web Text as Interlingua. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 818–827
Ruobing Xie, Zhiyuan Liu, Jia Jia, Huanbo Luan, Maosong Sun. 2016a. Representation Learning of Knowledge Graphs with Entity Descriptions. In AAAI 2016.
Ruobing Xie, Zhiyuan Liu, Maosong Sun. 2016b. Representation Learning of Knowledge Graphs with Hierarchical Types. In IJCAI 2016.