{"type":"ScholarlyArticle","title":"Mitigating the Effect of Out-of-Vocabulary Entity Pairs in Matrix Factorization for KB Inference","authors":[{"name":"Prachi Jain","slug":"prachi-jain","given":"Prachi","family":"Jain","affiliation":"Indian Institute of Technology Delhi"},{"name":"Shikhar Murty","slug":"shikhar-murty","given":"Shikhar","family":"Murty","affiliation":"Indian Institute of Technology Delhi"},{"name":"Mausam","slug":"mausam","given":"","family":"Mausam","affiliation":"Indian Institute of Technology Delhi"},{"name":"Soumen Chakrabarti","slug":"soumen-chakrabarti","given":"Soumen","family":"Chakrabarti","affiliation":"Indian Institute of Technology Bombay"}],"abstract":"This paper analyzes the varied performance of Matrix Factorization (MF) on the related tasks of relation extraction and knowledge-base completion, which have been unified recently into a single framework of knowledge-base inference (KBI) [Toutanova et al., 2015]. We first propose a new evaluation protocol that makes comparisons between MF and Tensor Factorization (TF) models fair. We find that this results in a steep drop in MF performance. Our analysis attributes this to the high out-of-vocabulary (OOV) rate of entity pairs in test folds of commonly-used datasets. To alleviate this issue, we propose three extensions to MF. Our best model is a TF-augmented MF model. This hybrid model is robust and obtains strong results across various KBI datasets.","doi":"10.24963/ijcai.2018/573","url":"https://ijcai.org/proceedings/2018/573","pdf":"https://ijcai.org/proceedings/2018/0573.pdf","markdown":"https://ijcai.org/proceedings/2018/573.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/573","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Natural Language Processing","track":"Main track","number":573,"pages":{"first":4122,"last":4129},"keywords":["Natural Language Processing: Embeddings","Natural Language Processing: Knowledge Extraction","Natural Language Processing: Information Extraction","Knowledge Representation and Reasoning: Non-classical Logics for Knowledge Representation"],"videos":[],"references":[{"position":1,"raw":"[Berant et al., 2011] Jonathan Berant, Ido Dagan, and Jacob Goldberger. Global Learning of Typed Entailment Rules. In ACL-HLT, pages 610-619, 2011.","title":"Global Learning of Typed Entailment Rules","authors":"Jonathan Berant, Ido Dagan, Jacob Goldberger","year":"2011","venue":"ACL-HLT","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bordes et al., 2013] Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Jason Weston, and Oksana Yakhnenko. Translating Embeddings for Modeling Multi-relational Data. In Christopher J. C. Burges, Léon Bottou, Zoubin Ghahramani, and Kilian Q. Weinberger, editors, NIPS, pages 2787-2795, 2013.","title":"Translating Embeddings for Modeling Multi-relational Data","authors":"Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Jason Weston, Oksana Yakhnenko","year":"2013","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chang et al., 2014] Kai-Wei Chang, Wen-tau Yih, Bishan Yang, and Christopher Meek. Typed Tensor Decompo- sition of Knowledge Bases for Relation Extraction. In Alessandro Moschitti, Bo Pang, and Walter Daelemans, editors, EMNLP, pages 1568-1579. ACL, 2014.","title":"Typed Tensor Decomposition of Knowledge Bases for Relation Extraction","authors":"Kai-Wei Chang, Wen-Tau Yih, Bishan Yang, Christopher Meek","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chollet, 2015] Franc ¸ois Chollet. Keras. https://github.com/ fchollet/keras, 2015.","title":"Franc ¸ois Chollet. Keras","authors":"Chollet","year":"2015","venue":null,"doi":null,"url":"https://github.com/fchollet/keras,2015","internal_url":null},{"position":5,"raw":"[Demeester et al., 2016] Thomas Demeester, Tim Rocktäschel, and Sebastian Riedel. Regularizing re- lation representations by first-order implications. In Jay Pujara, Tim Rocktäschel, Danqi Chen, and Sameer Singh, editors, AKBC@NAACL-HLT 2016, pages 75-80. The Association for Computer Linguistics, 2016.","title":"Regularizing relation representations by first-order implications","authors":"Thomas Demeester, Tim Rocktäschel, Sebastian Riedel","year":"2016","venue":"AKBC@NAACL-HLT 2016","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[García-Durán et al., 2015] Alberto García-Durán, Antoine Bordes, and Nicolas Usunier. Composing Relationships with Translations. In EMNLP, pages 286-290, 2015.","title":"Composing Relationships with Translations","authors":"Alberto García-Durán, Antoine Bordes, Nicolas Usunier","year":"2015","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Guu et al., 2015] Kelvin Guu, John Miller, and Percy Liang. Traversing Knowledge Graphs in Vector Space. In EMNLP, pages 318-327, 2015.","title":"Traversing Knowledge Graphs in Vector Space","authors":"Kelvin Guu, John Miller, Percy Liang","year":"2015","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Harshman, 1970] Richard Harshman. Foundations of the PARAFAC Procedure: Models and Conditions for an \"ex- planatory\" Multi-modal Factor Analysis . UCLA Working Papers in Phonetics, 1970.","title":"Foundations of the PARAFAC Procedure: Models and Conditions for an \"explanatory\" Multi-modal Factor Analysis","authors":"Richard Harshman","year":"1970","venue":"UCLA Working Papers in Phonetics","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jain and Mausam, 2016] Prachi Jain and Mausam. Knowledge-Guided Linguistic Rewrites for Inference Rule Verification. In NAACL-HLT, pages 86-92, 2016.","title":"Knowledge-Guided Linguistic Rewrites for Inference Rule Verification","authors":"Prachi Jain, Mausam","year":"2016","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Jain et al., 2018] Prachi Jain, Pankaj Kumar, Mausam, and Soumen Chakrabarti. Type-sensitive knowledge base in- ference without explicit type supervision. In ACL, 2018.","title":"Type-sensitive knowledge base inference without explicit type supervision","authors":"Prachi Jain, Pankaj Kumar, Mausam, Soumen Chakrabarti","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Manning and Schütze, 2001] Christopher D. Manning and Hinrich Schütze. Foundations of Statistical Natural Lan- guage Processing. MIT Press, 2001.","title":"Foundations of Statistical Natural Language Processing","authors":"Christopher D Manning, Hinrich Schütze","year":"2001","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[McCallum et al., 2017a] Andrew McCallum, Arvind Nee- lakantan, Rajarshi Das, and David Belanger. Chains of reasoning over entities, relations, and text using recurrent neural networks. In EACL, pages 132-141, 2017.","title":"Chains of reasoning over entities, relations, and text using recurrent neural networks","authors":"Mccallum","year":"2017","venue":"EACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[McCallum et al., 2017b] Andrew McCallum, Arvind Nee- lakantan, and Patrick Verga. Generalizing to unseen en- tities and entity pairs with row-less universal schema. In EACL, pages 613-622, 2017.","title":"Generalizing to unseen entities and entity pairs with row-less universal schema","authors":"Mccallum","year":"2017","venue":"EACL","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Nakashole et al., 2012] Ndapandula Nakashole, Gerhard Weikum, and Fabian Suchanek. PATTY: A Taxonomy of Relational Patterns with Semantic Types. In Joint EMNLP- CoNLL, pages 1135-1145, 2012.","title":"PATTY: A Taxonomy of Relational Patterns with Semantic Types","authors":"Nakashole","year":"2012","venue":"Joint EMNLP-CoNLL","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Nguyen et al., 2016] Dat Quoc Nguyen, Kairit Sirts, Lizhen Qu, and Mark Johnson. STransE: A novel Embedding model of entities and relationships in Knowledge bases. In NAACL-HLT, pages 460-466, 2016.","title":"STransE: A novel Embedding model of entities and relationships in Knowledge bases","authors":"Kairit Dat Quoc Nguyen, Lizhen Sirts, Mark Qu, Johnson","year":"2016","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Nickel et al., 2011] Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. A Three-Way Model for Collective Learning on Multi-Relational Data. In ICML, pages 809- 816, 2011.","title":"A Three-Way Model for Collective Learning on Multi-Relational Data","authors":"Maximilian Nickel, Hans-Peter Volker Tresp, Kriegel","year":"2011","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Nickel et al., 2016] Maximilian Nickel, Lorenzo Rosasco, and Tomaso A. Poggio. Holographic Embeddings of Knowledge Graphs. In AAAI, pages 1955-1961, 2016.","title":"Holographic Embeddings of Knowledge Graphs","authors":"Maximilian Nickel, Lorenzo Rosasco, Tomaso A Poggio","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nimishakavi et al., 2016] Madhav Nimishakavi, Uday Singh Saini, and Partha P. Talukdar. Relation Schema Induction using Tensor Factorization with Side Information. In EMNLP, pages 414-423, 2016.","title":"Relation Schema Induction using Tensor Factorization with Side Information","authors":"Madhav Nimishakavi, Uday Singh Saini, Partha P Talukdar","year":"2016","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Niu et al., 2012] Feng Niu, Ce Zhang, Christopher Ré, and Jude W. Shavlik. Elementary: Large-Scale Knowledge- Base Construction via Machine Learning and Statistical Inference. IJSWIS, pages 42-73, 2012.","title":"Elementary: Large-Scale Knowledge-Base Construction via Machine Learning and Statistical Inference","authors":"Feng Niu, Ce Zhang, Christopher Ré, Jude W Shavlik","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Raghavan et al., 2012] Sindhu Raghavan, Raymond J Mooney, and Hyeonseo Ku. Learning to \"Read Between the Lines\" using Bayesian Logic Programs. In ACL, pages 349-358, 2012.","title":"Learning to \"Read Between the Lines\" using Bayesian Logic Programs","authors":"Raymond J Sindhu Raghavan, Hyeonseo Mooney, Ku","year":"2012","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Riedel et al., 2013] Sebastian Riedel, Limin Yao, Andrew McCallum, and Benjamin M. Marlin. Relation Extraction with Matrix Factorization and Universal Schemas. In HLT- NAACL, pages 74-84, 2013.","title":"Relation Extraction with Matrix Factorization and Universal Schemas","authors":"Sebastian Riedel, Limin Yao, Andrew Mccallum, Benjamin M Marlin","year":"2013","venue":"HLT-NAACL","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rocktäschel et al., 2015] Tim Rocktäschel, Sameer Singh, and Sebastian Riedel. Injecting Logical Background Knowledge into Embeddings for Relation Extraction. In NAACL-HLT, pages 1119-1129, 2015.","title":"Injecting Logical Background Knowledge into Embeddings for Relation Extraction","authors":"Tim Rocktäschel, Sameer Singh, Sebastian Riedel","year":"2015","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Schoenmackers et al., 2008] Stefan Schoenmackers, Oren Etzioni, and Daniel S Weld. Scaling Textual Inference to the Web. In EMNLP, pages 79-88, 2008.","title":"Scaling Textual Inference to the Web","authors":"Stefan Schoenmackers, Oren Etzioni, Daniel S Weld","year":"2008","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Schoenmackers et al., 2010] Stefan Schoenmackers, Oren Etzioni, Daniel S Weld, and Jesse Davis. Learning First- Order Horn Clauses from Web Text. In EMNLP, pages 1088-1098, 2010.","title":"Learning First-Order Horn Clauses from Web Text","authors":"Stefan Schoenmackers, Oren Etzioni, Jesse Daniel S Weld, Davis","year":"2010","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Singh et al., 2015] Sameer Singh, Tim Rocktäschel, and Se- bastian Riedel. Towards Combined Matrix and Tensor Factorization for Universal Schema Relation Extraction. In VS@NAACL-HLT, pages 135-142, 2015.","title":"Towards Combined Matrix and Tensor Factorization for Universal Schema Relation Extraction","authors":"Sameer Singh, Tim Rocktäschel, Sebastian Riedel","year":"2015","venue":"VS@NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Socher et al., 2013] Richard Socher, Danqi Chen, Christo- pher D. Manning, and Andrew Y. Ng. Reasoning With Neural Tensor Networks for Knowledge Base Completion. In NIPS, pages 926-934, 2013.","title":"Reasoning With Neural Tensor Networks for Knowledge Base Completion","authors":"Richard Socher, Danqi Chen, Christopher D Manning, Andrew Y Ng","year":"2013","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Toutanova et al., 2015] Kristina Toutanova, Danqi Chen, Patrick Pantel, Hoifung Poon, Pallavi Choudhury, and Michael Gamon. Representing Text for Joint Embedding of Text and Knowledge Bases. In EMNLP, pages 1499- 1509, 2015.","title":"Representing Text for Joint Embedding of Text and Knowledge Bases","authors":"Kristina Toutanova, Danqi Chen, Patrick Pantel, Hoifung Poon, Pallavi Choudhury, Michael Gamon","year":"2015","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Toutanova et al., 2016] Kristina Toutanova, Xi Victoria Lin, Wen-tau Yih, Hoifung Poon, and Chris Quirk. Compo- sitional Learning of Embeddings for Relation Paths in Knowledge Bases and Text. In ACL, pages 1434-1444, 2016.","title":"Compositional Learning of Embeddings for Relation Paths in Knowledge Bases and Text","authors":"Kristina Toutanova, Victoria Xi, Wen-Tau Lin, Hoifung Yih, Chris Poon, Quirk","year":"2016","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Trouillon et al., 2016] Théo Trouillon, Johannes Welbl, Se- bastian Riedel, Éric Gaussier, and Guillaume Bouchard. Complex Embeddings for Simple Link Prediction. In ICML, pages 2071-2080, 2016.","title":"Complex Embeddings for Simple Link Prediction","authors":"Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, Guillaume Bouchard","year":"2016","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Verga et al., 2016] Patrick Verga, David Belanger, Emma Strubell, Benjamin Roth, and Andrew McCallum. Multi- lingual Relation Extraction using Compositional Universal Schema. In NAACL-HLT, pages 886-896, 2016.","title":"Multilingual Relation Extraction using Compositional Universal Schema","authors":"Patrick Verga, David Belanger, Emma Strubell, Benjamin Roth, Andrew Mccallum","year":"2016","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wang et al., 2017] Quan Wang, Zhendong Mao, Bin Wang, and Li Guo. Knowledge graph embedding: A survey of approaches and applications. IEEE Trans. Knowl. Data Eng., 29(12):2724-2743, 2017.","title":"Knowledge graph embedding: A survey of approaches and applications","authors":"Quan Wang, Zhendong Mao, Bin Wang, Li Guo","year":"2017","venue":"IEEE Trans. Knowl. Data Eng","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Xie et al., 2017] Qizhe Xie, Xuezhe Ma, Zihang Dai, and Eduard H. Hovy. An interpretable knowledge transfer model for knowledge base completion. In ACL, pages 950-962, 2017.","title":"An interpretable knowledge transfer model for knowledge base completion","authors":"Xie","year":"2017","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Yang et al., 2015] Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. Embedding Entities and Relations for Learning and Inference in Knowledge Bases. In ICLR, 2015.","title":"Embedding Entities and Relations for Learning and Inference in Knowledge Bases","authors":"Bishan Yang, Wen-Tau Yih, Xiaodong He, Jianfeng Gao, Li Deng","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}