On the Representation and Embedding of Knowledge Bases beyond Binary Relations

The models developed to date for knowledge base embedding are all based on the assumption that the relations contained in knowledge bases are binary. For the training and testing of these embedding models, multi-fold (or n-ary) relational data are converted to triples (e.g., in FB15K dataset) and interpreted as instances of binary relations. This paper presents a canonical representation of knowledge bases containing multi-fold relations. We show that the existing embedding models on the popular FB15K datasets correspond to a sub-optimal modelling framework, resulting in a loss of structural information. We advocate a novel modelling framework, which models multi-fold relations directly using this canonical representation. Using this framework, the existing TransH model is generalized to a new model, m-TransH. We demonstrate experimentally that m-TransH outperforms TransH by a large margin, thereby establishing a new state of the art.

[1]  James P. Callan,et al.  EsdRank: Connecting Query and Documents through External Semi-Structured Data , 2015, CIKM.

[2]  Gerhard Weikum,et al.  WWW 2007 / Track: Semantic Web Session: Ontologies ABSTRACT YAGO: A Core of Semantic Knowledge , 2022 .

[3]  E. F. CODD,et al.  A relational model of data for large shared data banks , 1970, CACM.

[4]  Jason Weston,et al.  Question Answering with Subgraph Embeddings , 2014, EMNLP.

[5]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[6]  James P. Callan,et al.  Query Expansion with Freebase , 2015, ICTIR.

[7]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[8]  Jason Weston,et al.  Learning Structured Embeddings of Knowledge Bases , 2011, AAAI.

[9]  Kathleen Daly,et al.  Volume 7 , 1998 .

[10]  Huanbo Luan,et al.  Modeling Relation Paths for Representation Learning of Knowledge Bases , 2015, EMNLP.

[11]  Evgeniy Gabrilovich,et al.  A Review of Relational Machine Learning for Knowledge Graphs , 2015, Proceedings of the IEEE.

[12]  Jens Lehmann,et al.  DBpedia: A Nucleus for a Web of Open Data , 2007, ISWC/ASWC.

[13]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[14]  Zhiyuan Liu,et al.  Learning Entity and Relation Embeddings for Knowledge Graph Completion , 2015, AAAI.

[15]  Praveen Paritosh,et al.  Freebase: a collaboratively created graph database for structuring human knowledge , 2008, SIGMOD Conference.

[16]  Jason Weston,et al.  A semantic matching energy function for learning with multi-relational data , 2013, Machine Learning.

[17]  Hans-Ulrich Krieger,et al.  Extending OWL Ontologies by Cartesian Types to Represent N-ary Relations in Natural Language , 2015 .

[18]  Ruhi Sarikaya,et al.  Learning phrase patterns for text classification using a knowledge graph and unlabeled data , 2014, INTERSPEECH.

[19]  Gerard de Melo,et al.  FrameBase: Representing N-Ary Relations Using Semantic Frames , 2015, ESWC.

[20]  Amit P. Sheth,et al.  Don't like RDF reification?: making statements about statements using singleton property , 2014, WWW.

[21]  F. E..  A Relational Model of Data Large Shared Data Banks , 2000 .

[22]  Daniel Gooch,et al.  Communications of the ACM , 2011, XRDS.

[23]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[24]  Bernhard Ganter,et al.  Completing Description Logic Knowledge Bases Using Formal Concept Analysis , 2007, IJCAI.

[25]  Zhen Wang,et al.  Knowledge Graph Embedding by Translating on Hyperplanes , 2014, AAAI.

[26]  Danqi Chen,et al.  Reasoning With Neural Tensor Networks for Knowledge Base Completion , 2013, NIPS.

[27]  Christopher D. Manning,et al.  Philosophers are Mortal: Inferring the Truth of Unseen Facts , 2013, CoNLL.