Online citations, reference lists, and bibliographies.
← Back to Search

Path-based Reasoning With Constrained Type Attention For Knowledge Graph Completion

Kai Lei, Jin Zhang, Yuexiang Xie, Desi Wen, Daoyuan Chen, Min Yang, Ying Shen
Published 2019 · Computer Science

Save to my Library
Download PDF
Analyze on Scholarcy Visualize in Litmaps
Share
Reduce the time it takes to create your bibliography by a factor of 10 by using the world’s favourite reference manager
Time to take this seriously.
Get Citationsy
Multi-hop reasoning over paths in knowledge graphs has attracted rising research interest in the field of knowledge graph completion. Entity types and relation types both contain various kinds of information content though only a subset of them are helpful in the specific triples. Although significant progress has been made by existing models, they have two major shortcomings. First, these models seldom learn an explicit representation of entities and relations with semantic information. Second, they reason without discriminating distinct role types that the same entity with multiple types plays in different triples. To address these issues, we develop a novel path-based reasoning with constrained type attention model, which tries to identify entity types by leveraging relation type constraints in the corresponding triples. Our experimental evaluation shows that the proposed model outperforms the state of the art on a real-world dataset. Further analyses also confirm that both word-level and triple-level attention mechanisms of our model are effective.
This paper references
10.1162/neco.1997.9.8.1735
Long Short-Term Memory
S. Hochreiter (1997)
10.1162/153244303322533205
Kernel methods for relation extraction
D. Zelenko (2003)
D Zelenko (2003)
10.1145/1242572.1242667
Yago: a core of semantic knowledge
Fabian M. Suchanek (2007)
10.1145/1376616.1376746
Freebase: a collaboratively created graph database for structuring human knowledge
K. Bollacker (2008)
10.1007/s10994-010-5205-8
Relational retrieval using a combination of path-constrained random walks
N. Lao (2010)
Understanding the difficulty of training deep feedforward neural networks
(2010)
Relational retrieval using a combination of path-constrained random walks
LaoNi (2010)
Toward an Architecture for Never-Ending Language Learning
Andrew Carlson (2010)
Random Walk Inference and Learning in A Large Scale Knowledge Base
N. Lao (2011)
Semantic Compositionality through Recursive Matrix-Vector Spaces
R. Socher (2012)
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Aciel Eshky (2012)
Translating Embeddings for Modeling Multi-relational Data
Antoine Bordes (2013)
Reasoning With Neural Tensor Networks for Knowledge Base Completion
R. Socher (2013)
Philosophers are Mortal: Inferring the Truth of Unseen Facts
Gabor Angeli (2013)
Improving Learning and Inference in a Large Knowledge-Base using Latent Syntactic Cues
Matt Gardner (2013)
10.3115/v1/D14-1067
Question Answering with Subgraph Embeddings
Antoine Bordes (2014)
10.3115/v1/D14-1044
Incorporating Vector Space Similarity in Random Walk Inference over Knowledge Bases
Matt Gardner (2014)
10.1007/978-3-662-44848-9_11
Open Question Answering with Weakly Supervised Embedding Models
Antoine Bordes (2014)
10.3115/v1/P15-1067
Knowledge Graph Embedding via Dynamic Mapping Matrix
Guoliang Ji (2015)
10.18653/v1/D15-1205
Improved Relation Extraction with Feature-Rich Compositional Embedding Models
Matthew R. Gormley (2015)
10.18653/v1/D15-1174
Representing Text for Joint Embedding of Text and Knowledge Bases
Kristina Toutanova (2015)
Compositional Vector Space Models for Knowledge Base Inference
Arvind Neelakantan (2015)
Adam: A Method for Stochastic Optimization
(2014)
10.3115/v1/P15-1016
Compositional Vector Space Models for Knowledge Base Completion
Arvind Neelakantan (2015)
10.3233/SW-140134
DBpedia - A large-scale, multilingual knowledge base extracted from Wikipedia
Jens Lehmann (2015)
Neural Machine Translation by Jointly Learning to Align and Translate
Dzmitry Bahdanau (2014)
10.18653/v1/P16-1200
Neural Relation Extraction with Selective Attention over Instances
Yankai Lin (2016)
10.18653/v1/N16-1174
Hierarchical Attention Networks for Document Classification
Zichao Yang (2016)
10.1145/2959100.2959131
Personalized Recommendations using Knowledge Graphs: A Probabilistic Logic Programming Approach
R. Catherine (2016)
10.18653/v1/P16-2034
Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification
P. Zhou (2016)
10.1145/2939672.2939673
Collaborative Knowledge Base Embedding for Recommender Systems
Fuzheng Zhang (2016)
Knowledge Graph Completion with Adaptive Sparse Transfer Matrix
Guoliang Ji (2016)
10.1109/TII.2016.2601521
Understanding Subtitles by Character-Level Sequence-to-Sequence Learning
Haijun Zhang (2017)
10.1007/978-3-319-73830-7_32
Attention-Aware Path-Based Relation Extraction for Medical Knowledge Graph
Desi Wen (2017)
Attentive Path Combination for Knowledge Graph Completion
Xiaotian Jiang (2017)
10.18653/V1/E17-1013
Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks
A. McCallum (2016)
A (2017) Chains of reasoning over entities, relations, and text using recurrent neural networks
R Das (2017)
10.18653/v1/N18-1165
Variational Knowledge Graph Reasoning
Wenhu Chen (2018)
10.1145/3209978.3210081
Knowledge-aware Attentive Neural Network for Ranking Question Answer Pairs
Ying Shen (2018)
Desi Wen (2018)
Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations



This paper is referenced by
Semantic Scholar Logo Some data provided by SemanticScholar