Differentiating Concepts and Instances for Knowledge Graph Embedding

@inproceedings{Lv2018DifferentiatingCA,
  title={Differentiating Concepts and Instances for Knowledge Graph Embedding},
  author={Xin Lv and Lei Hou and Juan-Zi Li and Zhiyuan Liu},
  booktitle={EMNLP},
  year={2018}
}
Concepts, which represent a group of different instances sharing common properties, are essential information in knowledge representation. [...] Key Method We use the relative positions to model the relations between concepts and instances (i.e., instanceOf), and the relations between concepts and sub-concepts (i.e., subClassOf). We evaluate our model on both link prediction and triple classification tasks on the dataset based on YAGO. Experimental results show that TransC outperforms state-of-the-art methods…Expand
JECI: A Joint Knowledge Graph Embedding Model for Concepts and Instances
TLDR
A novel knowledge graph embedding model called JECI is proposed to jointly embed concepts and instances and outperforms state-of-the-art models in most cases. Expand
JECI++: A Modified Joint Knowledge Graph Embedding Model for Concepts and Instances
TLDR
A novel knowledge graph embedding model called JECI++ to jointly embed concepts and instances is proposed, which can alleviate the problem of complex relations by incorporating neighbor information of instances. Expand
TransFG: A Fine-Grained Model for Knowledge Graph Embedding
Although concepts and instances in a knowledge graph (KG) are distinguished, TransC embeds concepts, instances, and various relations into the same vector space, which leads to the followingExpand
Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts
TLDR
This model is trained on large-scale knowledge bases that consist of massive instances and their corresponding ontological concepts connected via a (small) set of cross-view links and significantly outperforms previous models on instance-view triple prediction task as well as ontology population on ontology-view KG. Expand
Uncertain Ontology-Aware Knowledge Graph Embeddings
TLDR
A novel embedding model UOKGE (Uncertain Ontology-aware Knowledge Graph Embeddings), which learns embeddings of entities, classes, and properties on uncertain ontology- aware knowledge graphs according to confidence scores and preserves both structures and uncertainty of knowledge in the embedding space. Expand
KGSynNet: A Novel Entity Synonyms Discovery Framework with Knowledge Graph
TLDR
This work proposes a novel entity synonyms discovery framework, named KGSynNet, which pre-train subword embeddings for mentions and entities using a large-scale domain-specific corpus and employs a specifically designed fusion gate to adaptively absorb the entities’ knowledge information into their semantic features. Expand
Knowledge Graph Embedding Based On Multi-information Fusion
TLDR
The traditional triples are divided into concepts and entities, and through the conceptual constraint information generated by the entity, the structural information of the triple and the entity description text information encoded by the deep learning, the hidden relationship between the existing entities in the knowledge graph is mined, and a more accurate semantic space representation is obtained. Expand
Manifold Alignment across Geometric Spaces for Knowledge Base Representation Learning
Knowledge bases have multi-relations with distinctive properties. Most properties such as symmetry, inversion, and composition can be handled by the Euclidean embedding models. Nevertheless,Expand
Cosine-Based Embedding for Completing Schematic Knowledge
TLDR
A novel model named CosE is proposed, which outperforms state-of-the-art methods and successfully preserve the transitivity and symmetry of axioms in schematic knowledge. Expand
Connecting Embeddings for Knowledge Graph Entity Typing
TLDR
A novel approach for KG entity typing is proposed which is trained by jointly utilizing local typing knowledge from existing entity type assertions and global triple knowledge in KGs to infer missing entity type instances. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 27 REFERENCES
Representation Learning of Knowledge Graphs with Entity Descriptions
TLDR
Experimental results on real-world datasets show that, the proposed novel RL method for knowledge graphs outperforms other baselines on the two tasks, especially under the zero-shot setting, which indicates that the method is capable of building representations for novel entities according to their descriptions. Expand
Learning Entity and Relation Embeddings for Knowledge Graph Completion
TLDR
TransR is proposed to build entity and relation embeddings in separate entity space and relation spaces to build translations between projected entities and to evaluate the models on three tasks including link prediction, triple classification and relational fact extraction. Expand
Learning to Represent Knowledge Graphs with Gaussian Embedding
TLDR
The experimental results demonstrate that the KG2E method can effectively model the (un)certainties of entities and relations in a KG, and it significantly outperforms state-of-the-art methods (including TransH and TransR). Expand
Modeling Relation Paths for Representation Learning of Knowledge Bases
TLDR
This model considers relation paths as translations between entities for representation learning, and addresses two key challenges: (1) Since not all relation paths are reliable, it design a path-constraint resource allocation algorithm to measure the reliability of relation paths and (2) represents relation paths via semantic composition of relation embeddings. Expand
TransG : A Generative Model for Knowledge Graph Embedding
TLDR
This paper proposes a novel generative model (TransG) to address the issue of multiple relation semantics that a relation may have multiple meanings revealed by the entity pairs associated with the corresponding triples. Expand
Knowledge Graph Embedding via Dynamic Mapping Matrix
TLDR
A more fine-grained model named TransD, which is an improvement of TransR/CTransR, which not only considers the diversity of relations, but also entities, which makes it can be applied on large scale graphs. Expand
Knowledge Graph Completion with Adaptive Sparse Transfer Matrix
TLDR
Experimental results show that TranSparse outperforms Trans(E, H, R, and D) significantly, and achieves state-of-the-art performance on triplet classification and link prediction tasks. Expand
Knowledge Graph Embedding: A Survey of Approaches and Applications
TLDR
This article provides a systematic review of existing techniques of Knowledge graph embedding, including not only the state-of-the-arts but also those with latest trends, based on the type of information used in the embedding task. Expand
Embedding Entities and Relations for Learning and Inference in Knowledge Bases
TLDR
It is found that embeddings learned from the bilinear objective are particularly good at capturing relational semantics and that the composition of relations is characterized by matrix multiplication. Expand
Jointly Embedding Knowledge Graphs and Logical Rules
TLDR
Experimental results show that joint embedding brings significant and consistent improvements over state of theart methods and enhances the prediction of new facts which cannot even be directly inferred by pure logical inference, demonstrating the capability of the method to learn more predictive embeddings. Expand
...
1
2
3
...