Connecting Embeddings for Knowledge Graph Entity Typing

Yu, Zhiwu; zhang, anxiang; Xie, Rong; Liu, Kang; Wang, Xiaojie

doi:10.18653/v1/2020.acl-main.572

Cited by 52 publications

(37 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We observe that the relational triple information is also helpful to judge tuple qualities. Inspired by the work in [1], we first build the entity type triple (head type, relationship, tail type) by replacing both head entity and tail entity with their corresponding entity types, that is, (e, r, e) ⟶ replace (τ, r, τ) , using two entity type tuples (e, τ) and (e, τ).…”

Section: Global Tuple Confidencementioning

confidence: 99%

“…KGs are effective well-structural relational databases for knowledge acquisition. Beside the triples, KGs usually contain a great number of entity type instances in the form of (entity, entity type) (denoted by (e, τ)) [1], which indicate that an entity e is of a certain entity type τ. For example, an entity "Tom Hanks" is an instance of a type "actor."…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Confidence-Aware Embedding for Knowledge Graph Entity Typing

Hou

et al. 2021

Complexity

Self Cite

View full text Add to dashboard Cite

Knowledge graphs (KGs) entity typing aims to predict the potential types to an entity, that is, (entity, entity type = ?). Recently, several embedding models are proposed for KG entity types prediction according to the existing typing information of the (entity, entity type) tuples in KGs. However, most of them unreasonably assume that all existing entity typing instances in KGs are completely correct, which ignore the nonnegligible entity type noises and may lead to potential errors for the downstream tasks. To address this problem, we propose ConfE, a novel confidence-aware embedding approach for modeling the (entity, entity type) tuples, which takes tuple confidence into consideration for learning better embeddings. Specifically, we learn the embeddings of entities and entity types in separate entity space and entity type space since they are different objects in KGs. We utilize an asymmetric matrix to specify the interaction of their embeddings and incorporate the tuple confidence as well. To make the tuple confidence more universal, we consider only the internal structural information in existing KGs. We evaluate our model on two tasks, including entity type noise detection and entity type prediction. The extensive experimental results in two public benchmark datasets (i.e., FB15kET and YAGO43kET) demonstrate that our proposed model outperforms all baselines on all tasks, which verify the effectiveness of ConfE in learning better embeddings on noisy KGs. The source code and data of this work can be obtained from https://github.com/swufenlp/ConfE.

show abstract

Section: Global Tuple Confidencementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Confidence-Aware Embedding for Knowledge Graph Entity Typing

Hou

et al. 2021

Complexity

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

“…There have been some attempts to identify entity types in knowledge graphs [16,18,19,34]. We note that these existing methods assume that the entity types are predefined [16,34] or some rich features are provided to infer the semantic categories of entities [18,19]. On the other hand, our hypergraph-based clustering scheme does not require any prior information about entity types or other external features.…”

Section: Related Workmentioning

confidence: 99%

Knowledge Graph Embedding via Metagraph Learning

Chung

Whang

2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Knowledge graph embedding aims to represent entities and relations in a continuous feature space while preserving the structure of a knowledge graph. Most existing knowledge graph embedding methods either focus only on a flat structure of the given knowledge graph or exploit the predefined types of entities to explore an enriched structure. In this paper, we define the metagraph of a knowledge graph by proposing a new affinity metric that measures the structural similarity between entities, and then grouping close entities by hypergraph clustering. Without any prior information about entity types, a set of semantically close entities is successfully merged into one super-entity in our metagraph representation. We propose the metagraph-based pre-training model of knowledge graph embedding where we first learn representations in the metagraph and initialize the entities and relations in the original knowledge graph with the learned representations. Experimental results show that our method is effective in improving the accuracy of state-of-the-art knowledge graph embedding methods. CCS CONCEPTS• Computing methodologies → Semantic networks; • Information systems → Clustering.

show abstract

“…For example, Hogan [ 10 ] replaced entities with canonical labels for solemnising existential nodes. Zhao et al [ 11 ] proposed an effective method of using local relationships in entity type prediction.…”

Section: Introductionmentioning

confidence: 99%

Multipath Cross Graph Convolution for Knowledge Representation Learning

Tian

Yang

Yin

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In the past, most of the entity prediction methods based on embedding lacked the training of local core relationships, resulting in a deficiency in the end-to-end training. Aiming at this problem, we propose an end-to-end knowledge graph embedding representation method. It involves local graph convolution and global cross learning in this paper, which is called the TransC graph convolutional network (TransC-GCN). Firstly, multiple local semantic spaces are divided according to the largest neighbor. Secondly, a translation model is used to map the local entities and relationships into a cross vector, which serves as the input of GCN. Thirdly, through training and learning of local semantic relations, the best entities and strongest relations are found. The optimal entity relation combination ranking is obtained by evaluating the posterior loss function based on the mutual information entropy. Experiments show that this paper can obtain local entity feature information more accurately through the convolution operation of the lightweight convolutional neural network. Also, the maximum pooling operation helps to grasp the strong signal on the local feature, thereby avoiding the globally redundant feature. Compared with the mainstream triad prediction baseline model, the proposed algorithm can effectively reduce the computational complexity while achieving strong robustness. It also increases the inference accuracy of entities and relations by 8.1% and 4.4%, respectively. In short, this new method can not only effectively extract the local nodes and relationship features of the knowledge graph but also satisfy the requirements of multilayer penetration and relationship derivation of a knowledge graph.

show abstract

Connecting Embeddings for Knowledge Graph Entity Typing

Cited by 52 publications

References 27 publications

Confidence-Aware Embedding for Knowledge Graph Entity Typing

Confidence-Aware Embedding for Knowledge Graph Entity Typing

Knowledge Graph Embedding via Metagraph Learning

Multipath Cross Graph Convolution for Knowledge Representation Learning

Contact Info

Product

Resources

About