Graph neural entity disambiguation

Hu, Linmei; Ding, Jiayu; Shi, Chuan; Shao, Chao; Li, Shaohua

doi:10.1016/j.knosys.2020.105620

Cited by 19 publications

(19 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…. For a fair comparison, we employ the same parameters as baseline methods provided in [8,9,17,25]. In EDEGE, the embedding size d � 300, the walk length of a node θ � 3, and the threshold for choosing neighbor node α � 0.68, which achieve the best results on the validation set.…”

Section: Resultsmentioning

confidence: 99%

“…GNED [9] uses a graph neural network model to solve entity disambiguation problems. GNED constructs a graph containing entity and mentioned word for every text to build the global semantic relation between ambiguous entities in the text.…”

Section: Neural Network-based Entity Disambiguation Methodmentioning

confidence: 99%

“…e weakness of these models is that the global structure feature between entities is not encoded in the embedding presentation. Another line of work utilizes neural networks to do entity disambiguation in an end-to-end way [8,9] (joint entity and relation extraction model based on rich semantics), which utilizes entity-relation embedding and a differentiable joint inference method for entity disambiguation. Neural network-based entity disambiguation methods cannot capture the global structure feature of the knowledge graph and have poor explanation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Knowledge Graph Entity Disambiguation Method Based on Entity-Relationship Embedding and Graph Structure Embedding

Chen³

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The purpose of knowledge graph entity disambiguation is to match the ambiguous entities to the corresponding entities in the knowledge graph. Current entity ambiguity elimination methods usually use the context information of the entity and its attributes to obtain the mention embedding vector, compare it with the candidate entity embedding vector for similarity, and perform entity matching through the similarity. The disadvantage of this type of method is that it ignores the structural characteristics of the knowledge graph where the entity is located, that is, the connection between the entity and the entity, and therefore cannot obtain the global semantic features of the entity. To improve the Precision and Recall of entity disambiguation problems, we propose the EDEGE (Entity Disambiguation based on Entity and Graph Embedding) method, which utilizes the semantic embedding vector of entity relationship and the embedding vector of subgraph structure feature. EDEGE first trains the semantic vector of the entity relationship, then trains the graph structure vector of the subgraph where the entity is located, and balances the weights of these two vectors through the entity similarity function. Finally, the balanced vector is input into the graph neural network, and the matching between the entities is output to achieve entity disambiguation. Extensive experimental results proved the effectiveness of the proposed method. Among them, on the ACE2004 data set, the Precision, Recall, and F1 values of EDEGE are 9.2%, 7%, and 11.2% higher than baseline methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Neural Network-based Entity Disambiguation Methodmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Knowledge Graph Entity Disambiguation Method Based on Entity-Relationship Embedding and Graph Structure Embedding

Chen³

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…As the global coherence optimization problem is NP-hard, different approximation methods are often used. Apart from traditional methods like loopy belief propagation [8,11], several works approximate the problem into sequence decision problem [6] or graph learning [5,7,14,16].…”

Section: Entity Linkingmentioning

confidence: 99%

“…Most recently, some global methods [14,16] construct a document-level graph with candidate entities of the mentions as nodes and exploit Graph Convolutional Networks (GCN) [17] on the graph to integrate the global information, delivering promising results. Inspired by the effectiveness of using GCN to model the global signal, we present HEterogeneous Graph-based Entity Linker (HEGEL), a novel global EL framework designed to model the interactions among manifold heterogeneous information from different sources by constructing a document-level informative heterogeneous graph and applying a heterogeneous architecture in GNN aggregation operation.…”

Section: Introductionmentioning

confidence: 99%

Integrating Manifold Knowledge for Global Entity Linking with Heterogeneous Graphs

Chen

Feng

et al. 2022

Data Intelligence

View full text Add to dashboard Cite

Entity Linking (EL) aims to automatically link the mentions in unstructured documents to corresponding entities in a knowledge base (KB), which has recently been dominated by global models. Although many global EL methods attempt to model the topical coherence among all linked entities, most of them failed in exploiting the correlations among manifold knowledge helpful for linking, such as the semantics of mentions and their candidates, the neighborhood information of candidate entities in KB and the fine-grained type information of entities. As we will show in the paper, interactions among these types of information are very useful for better characterizing the topic features of entities and more accurately estimating the topical coherence among all the referred entities within the same document. In this paper, we present a novel HEterogeneous Graph-based Entity Linker (HEGEL) for global entity linking, which builds an informative heterogeneous graph for every document to collect various linking clues. Then HEGEL utilizes a novel heterogeneous graph neural network (HGNN) to integrate the different types of manifold information and model the interactions among them. Experiments on the standard benchmark datasets demonstrate that HEGEL can well capture the global coherence and outperforms the prior state-of-the-art EL methods.

show abstract

Collective Entity Disambiguation Based on Deep Semantic Neighbors and Heterogeneous Entity Correlation

Jiang

Wang

et al. 2020

Natural Language Processing and Chinese Computing

View full text Add to dashboard Cite

Graph neural entity disambiguation

Cited by 19 publications

References 19 publications

A Knowledge Graph Entity Disambiguation Method Based on Entity-Relationship Embedding and Graph Structure Embedding

A Knowledge Graph Entity Disambiguation Method Based on Entity-Relationship Embedding and Graph Structure Embedding

Integrating Manifold Knowledge for Global Entity Linking with Heterogeneous Graphs

Collective Entity Disambiguation Based on Deep Semantic Neighbors and Heterogeneous Entity Correlation

Contact Info

Product

Resources

About