Improving Entity Linking with Graph Networks

Deng, Zihao; Li, Zhixu; Yang, Qiang; Liu, Qingsheng; Chen, Zhigang

doi:10.1007/978-3-030-62005-9_25

Cited by 4 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GNED [54] applied graph convolutional network on the entity-word graph to generate enhanced entity embeddings, which were fed to a CRF for collective EL. Deng et al [10] generated entity embeddings based on graph convolutional network for combining global semantic information and latent relation between the entities. In addition, multi-hop attention was used to improve the representation of the mention context.…”

Section: Collective Entity Linkingmentioning

confidence: 99%

“…Specifically, the algorithm fully considers the Wikipedia page of an entity to compute its semantic similarity with the document topics. The authors in [10] propose to leverage an asymmetric graph convolutional network for entity embeddings, which can integrate global semantic information and latent relation between the entities. KGEL [11] utilizes a knowledge graph to improve the correlation information between the entities.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Entity Linking Algorithm Derived from Graph Convolutional Network and Contextualized Semantic Relevance

et al. 2022

View full text Add to dashboard Cite

In the era of big data, a large amount of unstructured text data springs up every day. Entity linking involves relating the mentions found in the texts to the corresponding entities, which stand for objective things in the real world, in a knowledge base. This task can help computers understand semantics in the texts correctly. Although there have been numerous approaches employed in research such as this, some challenges are still unresolved. Most current approaches utilize neural models to learn important features of the entity and mention context. However, the topic coherence among the referred entities is frequently ignored, which leads to a clear preference for popular entities but poor accuracy for less popular ones. Moreover, the graph-based models face much noise information and high computational complexity. To solve the problems above, the paper puts forward an entity linking algorithm derived from the asymmetric graph convolutional network and the contextualized semantic relevance, which can make full use of the neighboring node information as well as deal with unnecessary noise in the graph. The semantic vector of the candidate entity is obtained by continuously iterating and aggregating the information from neighboring nodes. The contextualized relevance model is a symmetrical structure that is designed to realize the deep semantic measurement between the mentions and the entities. The experimental results show that the proposed algorithm can fully explore the topology information of the graph and dramatically improve the effect of entity linking compared with the baselines.

show abstract

Section: Collective Entity Linkingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Entity Linking Algorithm Derived from Graph Convolutional Network and Contextualized Semantic Relevance

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The accuracy of knowledge representation in these three forms increases progressively, making the construction of hyper-relational knowledge graphs necessary. Building hyper-relational knowledge graphs helps deeply mine potential associations in data, revealing complex relationships between various operating parameters, equipment states, and environmental factors [2]. Research on hyper-relational knowledge graph link prediction can promote the development of intelligent mining technologies.…”

Section: Introductionmentioning

confidence: 99%

Research on Predicting Super-Relational Data Links for Mine Hoists within Hyper-Relational Knowledge Graphs

Dang,

Shu,

Dong

et al. 2024

Preprint

View full text Add to dashboard Cite

Hyper-relational knowledge graphs significantly enhance industrial production's intelligence, efficiency, and reliability by enabling equipment collaboration and optimizing supply chains. However, due to current limitations in data and technology, the construction of knowledge graphs in the industrial domain remains incomplete. Link prediction can effectively address this issue. This paper proposes a novel hyper-relational link prediction method called HyperFormer-LSTM, which integrates LSTM into the HyperFormer model and combines it with a MOE expert network to better capture information between entities. Experimental results show that this method performs excellently on both public datasets and self-constructed hoist datasets. In the MHSD (100) dataset, the MRR and H@1 increased by by 0.055 and 0.063, respectively, compared to HyperFormer. This method not only effectively solves the knowledge graph completion problem for mine hoists but also provides more accurate information for equipment maintenance and fault prediction. Key variables involved in this study include model structure, dataset type, dataset scale, evaluation metrics, and experimental settings. Future research will focus on further improving link prediction models and deeply studying the domain characteristics of mine hoist data to further advance research in the field of hyper-relational knowledge graph link prediction for mine hoist data.

show abstract

“…To alleviate this problem, various EL models have been proposed (Deng et al 2020;Yang et al 2019;Zhang et al 2020;Ganea and Hofmann 2017;Le and Titov 2018;Cao et al 2018), which can be divided into local model and global model. The local model mainly focuses on contextual words around the mention, and the global model concerns the topic coherence.…”

Section: Introductionmentioning

confidence: 99%

Learning to Select the Next Reasonable Mention for Entity Linking

Sun¹,

Zhou²,

Zong³

2021

Preprint

View full text Add to dashboard Cite

Entity linking aims to establish a link between entity mentions in a document and the corresponding entities in knowledge graphs (KGs). Previous work has shown the effectiveness of global coherence for entity linking. However, most of the existing global linking methods based on sequential decisions focus on how to utilize previously linked entities to enhance the later decisions. In those methods, the order of mention is fixed, making the model unable to adjust the subsequent linking targets according to the previously linked results, which will cause the previous information to be unreasonably utilized. To address the problem, we propose a novel model, called DyMen, to dynamically adjust the subsequent linking target based on the previously linked entities via reinforcement learning, enabling the model to select a link target that can fully use previously linked information. We sample mention by sliding window to reduce the action sampling space of reinforcement learning and maintain the semantic coherence of mention. Experiments conducted on several benchmark datasets have shown the effectiveness of the proposed model.

show abstract

Improving Entity Linking with Graph Networks

Cited by 4 publications

References 14 publications

An Entity Linking Algorithm Derived from Graph Convolutional Network and Contextualized Semantic Relevance

An Entity Linking Algorithm Derived from Graph Convolutional Network and Contextualized Semantic Relevance

Research on Predicting Super-Relational Data Links for Mine Hoists within Hyper-Relational Knowledge Graphs

Learning to Select the Next Reasonable Mention for Entity Linking

Contact Info

Product

Resources

About