Filters








3,497 Hits in 12.4 sec

Knowledge Transfer for Out-of-Knowledge-Base Entities: Improving Graph-Neural-Network-Based Embedding Using Convolutional Layers

Zhongqin Bi, Tianchen Zhang, Ping Zhou, Yongbin Li.
2020 IEEE Access  
ACKNOWLEDGMENT This work is supported by the National Nature Science Foundation of China (No. 61972357, No. 61672337).  ...  These popular methods can be broadly classified as graph neural network (GNN)-based models [24] - [26] and convolutional neural network (CNN)-based models [27] , [28] .  ...  Case (3) is the KBC task with out-of-knowledge-base (OOKB) entities. FIGURE 2 . 2 An illustration of OOKB knowledge base completion.  ... 
doi:10.1109/access.2020.3019592 fatcat:pbbe2hqi5na37fg5vf5au6u7cu

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

Jiangtao Ma, Duanyang Li, Yonggang Chen, Yaqiong Qiao, Haodong Zhu, Xuncai Zhang, Abdelkader Nasreddine Belkacem
2021 Computational Intelligence and Neuroscience  
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  ...  Finally, the balanced vector is input into the graph neural network, and the matching between the entities is output to achieve entity disambiguation.  ...  V KGSE . e splicing of vectors is the input of the graph neural network for entity disambiguation. e concat of V KGE and V KGSE is used as the input of graph convolutional network, which is an end-toend  ... 
doi:10.1155/2021/2878189 pmid:34603428 pmcid:PMC8486511 fatcat:yyh34x6zfbhgdntxzurlpgwdki

SubGraph Networks based Entity Alignment for Cross-lingual Knowledge Graph [article]

Shanqing Yu and Shihan Zhang and Jianlin Zhang and Jiajun Zhou and Qi Xuan and Bing Li and Xiaojuan Hu
2022 arXiv   pre-print
In the method, we extracted the first-order subgraphs of the KGs to expand the structural features of the original graph to enhance the representation ability of the entity embedding and improve the alignment  ...  Entity alignment is the task of finding entities representing the same real-world object in two knowledge graphs(KGs).  ...  Wang [23] and others first transferred the method of graph convolutional neural network to knowledge graph for entity alignment.  ... 
arXiv:2205.03557v1 fatcat:3qbtmckzhjfkjem2bysgazf5n4

Multichannel CNN Model for Biomedical Entity Reorganization

Ajay Kumar Singh, Ihtiram Raza Khan, Shakir Khan, Kumud Pant, Sandip Debnath, Shahajan Miah, B. D. Parameshachari
2022 BioMed Research International  
The fundamental scope of this research is that the approach described in this research uses technologies like dynamic word vectors and multichannel convolution to learn a larger variety of relational expression  ...  improve the accuracy of lexical semantic representation and uses multihead attention to capture the dependencies of long sentences and by designing the Ranking loss function to replace the multimodel  ...  , and knowledge graphs have become the focus of research.  ... 
doi:10.1155/2022/5765629 pmid:35345527 pmcid:PMC8957457 fatcat:w7gziimnbzfc5asxcoc7rjjud4

EchoEA: Echo Information between Entities and Relations for Entity Alignment [article]

Xueyuan Lin, Haihong E, Wenyu Song, Haoran Luo
2021 arXiv   pre-print
Recent approaches based on Graph Neural Network (GNN) obtain entity representation from relation information and have achieved promising results.  ...  Entity alignment (EA) plays an important role in automatically integrating knowledge graphs (KGs) from multiple sources.  ...  To obstacle the problem, they design a Graph Neural Networks (GNN) based network to obtain entity embedding.  ... 
arXiv:2107.03054v2 fatcat:niq7ycsf4nfexbrlcahfpezgta

Entity-Centric Fully Connected GCN for Relation Classification

Jun Long, Ye Wang, Xiangxiang Wei, Zhen Ding, Qianqian Qi, Fang Xie, Zheman Qian, Wenti Huang
2021 Applied Sciences  
The Graph Convolutional Network (GCN) is an effective model for accurate relation classification, which models the dependency tree of textual instances to extract the semantic features of relation mentions  ...  a knowledge graph.  ...  Fully Connect Moudle The graph convolutional network [18] is an adaptation of the convolutional neural network [27] for encoding graphs.  ... 
doi:10.3390/app11041377 fatcat:g7kzjzjpnng5bmaorjjm3zqkjq

Neural Entity Linking: A Survey of Models Based on Deep Learning [article]

Ozge Sevgili, Artem Shelmanov, Mikhail Arkhipov, Alexander Panchenko, Chris Biemann
2021 arXiv   pre-print
Since many neural models take advantage of entity and mention/context embeddings to catch semantic meaning of them, we provide an overview of popular embedding techniques.  ...  Finally, we briefly discuss applications of entity linking, focusing on the recently emerged use-case of enhancing deep pre-trained masked language models based on the transformer architecture.  ...  The work of Artem Shelmanov in the current study (preparation of sections related to application of entity linking to neural language models, entity ranking, contextmention encoding, and overall harmonization  ... 
arXiv:2006.00575v3 fatcat:ra3kwc4tmbfhlmgtlevkcshcqq

FGN: Fusion Glyph Network for Chinese Named Entity Recognition [article]

Zhenyu Xuan, Rui Bao, Shengyi Jiang
2020 arXiv   pre-print
In this paper, we propose the FGN, Fusion Glyph Network for Chinese NER. Except for adding glyph information, this method may also add extra interactive information with the fusion mechanism.  ...  we provide a method with sliding window and Slice-Attention to fuse the BERT representation and glyph representation for a character, which may capture potential interactive knowledge between context and  ...  Acknowledgments This work was supported by the National Natural Science Foundation of China(No. 61572145) and the Major Projects of Guangdong Education Department for Foundation Research and Applied Research  ... 
arXiv:2001.05272v6 fatcat:hl24dicdlnc7lkakoaxbdmslqq

Named entity recognition method in health preserving field based on BERT

Qiang Zhang, Yong Sun, Linlin Zhang, Yanfei Jiao, Yue Tian
2021 Procedia Computer Science  
In order to build a knowledge graph of health-preserving field, named entity recognition is required first.  ...  Considering the complexity and ambiguity of data, a named entity recognition method based on BERT in the health-preserving field is proposed.  ...  neural network or a recursive neural network.  ... 
doi:10.1016/j.procs.2021.03.010 fatcat:a3rsehntivbx7bpxvjy5vz7a3m

Addressing Syntax-Based Semantic Complementation: Incorporating Entity and Soft Dependency Constraints into Metonymy Resolution

Siyuan Du, Hao Wang
2022 Future Internet  
Other approaches only using deep neural network fail to capture such information. To leverage both entity and syntax constraints, this paper proposes a robust model EBAGCN for metonymy resolution.  ...  Then the work constructs a neural network to incorporate both entity representation and syntactic structure into better resolution representations.  ...  [27] proposed a dependencydriven approach for relation extraction with attentive graph convolutional networks (A-GCN).  ... 
doi:10.3390/fi14030085 fatcat:t3tnwe75zrbdfd4je7rk2jfa6e

A comprehensive survey of entity alignment for knowledge graphs

Kaisheng Zeng, Chengjiang Li, Lei Hou, Juanzi Li, Ling Feng
2021 AI Open  
A B S T R A C T Knowledge Graphs (KGs), as a structured human knowledge, manage data in an ease-of-store, recognizable, and understandable way for machines and provide a rich knowledge base for different  ...  Entity alignment aims to find equivalence relations between entities in different knowledge graphs but semantically represent the same real-world object, which is the most fundamental and essential technology  ...  To obtain an ideal embedding representation, a convolutional neural network is used to generate the similarity feature of the entity pair from the attributes of the entity pair.  ... 
doi:10.1016/j.aiopen.2021.02.002 fatcat:mj2ens2perb5jn5koxdvjmryii

BIBC: A Chinese Named Entity Recognition Model for Diabetes Research

Lei Yang, Yufan Fu, Yu Dai
2021 Applied Sciences  
Based on the deep and bidirectional transformer network structure, the pre-training language model BERT model can solve the problem of polysemous word representation, and supplement the features by large-scale  ...  In the experiment of diabetic entity recognition in Ruijin Hospital, the accuracy rate, recall rate, and F1 score are improved to 79.58%, 80.21%, and 79.89%, which are better than the evaluation indexes  ...  [22] used graph neural networks to model the entity recognition task and used external lexicons for feature supplementation during the training process to learn the features inside automatically using  ... 
doi:10.3390/app11209653 fatcat:grlagc4vevcupgp3nlseutihym

Mining Implicit Entity Preference from User-Item Interaction Data for Knowledge Graph Completion via Adversarial Learning [article]

Gaole He, Junyi Li, Wayne Xin Zhao, Peiju Liu, Ji-Rong Wen
2020 arXiv   pre-print
To discover implicit entity preference of users, we design an elaborate collaborative learning algorithms based on graph neural networks, which will be jointly optimized with the discriminator.  ...  The task of Knowledge Graph Completion (KGC) aims to automatically infer the missing fact information in Knowledge Graph (KG).  ...  , regularization-based methods [1, 20] and graph neural network methods [36] .  ... 
arXiv:2003.12718v3 fatcat:oqmheyperrcepadai77a2hoj2u

Neural entity linking: A survey of models based on deep learning

Özge Sevgili, Artem Shelmanov, Mikhail Arkhipov, Alexander Panchenko, Chris Biemann, Mehwish Alam, Davide Buscaldi, Michael Cochez, Francesco Osborne, Diego Reforgiato Recupero, Harald Sack
2022 Semantic Web Journal  
Since many neural models take advantage of entity and mention/context embeddings to represent their meaning, this work also overviews prominent entity embedding techniques.  ...  Finally, the survey touches on applications of entity linking, focusing on the recently emerged use-case of enhancing deep pre-trained masked language models based on the Transformer architecture.  ...  The work of Artem Shelmanov in the current study (preparation of sections related to application of entity linking to neural language models, entity ranking, context-mention encoding, and overall harmonization  ... 
doi:10.3233/sw-222986 fatcat:6gwmbtev7ngbliovf6cpf5hyde

Attention-based Multi-level Feature Fusion for Named Entity Recognition

Zhiwei Yang, Hechang Chen, Jiawei Zhang, Jing Ma, Yi Chang
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
In this study, we propose a novel framework called attention-based multi-level feature fusion (AMFF), which is used to capture the multi-level features from different perspectives to improve NER.  ...  for the final sequence labeling.  ...  Acknowledgments This work was partially supported by Natural Science Foundation of China (No.61772284), Postgraduate Re-search&Practice Innovation Program of Jiangsu Province (SJKY19 0763).  ... 
doi:10.24963/ijcai.2020/493 dblp:conf/ijcai/Zhu0T020 fatcat:ktpek73hm5dchmc6j246gdaj5q
« Previous Showing results 1 — 15 out of 3,497 results