Filters








3,625 Hits in 8.9 sec

Multi-Stream Semantics-Guided Dynamic Aggregation Graph Convolution Networks to Extract Overlapping Relations

XiuShan Liu, Jun Cheng, Qin Zhang
2021 IEEE Access  
graph convolution network (SG-DAGCN) to realize the extraction of overlapping relations.  ...  The proposed model constructs the entity relation graphs by enumerating the possible candidates and external auxiliary information and adaptively manages the relevant substructure.  ...  ACKNOWLEDGMENT The authors would like to thank the anonymous reviewers for their comments and helpful suggestions.  ... 
doi:10.1109/access.2021.3062231 fatcat:zu4rrzkalfcsxdol7x63lzhadu

A Relational Adaptive Neural Model for Joint Entity and Relation Extraction

Guiduo Duan, Jiayu Miao, Tianxi Huang, Wenlong Luo, Dekun Hu
2021 Frontiers in Neurorobotics  
The structure information of deeper level in the text graph is extracted by the densely connected graph convolution network, and the interaction information of entity relation is captured.  ...  In the task of entity relation joint extraction, overlapping entities and multi-type relation extraction in overlapping triplets remain a challenging problem.  ...  CONCLUSION We propose a new joint entity and relation extraction model based on densely connected graph convolutional network (DCGCN).  ... 
doi:10.3389/fnbot.2021.635492 pmid:33796016 pmcid:PMC8008121 fatcat:gicxhwevdfgodcephdlnw5xbrm

Improving Graph Convolutional Networks Based on Relation-aware Attention for End-to-End Relation Extraction

Yin Hong, Yanxia Liu, Suizhu Yang, Kaiwen Zhang, Aiqing Wen, Jianjun Hu
2020 IEEE Access  
INDEX TERMS Graph convolutional network, joint extraction of entities and relations, attention, sequential labelling. 1 In this paper, overlapping relation = overlapping triplets.  ...  In this paper, we present a novel end-to-end neural model based on graph convolutional networks (GCN) for jointly extracting entities and relations between them.  ...  A BREIF OF GCN As an adaptation of convolutional neural network [35] , the graph convolutional network [13] encodes each node representation based on adjacency nodes.  ... 
doi:10.1109/access.2020.2980859 fatcat:ueeiv74fmndkpgthcofndyktta

RECA: Relation Extraction Based on Cross-Attention Neural Network

Xiaofeng Huang, Zhiqiang Guo, Jialiang Zhang, Hui Cao, Jie Yang
2022 Electronics  
Nevertheless, the mainstream relation-extraction methods, the pipeline method and the joint method, ignore the dependency between the subject entity and the object entity.  ...  Extracting entities and relations, as a crucial part of many tasks in natural language processing, transforms the unstructured text information into structured information and provides corresponding data  ...  [10] addressed the overlapping problem by treating words in sentences as nodes of a graph and relations between the entities as edges of a graph and then introducing a graph convolutional neural network  ... 
doi:10.3390/electronics11142161 fatcat:wcarjdx5pvaipk5bic654ee3du

GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction

Tsu-Jui Fu, Peng-Hsuan Li, Wei-Yun Ma
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
In this paper, we present GraphRel, an end-to-end relation extraction model which uses graph convolutional networks (GCNs) to jointly learn named entities and relations.  ...  Also, GraphRel outperforms previous work by 3.2% and 5.8% (F1 score), achieving a new state-of-the-art for relation extraction.  ...  Review of GCN As convolutional neural network (CNN), Graph Convolutional Network (GCN) (Kipf and Welling, 2017) convolves the features of neighboring nodes and also propagates the information of a node  ... 
doi:10.18653/v1/p19-1136 dblp:conf/acl/FuLM19 fatcat:rrmpsowi7fe6xp32i2tuw5bgte

Extraction of Joint Entity and Relationships with Soft Pruning and GlobalPointer

Jianming Liang, Qing He, Damin Zhang, Shuangshuang Fan
2022 Applied Sciences  
In recent years, scholars have paid increasing attention to the joint entity and relation extraction. However, the most difficult aspect of joint extraction is extracting overlapping triples.  ...  Specifically, to address the lack of information caused by the rule-based pruning strategies, we utilize the Gaussian Graph Generator and the attention-guiding layer to construct a fully connected graph  ...  Conflicts of Interest: There are no conflict to declare. Appl. Sci. 2022, 12, 6361  ... 
doi:10.3390/app12136361 fatcat:773ukym7c5g55bbvkrsrkei7c4

Joint Entity-Relation Extraction via Improved Graph Attention Networks

Qinghan Lai, Zihan Zhou, Song Liu
2020 Symmetry  
To mitigate the over-smoothing problem of graph convolutional networks, inspired by matrix factorization, we improved the graph attention network by designing a new multi-head attention mechanism and sharing  ...  To solve this problem, we proposed a novel joint model named extracting Entity-Relations viaImproved Graph Attention networks (ERIGAT), which enhances the ability of the relation extraction task.  ...  Acknowledgments: The authors are very thankful to the editor and referees for their valuable comments and suggestions for improving the paper.  ... 
doi:10.3390/sym12101746 fatcat:owevexuchjcgpf5eghrbkqr2wm

Deep Neural Networks for Relation Extraction [article]

Tapas Nayak
2021 arXiv   pre-print
Finally, we propose a hierarchical entity graph convolutional network for relation extraction across documents.  ...  Next, we propose two joint entity and relation extraction frameworks based on encoder-decoder architecture.  ...  F1 score drops by 1.3% after removing the entity mentionlevel graph convolutional network (-EMGCN). F1 score drops by 0.3% after removing the unified entity-level graph convolutional network (-EGCN).  ... 
arXiv:2104.01799v1 fatcat:vmatz7gxazd4xnm2oprncd5mm4

Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey [article]

Tapas Nayak and Navonil Majumder and Pawan Goyal and Soujanya Poria
2021 arXiv   pre-print
Regarding neural architectures, we cover convolutional models, recurrent network models, attention network models, and graph convolutional models in this survey.  ...  Recently, with the advances made in continuous representation of words (word embeddings) and deep neural architectures, many research works are published in the area of relation extraction and it is very  ...  Zeng et al. (2015) introduced a piecewise convolutional neural network (PCNN) to improve relation extraction.  ... 
arXiv:2103.16929v1 fatcat:a25435weifccdknduaiilk7ufy

A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition [article]

Fei Li, Zhichao Lin, Meishan Zhang, Donghong Ji
2021 arXiv   pre-print
In this way, we can recognize not only discontinuous entities, and meanwhile doubly check the overlapped entities. As a whole, our model can be regarded as a relation extraction paradigm essentially.  ...  Second, we perform relation classification to judge whether a given pair of entity fragments to be overlapping or succession.  ...  Acknowledgments We thank the reviewers for their comments and recommendation. This work is supported by the National Natural Science  ... 
arXiv:2106.14373v1 fatcat:lyyvifwsjzgbhcv4nct75xqm6m

TDRE: A Tensor Decomposition Based Approach for Relation Extraction [article]

Bin-Bin Zhao and Liang Li and Hui-Dong Zhang
2020 arXiv   pre-print
Extracting entity pairs along with relation types from unstructured texts is a fundamental subtask of information extraction.  ...  According to effective decomposition methods, we propose the Tensor Decomposition based Relation Extraction (TDRE) approach which is able to extract overlapping triplets and avoid detecting unnecessary  ...  [2] made fully uses of the relevance between entity and relation types by building entity-relation graph to catch the combination of entity pairs and valid relation. Guo et al.  ... 
arXiv:2010.07533v1 fatcat:jxesupcclrehham46e57bef74u

Complex Causal Extraction of Fusion of Entity Location Sensing and Graph Attention Networks

Yang Chen, Weibing Wan, Jimi Hu, Yuxuan Wang, Bo Huang
2022 Information  
Based on this, a causal model, RPA-GCN (relation position and attention-graph convolutional networks), is constructed, incorporating GAT (graph attention network) and entity location perception.  ...  At present, there is no uniform definition of annotation schemes for causal extraction, and existing methods are limited by the dependence of relations on long spans, which makes complex sentences such  ...  Dixit [22] constructs a span-level graph for joint detection of overlapping entities and relations.  ... 
doi:10.3390/info13080364 fatcat:ehadgpncf5htnlz5r5hutj5lui

A Method about Building Deep Knowledge Graph for the Plant Insect Pest and Disease (DKG-PIPD)

Yingying Liu
2021 IEEE Access  
efficiency, but also solved the problem of one-versus-many overlapping relation extraction.  ...  Moreover, the related work in this paper first introduced the general architecture required for the building of knowledge graph, and then summarized its key points, that is, named entity recognition, entity  ...  pairs, which can improve the problem of entity overlap and relation overlap to some extent.  ... 
doi:10.1109/access.2021.3116467 fatcat:vyoluv7ln5ebnlrm3ogut32eoa

A Deep Neural Network Model for Joint Entity and Relation Extraction

Yihe Pang, Jie Liu, Jianshe Zhou, Kai Zhang, Lizhen Liu, Zhengtao Yu
2019 IEEE Access  
Joint extraction of entities and their relations from the text is an essential issue in automatic knowledge graph construction, which is also known as the joint extraction of relational triplets.  ...  INDEX TERMS Automatic knowledge graph construction, entity and relation extraction, deep neural networks, natural language processing, pointer networks, relational triplet extraction, sequence-to-sequence  ...  Zeng and Dr. K. Liu from the Institute of Automation of the Chinese Academy of Sciences for their helpful discussion on this article. VOLUME 7, 2019  ... 
doi:10.1109/access.2019.2949086 fatcat:u2kruchoufalreo3u7eegu2dd4

RTJTN: Relational Triplet Joint Tagging Network for Joint Entity and Relation Extraction

Zhenyu Yang, Lei Wang, Bo Ma, Yating Yang, Rui Dong, Zhen Wang, Wei Xiang
2021 Computational Intelligence and Neuroscience  
In the joint tagging layer, instead of extracting entity and relation separately, we propose a tagging method that allows the model to simultaneously extract entities and relations in unstructured sentences  ...  In this paper, we introduce a relational triplet joint tagging network (RTJTN), which is divided into joint entities and relations tagging layer and relational triplet judgment layer.  ...  Conflicts of Interest e authors declare that there are no conflicts of interest regarding the publication of this paper.  ... 
doi:10.1155/2021/3447473 pmid:34697539 pmcid:PMC8541843 fatcat:h5bcw3k4pbhdrhi7m4adt6dzsy
« Previous Showing results 1 — 15 out of 3,625 results