Filters








1,647 Hits in 6.1 sec

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
Research on overlapped and discontinuous named entity recognition (NER) has received increasing attention. The majority of previous work focuses on either overlapped or discontinuous entities.  ...  Experimental results on multiple benchmark datasets (i.e., CLEF, GENIA and ACE05) show that our model is highly competitive for overlapped and discontinuous NER.  ...  Acknowledgments We thank the reviewers for their comments and recommendation. This work is supported by the National Natural Science  ... 
arXiv:2106.14373v1 fatcat:lyyvifwsjzgbhcv4nct75xqm6m

A History and Theory of Textual Event Detection and Recognition

Yanping Chen, Zehua Ding, Qinghua Zheng, Yongbin Qin, Ruizhang Huang, Nazaraf Shah
2020 IEEE Access  
For example, Fu et al. [138] extracted joint entities and relations using graph convolutional networks. The endto-end approach implements a task from scratch without depending on other tasks.  ...  Another important issue for named entity recognition is the nestification problem, where two named entities may overlap mutually.  ... 
doi:10.1109/access.2020.3034907 fatcat:ng7mbplve5dttao7ro6e2623ti

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.  ...  In contrast to previous baselines, we consider the interaction between named entities and relations via a relation-weighted GCN to better extract relations.  ...  Case Study Conclusion In this paper, we present GraphRel, an end-toend relation extraction model which jointly learns named entities and relations based on graph convolutional networks (GCN).  ... 
doi:10.18653/v1/p19-1136 dblp:conf/acl/FuLM19 fatcat:rrmpsowi7fe6xp32i2tuw5bgte

Relation Classification for Bleeding Events from Electronic Health Records: Exploration of Deep Learning Systems (Preprint)

Avijit Mitra, Bhanu Pratap Singh Rawat, David D McManus, Hong Yu
2021 JMIR Medical Informatics  
Attention guided graph convolutional networks for relation extraction.  ...  Multimedia Appendix 1 Attention-guided graph convolutional network (AGGCN).  ... 
doi:10.2196/27527 fatcat:re3lu3csonazxa2w3pfegpanym

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.  ...  However, entity representation, or syntactic structure that are informative may be beneficial for identifying metonymy.  ...  [27] proposed a dependencydriven approach for relation extraction with attentive graph convolutional networks (A-GCN).  ... 
doi:10.3390/fi14030085 fatcat:t3tnwe75zrbdfd4je7rk2jfa6e

Linguistic Structure Guided Context Modeling for Referring Image Segmentation [article]

Tianrui Hui, Si Liu, Shaofei Huang, Guanbin Li, Sansi Yu, Faxi Zhang, Jizhong Han
2020 arXiv   pre-print
Our LSCM module builds a Dependency Parsing Tree suppressed Word Graph (DPT-WG) which guides all the words to include valid multimodal context of the sentence while excluding disturbing ones through three  ...  To tackle this problem, we propose a "gather-propagate-distribute" scheme to model multimodal context by cross-modal interaction and implement this scheme as a novel Linguistic Structure guided Context  ...  Chen et al [9] proposes a latent graph with a small number of nodes to capture context from visual features for recognition and segmentation.  ... 
arXiv:2010.00515v3 fatcat:srty5inkzfehxicu6kwd3ojo4i

Graph Neural Networks for Natural Language Processing: A Survey [article]

Lingfei Wu, Yu Chen, Kai Shen, Xiaojie Guo, Hanning Gao, Shucheng Li, Jian Pei, Bo Long
2021 arXiv   pre-print
In this survey, we present a comprehensive overview onGraph Neural Networks(GNNs) for Natural Language Processing.  ...  We propose a new taxonomy of GNNs for NLP, whichsystematically organizes existing research of GNNs for NLP along three axes: graph construction,graph representation learning, and graph based encoder-decoder  ...  Bipartite flat-graph network for nested named entity recognition.  ... 
arXiv:2106.06090v1 fatcat:zvkhinpcvzbmje4kjpwjs355qu

Symbolic Graph Reasoning Meets Convolutions

Xiaodan Liang, Zhiting Hu, Hao Zhang, Liang Lin, Eric P. Xing
2018 Neural Information Processing Systems  
Beyond local convolution networks, we explore how to harness various external human knowledge for endowing the networks with the capability of semantic global reasoning.  ...  CRF) or constraints for modeling broader dependencies, we propose a new Symbolic Graph Reasoning (SGR) layer, which performs reasoning over a group of symbolic nodes whose outputs explicitly represent  ...  One stream exploits networks for the graph-structured data with a family of graph-based CNNs [36, 40] and RNNs [25, 26] or advanced convolution filters [43] to discover more complex feature dependencies  ... 
dblp:conf/nips/LiangHZLX18 fatcat:ev3i2ub4yjfsfbo6i6vq7vdw3u

Deep Learning applied to NLP [article]

Marc Moreno Lopez, Jugal Kalita
2017 arXiv   pre-print
Convolutional Neural Network (CNNs) are typically associated with Computer Vision.  ...  CNNs are responsible for major breakthroughs in Image Classification and are the core of most Computer Vision systems today.  ...  II RESULTS 4) Dependency Sensitive Convolutional Neural Networks for .  ... 
arXiv:1703.03091v1 fatcat:3grekqst4jbr3np5yv4vzqa4ze

Syntax-informed Question Answering with Heterogeneous Graph Transformer [article]

Fangyi Zhu, Lok You Tan, See-Kiong Ng, Stéphane Bressan
2022 arXiv   pre-print
We present a linguistics-informed question answering approach that extends and fine-tunes a pre-trained transformer-based neural language model with symbolic knowledge encoded with a heterogeneous graph  ...  We illustrate the approach by the addition of syntactic information in the form of dependency and constituency graphic structures connecting tokens and virtual vertices.  ...  Any opinions, Syntax-informed Question Answering with Heterogeneous Graph Transformer 13 findings and conclusions or recommendations expressed in this material are those of the authors and do not reflect  ... 
arXiv:2204.09655v2 fatcat:r7guxjblk5fapf2mvl2obppcsy

Construction and Research on Chinese Semantic Mapping Based on Linguistic Features and Sparse Self-Learning Neural Networks

Haiping Zhang, Bo Chao, Zhijing Huang, Tingyu Li, Gengxin Sun
2022 Computational Intelligence and Neuroscience  
Based on the segmented convolutional neural network, the model first introduces the dependent subtree of relational attributes to obtain the position weights of each word in the sentence, then introduces  ...  term entity and relational attribute recognition extraction and makes the knowledge map constructed in this paper.  ...  Named entity recognition (NER) is one of the key algorithms in building knowledge graphs, and named entity recognition algorithms in natural language processing toolkits rely heavily on the manual production  ... 
doi:10.1155/2022/2315802 pmid:35769283 pmcid:PMC9236845 fatcat:pwd5ryxrhzay3lnvmyxa2duvyi

A Survey of Knowledge Enhanced Pre-trained Models [article]

Jian Yang, Gang Xiao, Yulong Shen, Wei Jiang, Xinyu Hu, Ying Zhang, Jinghui Peng
2022 arXiv   pre-print
Finally, we outline some potential directions of KEPTMs for future research.  ...  [98] encodes dependency structure of the input sentence by a graph neural network.  ...  With customized graphs, the model adopts a graph convolutional network(GCN) to encode neighbor information into the representations of nodes and aggregates evidence with the graph attention mechanism for  ... 
arXiv:2110.00269v3 fatcat:b2g3ezuplvftfp7zlehvogd44m

Document-level Biomedical Relation Extraction Using Graph Convolutional Network and Multi-head Attention (Preprint)

Jian Wang, Xiaoyu Chen, Yu Zhang, Yijia Zhang, Jiabin Wen, Hongfei Lin, Zhihao Yang, Xin Wang
2019 JMIR Medical Informatics  
Methods: In this paper, we propose a novel end-to-end neural network based on the graph convolutional network (GCN) and multi-head attention.  ...  GCN is applied to capture the feature representation of the document-level dependency graph.  ...  We also would like to thank all the anonymous reviewers for their valuable suggestions and constructive comments.  ... 
doi:10.2196/17638 pmid:32459636 fatcat:wbhiwn3wwjg5bbv577zbd5f5cm

Classifying relations in clinical narratives using segment graph convolutional and recurrent neural networks (Seg-GCRNs)

Yifu Li, Ran Jin, Yuan Luo
2018 JAMIA Journal of the American Medical Informatics Association  
We propose to use segment graph convolutional and recurrent neural networks (Seg-GCRNs), which use only word embedding and sentence syntactic dependencies, to classify relations from clinical notes without  ...  Comparison with the previous state-of-the-art segment convolutional neural network (Seg-CNN) suggests that adding syntactic dependency information helps refine medical word embedding and improves concept  ...  ACKNOWLEDGMENTS The authors thank i2b2 National Center for Biomedical Computing, which is funded by U54LM008748, for creating the clinical records in the i2b2/VA relation classification challenge.  ... 
doi:10.1093/jamia/ocy157 pmid:30590613 pmcid:PMC6351971 fatcat:jbjhkur43vcjpfly6i4fhbklrq

A Chinese Named Entity Recognition Model of Maintenance Records for Power Primary Equipment Based on Progressive Multitype Feature Fusion

Lanfei He, Xuefei Zhang, Zhiwei Li, Peng Xiao, Ziming Wei, Xu Cheng, Shaocheng Qu, Manman Yuan
2022 Complexity  
This paper proposes a progressive multitype feature fusion model to recognize Chinese named entity of unstructured maintenance records for power primary equipment.  ...  Further, radicals feature representation and character embedding are concatenated and sent to BiLSTM module to extract contextual information in order to improve Chinese entity recognition ability.  ...  For this purpose, we construct the first EPE-MR dataset for Chinese named entity recognition of maintenance records of power primary equipment.  ... 
doi:10.1155/2022/8114217 fatcat:f7o2e2kgpzcjvihx2d5npwen6m
« Previous Showing results 1 — 15 out of 1,647 results