1,467 Hits in 12.0 sec

Joint Event Extraction along Shortest Dependency Paths using Graph Convolutional Networks [article]

Ali Balali, Masoud Asadpour, Ricardo Campos, Adam Jatowt
2020 arXiv   pre-print
Also, an attention-based graph convolutional network is proposed, to carry syntactically related information along the shortest paths between argument candidates that captures and aggregates the latent  ...  path (SDP) in the dependency graph.  ...  [29] used graph convolution networks (GCNs) to model syntactic information in the dependency graph.  ... 
arXiv:2003.08615v1 fatcat:hfv734fdwrgf7dslzlgdikmhyy

Effective Use of Graph Convolution Network and Contextual Sub-Tree forCommodity News Event Extraction [article]

Meisin Lee, Lay-Ki Soon, Eu-Gene Siew
2021 arXiv   pre-print
This paper proposes an effective use of Graph Convolutional Networks(GCN) with a pruned dependency parse tree, termed contextual sub-tree, for better event ex-traction in commodity news.  ...  However, accurate event extraction from commodity news is useful in abroad range of applications such as under-standing event chains and learning event-event relations, which can then be used for commodity  ...  The proposed solution uses a Graph Convolutional Network with a contextual sub-tree to extract events effectively.  ... 
arXiv:2109.12781v1 fatcat:7ubgfb3znjek3puqtadecejdn4

Planning and Learning: A Review of Methods involving Path-Planning for Autonomous Vehicles [article]

Kevin Osanlou, Christophe Guettier, Tristan Cazenave, Eric Jacopin
2022 arXiv   pre-print
We give a brief introduction of neural networks. Then we explore in more detail graph neural networks, a recent variant of neural networks suited for processing graph-structured inputs.  ...  Next, we study some successful approaches combining neural networks for path-planning. Lastly, we focus on temporal planning problems with uncertainty.  ...  This process is repeated for each layer. propose Spatio-Temporal Graph Convolutional Networks (STGCN), which uses a 1D-CNN alongside the ChebNet convolutional layer.  ... 
arXiv:2207.13181v1 fatcat:o7o4ss2l2vbfpcb4kal34u3mj4

Multi-Scale Feature and Metric Learning for Relation Extraction [article]

Mi Zhang, Tieyun Qian
2021 arXiv   pre-print
Meanwhile, the syntactic features are usually encoded via graph convolutional networks which have restricted receptive field.  ...  We also design a multi-scale graph convolutional network which can increase the receptive field towards specific syntactic roles.  ...  Meanwhile, the dependency based GCN methods can only convolute along the syntactic paths.  ... 
arXiv:2107.13425v1 fatcat:fav425fzzrdy3dujlntcznh6he

Matching Article Pairs with Graphical Decomposition and Convolutions [article]

Bang Liu, Di Niu, Haojie Wei, Jinghong Lin, Yancheng He, Kunfeng Lai, Yu Xu
2019 arXiv   pre-print
network.  ...  We then match a pair of articles by comparing the sentences that enclose the same concept vertex through a series of encoding techniques, and aggregate the matching signals through a graph convolutional  ...  and concepts along the paths [28] .  ... 
arXiv:1802.07459v2 fatcat:x436jyfbxjeb7euf5fmbp5nxsa

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.  ...  The attention layer is combined with a dependency tree to enhance the model's ability to perceive relational features, and a bi-directional graph convolutional network is constructed to further capture  ...  SDP-LSTM [27] : a multichannel recurrent neural network with long short-term memory (LSTM) units is used to pick up heterogeneous information along the SDP (shortest dependency path between two entities  ... 
doi:10.3390/info13080364 fatcat:ehadgpncf5htnlz5r5hutj5lui

Feedback Graph Convolutional Network for Skeleton-based Action Recognition [article]

Hao Yang, Dan Yan, Li Zhang, Dong Li, YunDa Sun, ShaoDi You, Stephen J. Maybank
2020 arXiv   pre-print
Recently, many researchers have used the Graph Convolutional Network (GCN) to model spatial-temporal features of skeleton sequences by an end-to-end optimization.  ...  In this paper, we propose a novel network, named Feedback Graph Convolutional Network (FGCN). This is the first work that introduces the feedback mechanism into GCNs and action recognition.  ...  For a vertex v ti in the graph, its neighbor set is denoted as N (v ti ) = {v tj |d(v ti , v tj ) ≤ D}, where d(v ti , v tj ) is the length of the shortest path from v tj to v ti .  ... 
arXiv:2003.07564v1 fatcat:mp7qkpj6hzbnzprdtrnvl2khj4

GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction [article]

Wasi Uddin Ahmad and Nanyun Peng and Kai-Wei Chang
2021 arXiv   pre-print
Recent progress in cross-lingual relation and event extraction use graph convolutional networks (GCNs) with universal dependency parses to learn language-agnostic sentence representations such that models  ...  We introduce GATE, a Graph Attention Transformer Encoder, and test its cross-lingual transferability on relation and event extraction tasks.  ...  All rights reserved. 1 The shortest path in the dependency graph structure.  ... 
arXiv:2010.03009v2 fatcat:h6xomdspjzh6xhfmvsmii7n2mu

A Comprehensive Survey on Graph Neural Networks [article]

Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, Philip S. Yu
2019 arXiv   pre-print
We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders, and  ...  spatial-temporal graph neural networks.  ...  PGC-DGCNN [46] increases the contributions of distant neighbors based on shortest paths. It defines a shortest path adjacency matrix S (j) .  ... 
arXiv:1901.00596v4 fatcat:xxuchvawonhczay2sgjgzw5wgu

Neural relation extraction: a survey [article]

Mehmet Aydar and Ozge Bozal and Furkan Ozbay
2020 arXiv   pre-print
In this study, we present a comprehensive review of methods on neural network based relation extraction.  ...  Neural relation extraction discovers semantic relations between entities from unstructured text using deep learning methods.  ...  [66] takes advantage of the shortest dependency path (SDP) between entities. They claim that the words along SDP are more informative.  ... 
arXiv:2007.04247v1 fatcat:xxrcy2ef75dk5aeijqlf6tjgke

DERE: A Task and Domain-Independent Slot Filling Framework for Declarative Relation Extraction

Heike Adel, Laura Ana Maria Bostan, Sean Papay, Sebastian Padó, Roman Klinger
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations  
It uses a generic specification language for the task and for data annotations in terms of spans and frames.  ...  To address these limitations, we present DERE, a novel framework for declarative specification and compilation of templatebased information extraction.  ...  Tokenization and stemming is done with NLTK (Loper and Bird, 2002) , dependency features are extracted with spacy (Honnibal and Johnson, 2015) and dependency graphs are stored and processed using NetworkX  ... 
doi:10.18653/v1/d18-2008 dblp:conf/emnlp/AdelBPPK18 fatcat:osp5ugahuvbkvceafvrd6ryd7e

An Indexing Framework for Queries on Probabilistic Graphs

Silviu Maniu, Reynold Cheng, Pierre Senellart
2017 ACM Transactions on Database Systems  
In particular, we examine "source-to-target" queries (or ST-queries), such as computing the shortest path between two vertices. e major di erence with the deterministic se ing is that query answers are  ...  Information in many applications, such as mobile wireless systems, social networks, and road networks, is captured by graphs. In many cases, such information is uncertain.  ...  Moreover, we are interested in evaluating paths over a graph, not the joint distributions in its nodes.  ... 
doi:10.1145/3044713 fatcat:4ekoy7ahwbamhojmvse62yfafy

Cell Tracking via Proposal Generation and Selection [article]

Saad Ullah Akram, Juho Kannala, Lauri Eklund, Janne Heikkilä
2017 arXiv   pre-print
in a graphical model using edges representing different cellular events and poses joint cell detection and tracking as the selection of a subset of cell and edge proposals.  ...  To efficiently and reliably extract useful insights from these captured sequences, automated cell tracking is essential.  ...  BLOB generates cell proposals by using multiple elliptical filter banks, and performs cell tracking by iteratively finding the shortest path in the tracking graph.  ... 
arXiv:1705.03386v1 fatcat:tbuoc6ve7zfwjkiz2jvhjsgtfi

Attention-Gated Graph Convolutions for Extracting Drug Interaction Information from Drug Labels [article]

Tung Tran, Ramakanth Kavuluru, Halil Kilicoglu
2019 arXiv   pre-print
Our deep learning approach entails composing various intermediate representations including sequence and graph based context, where the latter is derived using graph convolutions (GC) with a novel attention-based  ...  As drug-drug interactions (DDIs) may lead to preventable adverse events, being able to extract DDIs from drug labels into a machine-processable form is an important step toward effective dissemination  ...  [29] , wherein for a pair of subject and object entities (corresponding to t Sub and t Obj ), we keep only nodes either along or within one hop of the shortest dependency path.  ... 
arXiv:1910.12419v2 fatcat:nmb5j35aczcldg2h4ywoijiojy

Neural Metric Learning for Fast End-to-End Relation Extraction [article]

Tung Tran, Ramakanth Kavuluru
2019 arXiv   pre-print
We introduce a novel neural architecture utilizing the table structure, based on repeated applications of 2D convolutions for pooling local dependency and metric-based features, that improves on the state-of-the-art  ...  Relation extraction (RE) is an indispensable information extraction task in several disciplines.  ...  Liu et al. (2016) proposed a dependency-based convolutional neural network (CNN) architecture wherein the convolution is applied over words adjacent according to the shortest path connecting the entities  ... 
arXiv:1905.07458v4 fatcat:ozzii4u4lrasxfojqeesasxktu
« Previous Showing results 1 — 15 out of 1,467 results