Results 51 to 60 of about 2,563,850 (352)
Workshop on Graph-based Methods for Natural Language Processing, 2020 Named entity recognition (NER) from visual documents, such as invoices, receipts or business cards, is a critical task for visual document understanding.
Chuwei Luo +5 more
semanticscholar +1 more source
Entropy, 2022 Users participate in multiple social networks for different services. User identity linkage aims to predict whether users across different social networks refer to the same person, and it has received significant attention for downstream tasks such as ...
Hao Gao +4 more
doaj +1 more source
Named Entity Recognition based on a Graph Structure
Computación y Sistemas, 2020 The identification of indirect relationships between texts from different sources makes the task of text mining useful when the goal is to obtain the most valuable information from a set of texts. That is why in the field of information retrieval the correct recognition of named entities plays an important role when extracting valuable information in ...
Muñoz, David +2 more
openaire +7 more sources
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition [PDF]
Computer Vision and Pattern Recognition, 2020 Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics. To capture robust movement patterns from these graphs, long-range and multi-scale context aggregation and spatial-temporal ...
Ken Ziyu Liu +4 more
semanticscholar +1 more source
MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding [PDF]
The Web Conference, 2020 A large number of real-world graphs or networks are inherently heterogeneous, involving a diversity of node types and relation types. Heterogeneous graph embedding is to embed rich structural and semantic information of a heterogeneous graph into low ...
Xinyu Fu +3 more
semanticscholar +1 more source
KCD indices and coindices of graphs
Ratio Mathematica, 2020 The relationship between vertices of a graph is always an interesting fact, but the relations of vertices and edges also seeks attention. Motivation of the relationship between vertices and edges of a graph has helped to arise with a set of new degree ...
Keerthi G. Mirajkar, Akshata Morajkar
doaj +1 more source
Labelled (Hyper)Graphs, Negotiations and the Naming Problem [PDF]
, 2008 We consider four different models of process interactions that unify and generalise models introduced and studied by Angluin et al. and models introduced and studied by Mazurkiewicz. We encode these models by labelled (hyper)graphs and relabelling rules on this labelled (hyper)graphs called negotiations.
Chalopin, Jérémie +2 more
openaire +4 more sources
Named Entity Filtering Based on Concept Association Graphs [PDF]
Research in Computing Science, 2013 In this paper, we introduce a novel technique for named entity filtering, focused on the analysis of word association networks. We present an approach for modelling concepts which are distinctively related to specific named entity. We evaluated our approach in the context of the TREC Knowledge Base Acceleration track, and we obtained significantly ...
Gross, Oskar +2 more
openaire +3 more sources
Identity-aware Graph Neural Networks [PDF]
AAAI Conference on Artificial Intelligence, 2021 Message passing Graph Neural Networks (GNNs) provide a powerful modeling framework for relational data. However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means GNNs that are ...
Jiaxuan You +3 more
semanticscholar +1 more source
Maximal Digraphs With Respect to Primitive Positive Constructibility [PDF]
, 2021 We study the class of all finite directed graphs up to primitive positive constructability. The resulting order has a unique greatest element, namely the graph $P_1$ with one vertex and no edges. The graph $P_1$ has a unique greatest lower bound, namely the graph $P_2$ with two vertices and one directed edge.
arxiv +1 more source