About: MSGE: A Multi-step Gated Model for Knowledge Graph Completion

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: MSGE: A Multi-step Gated Model for Knowledge Graph Completion Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	MSGE: A Multi-step Gated Model for Knowledge Graph Completion
Creator	Huang, Shujian Chen, Jiajun Dai, Xinyu Tan, Chunyang Yang, Kaijia
Source	PMC
abstract	Knowledge graph embedding models aim to represent entities and relations in continuous low-dimensional vector space, benefiting many research areas such as knowledge graph completion and web searching. However, previous works do not consider controlling information flow, which makes them hard to obtain useful latent information and limits model performance. Specifically, as human beings, predictions are usually made in multiple steps with every step filtering out irrelevant information and targeting at helpful information. In this paper, we first integrate iterative mechanism into knowledge graph embedding and propose a multi-step gated model which utilizes relations as queries to extract useful information from coarse to fine in multiple steps. First gate mechanism is adopted to control information flow by the interaction between entity and relation with multiple steps. Then we repeat the gate cell for several times to refine the information incrementally. Our model achieves state-of-the-art performance on most benchmark datasets compared to strong baselines. Further analyses demonstrate the effectiveness of our model and its scalability on large knowledge graphs.
has issue date	2020-04-17(xsd:dateTime)
bibo:doi	10.1007/978-3-030-47426-3_33
has license	no-cc
sha1sum (hex)	9a731dc0eaeb4cbabe147361c3a903181875b439
schema:url	https://doi.org/10.1007/978-3-030-47426-3_33
resource representing a document's title	MSGE: A Multi-step Gated Model for Knowledge Graph Completion
has PubMed Central identifier	PMC7206261
schema:publication	Advances in Knowledge Discovery and Data Mining
resource representing a document's body	covid:9a731dc0eaeb4cbabe147361c3a903181875b439#body_text
is schema:about of	named entity 'INTERACTION' named entity 'low-dimensional' named entity 'scalability' named entity 'vector space' named entity 'NTP' named entity 'Knowledge graph' named entity 'knowledge graph' named entity 'embedding dimension' named entity 'MRR' named entity 'matrix multiplication' named entity 'empirical results' named entity 'batch normalization' named entity 'Alyawarra' named entity 'extracting information' named entity 'feature extraction' named entity 'UMLS' named entity 'antibiotic' named entity 'knowledge graph' named entity 'reinforcement learning' named entity 'extract information' named entity 'knowledge graph' named entity 'non-linear' named entity 'extracting information' named entity 'knowledge graph' named entity 'semantic' named entity 'feature extraction' named entity 'empirical results' named entity 'triples' named entity 'logic' named entity 'UMLS' named entity 'schematic diagram' named entity 'vector space' named entity 'TransE' named entity 'information extraction' named entity 'question answering' named entity 'core module' named entity 'overfitting' named entity 'semantics' named entity 'data mining' named entity 'knowledge graph' named entity 'knowledge graphs' named entity 'knowledge graphs' named entity 'GRU' named entity 'progress in artificial intelligence' named entity 'matrices' named entity 'Gated Recurrent Unit' named entity 'knowledge graphs' named entity 'convolution operator' named entity 'knowledge graphs' named entity 'UMLS' named entity 'Kmeans' named entity 'Freebase' named entity 'knowledge graphs' named entity 'vector space' named entity 'dot product' named entity 'Long Short-Term Memory' named entity 'knowledge graphs' named entity 'knowledge graph' named entity 'Kinship' named entity 'Tensor decomposition' named entity 'knowledge graph' named entity 'Kinship' named entity 'matrix multiplication' named entity 'great power' named entity 'triples' named entity 'triples' named entity 'TransE' named entity 'algorithm' named entity 'knowledge graph' named entity 'Logistic sigmoid function' named entity 'Kinship' named entity 'logistic sigmoid function' named entity 'knowledge graphs' named entity 'triples' named entity 'Kinship' named entity 'TransE' named entity 'knowledge graphs' named entity 'error propagation' named entity 'loss function'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software