About: JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment

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

About: JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment Goto Sponge NotDistinct Permalink

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

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment
Creator	Zhang, Jing Chen, Hong Chen, Bo Li, Cuiping Tang, Xiaobin
Source	PMC
abstract	Cross-lingual knowledge alignment is the cornerstone in building a comprehensive knowledge graph (KG), which can benefit various knowledge-driven applications. As the structures of KGs are usually sparse, attributes of entities may play an important role in aligning the entities. However, the heterogeneity of the attributes across KGs prevents from accurately embedding and comparing entities. To deal with the issue, we propose to model the interactions between attributes, instead of globally embedding an entity with all the attributes. We further propose a joint framework to merge the alignments inferred from the attributes and the structures. Experimental results show that the proposed model outperforms the state-of-art baselines by up to 38.48% HitRatio@1. The results also demonstrate that our model can infer the alignments between attributes, relationships and values, in addition to entities.
has issue date	2020-04-17(xsd:dateTime)
bibo:doi	10.1007/978-3-030-47426-3_65
has license	no-cc
sha1sum (hex)	b3a0a12a9c9abce412ca81659004b5783e86775a
schema:url	https://doi.org/10.1007/978-3-030-47426-3_65
resource representing a document's title	JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment
has PubMed Central identifier	PMC7206167
schema:publication	Advances in Knowledge Discovery and Data Mining
resource representing a document's body	covid:b3a0a12a9c9abce412ca81659004b5783e86775a#body_text
is schema:about of	named entity 'embedding' named entity 'accurately' covid:arg/b3a0a12a9c9abce412ca81659004b5783e86775a named entity 'entities' named entity 'interactions' named entity 'cornerstone' named entity 'globally' named entity 'heterogeneity' named entity 'knowledge graph' named entity 'cornerstone' named entity 'entities' named entity 'merge' named entity 'machine translation' named entity 'algorithm' named entity 'Audi RSQ' named entity 'New York' named entity '0.9' named entity 'validation set' named entity 'HR1' named entity 'matrix product' named entity 'matrix computation' named entity 'loss function' named entity 'word embedding' named entity 'GCN' named entity 'HitRa' named entity 'MRR' named entity 'knowledge graph' named entity 'one-hot' named entity 'inference' named entity 'maximal matching' named entity 'neural machine translation' named entity 'Google' named entity 'multi-dimensional' named entity 'word embeddings' named entity 'Einstein summation convention' named entity 'HR1' named entity 'Algorithm' named entity 'DBpedia' named entity 'vector space' named entity 'HR1' named entity 'language model' named entity 'vector' named entity 'JAPE' named entity 'matrices' named entity 'similarity matrix' named entity 'knowledge graphs' named entity 'one-hot' named entity '15,000' named entity 'HR1' named entity 'MRR' named entity 'JAPE' named entity 'DBpedia' named entity 'graph' named entity 'matrices' named entity 'similarity matrix' named entity 'bootstrap method' named entity 'one-hot' named entity 'test set' named entity 'dot product' named entity 'knowledge graphs' named entity 'NMT' named entity 'NMT' named entity 'JAPE' named entity 'Freebase' named entity 'similarity matrix' named entity 'matrices' named entity 'HR1' named entity 'time complexity' named entity 'training data' named entity 'semantic' named entity 'multiple languages' named entity 'NMT' named entity 'NMT' named entity 'ground truth' named entity 'machine translation' named entity 'Heterogeneity' named entity 'word embedding' named entity 'similarity matrix' named entity 'vector'

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