About: Embedding-Based Recommendations on Scholarly Knowledge Graphs

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

About: Embedding-Based Recommendations on Scholarly Knowledge Graphs 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	Embedding-Based Recommendations on Scholarly Knowledge Graphs
Creator	Lehmann, Jens Nayyeri, Mojtaba Shariat Yazdi, Hamed Vahdati, Sahar Zhou, Xiaotian
Source	PMC
abstract	The increasing availability of scholarly metadata in the form of Knowledge Graphs (KG) offers opportunities for studying the structure of scholarly communication and evolution of science. Such KGs build the foundation for knowledge-driven tasks e.g., link discovery, prediction and entity classification which allow to provide recommendation services. Knowledge graph embedding (KGE) models have been investigated for such knowledge-driven tasks in different application domains. One of the applications of KGE models is to provide link predictions, which can also be viewed as a foundation for recommendation service, e.g. high confidence “co-author” links in a scholarly knowledge graph can be seen as suggested collaborations. In this paper, KGEs are reconciled with a specific loss function (Soft Margin) and examined with respect to their performance for co-authorship link prediction task on scholarly KGs. The results show a significant improvement in the accuracy of the experimented KGE models on the considered scholarly KGs using this specific loss. TransE with Soft Margin (TransE-SM) obtains a score of 79.5% Hits@10 for co-authorship link prediction task while the original TransE obtains 77.2%, on the same task. In terms of accuracy and Hits@10, TransE-SM also outperforms other state-of-the-art embedding models such as ComplEx, ConvE and RotatE in this setting. The predicted co-authorship links have been validated by evaluating profile of scholars.
has issue date	2020-05-07(xsd:dateTime)
bibo:doi	10.1007/978-3-030-49461-2_15
has license	no-cc
sha1sum (hex)	6cad099c2bf9400ecf27b18d5d7e8a153fca8376
schema:url	https://doi.org/10.1007/978-3-030-49461-2_15
resource representing a document's title	Embedding-Based Recommendations on Scholarly Knowledge Graphs
has PubMed Central identifier	PMC7250594
schema:publication	The Semantic Web
resource representing a document's body	covid:6cad099c2bf9400ecf27b18d5d7e8a153fca8376#body_text
is schema:about of	named entity 'scholarly' named entity 'domains' named entity 'studying' named entity 'original' named entity 'prediction' named entity 'respect' named entity 'Graphs' named entity 'LINK PREDICTION' named entity 'SERVICES' named entity 'SCORE' named entity 'SPECIFIC' named entity 'CONVE' named entity 'STATE' named entity 'COMPLEX' named entity 'AUTHOR' named entity 'PREDICTED' named entity 'LOSS' named entity 'SEEN' named entity 'TRANSE' named entity 'PERFORMANCE' named entity 'HITS' named entity 'ART' named entity 'PAPER' named entity 'SCHOLARS' named entity 'Soft' named entity 'confidence' named entity 'Yoshua Bengio' named entity 'scholarly communication' named entity 'loss function' named entity 'false negative' named entity 'evolution' named entity 'KGs' named entity 'semantic' named entity 'Yann LeCun' named entity 'many-to-many' named entity 'Yoshua Bengio' named entity 'semantic similarity' named entity 'triples' named entity 'Knowledge Graph' named entity 'knowledge graphs' named entity 'metadata' named entity 'Hits' named entity 'scholarly' named entity 'models' named entity 'predicted' named entity 'knowledge graph' named entity 'knowledge graph' named entity 'RDF' named entity 'machine learning' named entity 'slack variable' named entity 'score function' named entity 'knowledge graph' named entity 'knowledge graphs' named entity 'real-world' named entity 'score function' named entity 'linear transformation' named entity 'probability' named entity 'Google Scholar' named entity 'Yann LeCun' named entity 'loss function' named entity 'SGD' named entity 'triples' named entity 'penalty method' named entity 'DBLP' named entity 'Semantic Scholar' named entity 'optimization problem' named entity 'Knowledge Graphs' named entity 'metadata' named entity 'scholarly communication' named entity 'knowledge graph' named entity 'metadata' named entity 'semantic web' named entity 'triples' named entity 'knowledge graphs' named entity 'Knowledge Graphs' named entity 'triples' named entity 'Albert Einstein' named entity 'false negative' named entity 'triples'

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