What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?

Knowledge Graphs (KG) are the backbone of many data-intensive applications since they can represent data coupled with its meaning and context. Aligning KGs across different domains and providers is necessary to afford a fuller and integrated representation. A severe limitation of current KG alignmen...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-10
Hauptverfasser: Cotovio, Pedro Giesteira, Jimenez-Ruiz, Ernesto, Pesquita, Catia
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Cotovio, Pedro Giesteira
Jimenez-Ruiz, Ernesto
Pesquita, Catia
description Knowledge Graphs (KG) are the backbone of many data-intensive applications since they can represent data coupled with its meaning and context. Aligning KGs across different domains and providers is necessary to afford a fuller and integrated representation. A severe limitation of current KG alignment (KGA) algorithms is that they fail to articulate logical thinking and reasoning with lexical, structural, and semantic data learning. Deep learning models are increasingly popular for KGA inspired by their good performance in other tasks, but they suffer from limitations in explainability, reasoning, and data efficiency. Hybrid neurosymbolic learning models hold the promise of integrating logical and data perspectives to produce high-quality alignments that are explainable and support validation through human-centric approaches. This paper examines the current state of the art in KGA and explores the potential for neurosymbolic integration, highlighting promising research directions for combining these fields.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2876187101</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2876187101</sourcerecordid><originalsourceid>FETCH-proquest_journals_28761871013</originalsourceid><addsrcrecordid>eNqNyrsKwjAUgOEgCBbtOxxwLuRiL5uDKE4iKDiWY41paprUpKX49nbwAZz-4f9mJOJCsKTYcL4gcQgNpZRnOU9TEZHzrcYeKrTwsm408qEkKI9dDWi0sq20PSjUFkbd13CSg3fJ5dPendEVGIneaqsAu847rGoZtisyf6IJMv51SdaH_XV3TCbxHmToy8YN3k6r5EWesSJnlIn_1BdyYD8m</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2876187101</pqid></control><display><type>article</type><title>What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?</title><source>Free E- Journals</source><creator>Cotovio, Pedro Giesteira ; Jimenez-Ruiz, Ernesto ; Pesquita, Catia</creator><creatorcontrib>Cotovio, Pedro Giesteira ; Jimenez-Ruiz, Ernesto ; Pesquita, Catia</creatorcontrib><description>Knowledge Graphs (KG) are the backbone of many data-intensive applications since they can represent data coupled with its meaning and context. Aligning KGs across different domains and providers is necessary to afford a fuller and integrated representation. A severe limitation of current KG alignment (KGA) algorithms is that they fail to articulate logical thinking and reasoning with lexical, structural, and semantic data learning. Deep learning models are increasingly popular for KGA inspired by their good performance in other tasks, but they suffer from limitations in explainability, reasoning, and data efficiency. Hybrid neurosymbolic learning models hold the promise of integrating logical and data perspectives to produce high-quality alignments that are explainable and support validation through human-centric approaches. This paper examines the current state of the art in KGA and explores the potential for neurosymbolic integration, highlighting promising research directions for combining these fields.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Alignment ; Deep learning ; Knowledge representation ; Reasoning</subject><ispartof>arXiv.org, 2023-10</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Cotovio, Pedro Giesteira</creatorcontrib><creatorcontrib>Jimenez-Ruiz, Ernesto</creatorcontrib><creatorcontrib>Pesquita, Catia</creatorcontrib><title>What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?</title><title>arXiv.org</title><description>Knowledge Graphs (KG) are the backbone of many data-intensive applications since they can represent data coupled with its meaning and context. Aligning KGs across different domains and providers is necessary to afford a fuller and integrated representation. A severe limitation of current KG alignment (KGA) algorithms is that they fail to articulate logical thinking and reasoning with lexical, structural, and semantic data learning. Deep learning models are increasingly popular for KGA inspired by their good performance in other tasks, but they suffer from limitations in explainability, reasoning, and data efficiency. Hybrid neurosymbolic learning models hold the promise of integrating logical and data perspectives to produce high-quality alignments that are explainable and support validation through human-centric approaches. This paper examines the current state of the art in KGA and explores the potential for neurosymbolic integration, highlighting promising research directions for combining these fields.</description><subject>Algorithms</subject><subject>Alignment</subject><subject>Deep learning</subject><subject>Knowledge representation</subject><subject>Reasoning</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNyrsKwjAUgOEgCBbtOxxwLuRiL5uDKE4iKDiWY41paprUpKX49nbwAZz-4f9mJOJCsKTYcL4gcQgNpZRnOU9TEZHzrcYeKrTwsm408qEkKI9dDWi0sq20PSjUFkbd13CSg3fJ5dPendEVGIneaqsAu847rGoZtisyf6IJMv51SdaH_XV3TCbxHmToy8YN3k6r5EWesSJnlIn_1BdyYD8m</recordid><startdate>20231011</startdate><enddate>20231011</enddate><creator>Cotovio, Pedro Giesteira</creator><creator>Jimenez-Ruiz, Ernesto</creator><creator>Pesquita, Catia</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20231011</creationdate><title>What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?</title><author>Cotovio, Pedro Giesteira ; Jimenez-Ruiz, Ernesto ; Pesquita, Catia</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28761871013</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Alignment</topic><topic>Deep learning</topic><topic>Knowledge representation</topic><topic>Reasoning</topic><toplevel>online_resources</toplevel><creatorcontrib>Cotovio, Pedro Giesteira</creatorcontrib><creatorcontrib>Jimenez-Ruiz, Ernesto</creatorcontrib><creatorcontrib>Pesquita, Catia</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cotovio, Pedro Giesteira</au><au>Jimenez-Ruiz, Ernesto</au><au>Pesquita, Catia</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?</atitle><jtitle>arXiv.org</jtitle><date>2023-10-11</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Knowledge Graphs (KG) are the backbone of many data-intensive applications since they can represent data coupled with its meaning and context. Aligning KGs across different domains and providers is necessary to afford a fuller and integrated representation. A severe limitation of current KG alignment (KGA) algorithms is that they fail to articulate logical thinking and reasoning with lexical, structural, and semantic data learning. Deep learning models are increasingly popular for KGA inspired by their good performance in other tasks, but they suffer from limitations in explainability, reasoning, and data efficiency. Hybrid neurosymbolic learning models hold the promise of integrating logical and data perspectives to produce high-quality alignments that are explainable and support validation through human-centric approaches. This paper examines the current state of the art in KGA and explores the potential for neurosymbolic integration, highlighting promising research directions for combining these fields.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_2876187101
source Free E- Journals
subjects Algorithms
Alignment
Deep learning
Knowledge representation
Reasoning
title What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-20T17%3A27%3A18IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=What%20can%20knowledge%20graph%20alignment%20gain%20with%20Neuro-Symbolic%20learning%20approaches?&rft.jtitle=arXiv.org&rft.au=Cotovio,%20Pedro%20Giesteira&rft.date=2023-10-11&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2876187101%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2876187101&rft_id=info:pmid/&rfr_iscdi=true