Language Models As or For Knowledge Bases

Language Models As or For Knowledge Bases

DL4KG 2021 Pre-trained language models (LMs) have recently gained attention for their potential as an alternative to (or proxy for) explicit knowledge bases (KBs). In this position paper, we examine this hypothesis, identify strengths and limitations of both LMs and KBs, and discuss the complementar...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Razniewski, Simon, Yates, Andrew, Kassner, Nora, Weikum, Gerhard
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Computer Science - Databases
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Razniewski, Simon
Yates, Andrew
Kassner, Nora
Weikum, Gerhard
description DL4KG 2021 Pre-trained language models (LMs) have recently gained attention for their potential as an alternative to (or proxy for) explicit knowledge bases (KBs). In this position paper, we examine this hypothesis, identify strengths and limitations of both LMs and KBs, and discuss the complementary nature of the two paradigms. In particular, we offer qualitative arguments that latent LMs are not suitable as a substitute for explicit KBs, but could play a major role for augmenting and curating KBs.
doi_str_mv 10.48550/arxiv.2110.04888
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2110_04888</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2110_04888</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-9bb29fdc4e5cc2475383fb59a60c46eb42d7096c2472db1c4810dfff314bd86b3</originalsourceid><addsrcrecordid>eNotjrkOgkAARLexMOgHWElrge7NUioRNWJs6MmehATBsPH6e_EoJpPMSyYPgBmCSyoYgyvZP-v7EqNhgFQIMQaLXLbVTVY2PHXGNj5c-7Drw2zIse0ejTUD2khv_QSMnGy8nf47AEW2LdJ9lJ93h3SdR5LHIkqUwokzmlqmNaYxI4I4xRLJoabcKopNDBP-QdgopKlA0DjnCKLKCK5IAOa_269ree3ri-xf5ce5_DqTN62OOqs</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Language Models As or For Knowledge Bases</title><source>arXiv.org</source><creator>Razniewski, Simon ; Yates, Andrew ; Kassner, Nora ; Weikum, Gerhard</creator><creatorcontrib>Razniewski, Simon ; Yates, Andrew ; Kassner, Nora ; Weikum, Gerhard</creatorcontrib><description>DL4KG 2021 Pre-trained language models (LMs) have recently gained attention for their potential as an alternative to (or proxy for) explicit knowledge bases (KBs). In this position paper, we examine this hypothesis, identify strengths and limitations of both LMs and KBs, and discuss the complementary nature of the two paradigms. In particular, we offer qualitative arguments that latent LMs are not suitable as a substitute for explicit KBs, but could play a major role for augmenting and curating KBs.</description><identifier>DOI: 10.48550/arxiv.2110.04888</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computation and Language ; Computer Science - Databases</subject><creationdate>2021-10</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2110.04888$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2110.04888$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Razniewski, Simon</creatorcontrib><creatorcontrib>Yates, Andrew</creatorcontrib><creatorcontrib>Kassner, Nora</creatorcontrib><creatorcontrib>Weikum, Gerhard</creatorcontrib><title>Language Models As or For Knowledge Bases</title><description>DL4KG 2021 Pre-trained language models (LMs) have recently gained attention for their potential as an alternative to (or proxy for) explicit knowledge bases (KBs). In this position paper, we examine this hypothesis, identify strengths and limitations of both LMs and KBs, and discuss the complementary nature of the two paradigms. In particular, we offer qualitative arguments that latent LMs are not suitable as a substitute for explicit KBs, but could play a major role for augmenting and curating KBs.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Databases</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotjrkOgkAARLexMOgHWElrge7NUioRNWJs6MmehATBsPH6e_EoJpPMSyYPgBmCSyoYgyvZP-v7EqNhgFQIMQaLXLbVTVY2PHXGNj5c-7Drw2zIse0ejTUD2khv_QSMnGy8nf47AEW2LdJ9lJ93h3SdR5LHIkqUwokzmlqmNaYxI4I4xRLJoabcKopNDBP-QdgopKlA0DjnCKLKCK5IAOa_269ree3ri-xf5ce5_DqTN62OOqs</recordid><startdate>20211010</startdate><enddate>20211010</enddate><creator>Razniewski, Simon</creator><creator>Yates, Andrew</creator><creator>Kassner, Nora</creator><creator>Weikum, Gerhard</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20211010</creationdate><title>Language Models As or For Knowledge Bases</title><author>Razniewski, Simon ; Yates, Andrew ; Kassner, Nora ; Weikum, Gerhard</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-9bb29fdc4e5cc2475383fb59a60c46eb42d7096c2472db1c4810dfff314bd86b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Databases</topic><toplevel>online_resources</toplevel><creatorcontrib>Razniewski, Simon</creatorcontrib><creatorcontrib>Yates, Andrew</creatorcontrib><creatorcontrib>Kassner, Nora</creatorcontrib><creatorcontrib>Weikum, Gerhard</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Razniewski, Simon</au><au>Yates, Andrew</au><au>Kassner, Nora</au><au>Weikum, Gerhard</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Language Models As or For Knowledge Bases</atitle><date>2021-10-10</date><risdate>2021</risdate><abstract>DL4KG 2021 Pre-trained language models (LMs) have recently gained attention for their potential as an alternative to (or proxy for) explicit knowledge bases (KBs). In this position paper, we examine this hypothesis, identify strengths and limitations of both LMs and KBs, and discuss the complementary nature of the two paradigms. In particular, we offer qualitative arguments that latent LMs are not suitable as a substitute for explicit KBs, but could play a major role for augmenting and curating KBs.</abstract><doi>10.48550/arxiv.2110.04888</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2110.04888
ispartof
issn
language eng
recordid cdi_arxiv_primary_2110_04888
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Computer Science - Databases
title Language Models As or For Knowledge Bases
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-21T20%3A07%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Language%20Models%20As%20or%20For%20Knowledge%20Bases&rft.au=Razniewski,%20Simon&rft.date=2021-10-10&rft_id=info:doi/10.48550/arxiv.2110.04888&rft_dat=%3Carxiv_GOX%3E2110_04888%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true