Hierarchical Entity Typing via Multi-level Learning to Rank

We propose a novel method for hierarchical entity classification that embraces ontological structure at both training and during prediction. At training, our novel multi-level learning-to-rank loss compares positive types against negative siblings according to the type tree. During prediction, we de...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Chen, Tongfei, Chen, Yunmo, Van Durme, Benjamin
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language
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	Chen, Tongfei Chen, Yunmo Van Durme, Benjamin
description	We propose a novel method for hierarchical entity classification that embraces ontological structure at both training and during prediction. At training, our novel multi-level learning-to-rank loss compares positive types against negative siblings according to the type tree. During prediction, we define a coarse-to-fine decoder that restricts viable candidates at each level of the ontology based on already predicted parent type(s). We achieve state-of-the-art across multiple datasets, particularly with respect to strict accuracy.
doi_str_mv	10.48550/arxiv.2004.02286
format	Article
fullrecord	<record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2004_02286</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2004_02286</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-573437214b68a7876256c27e7c00f0b37b7198883cddfc6ea616e51f29ad24943</originalsourceid><addsrcrecordid>eNotj81Kw0AURmfThbQ-gCvnBRLn994JXUmpVogIkn24mUx06BjLGIN5e2l1dRYfHL7D2I0UpXHWijvKP3EulRCmFEo5uGLbQwyZsn-PnhLfj1OcFt4spzi-8TkSf_5OUyxSmEPidaA8nofpk7_SeNyw1UDpK1z_c82ah32zOxT1y-PT7r4uCBAKi9poVNJ04AgdgrLgFQb0Qgyi09ihrJxz2vf94CEQSAhWDqqiXpnK6DW7_dNe3renHD8oL-25or1U6F_6Y0Ci</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Hierarchical Entity Typing via Multi-level Learning to Rank</title><source>arXiv.org</source><creator>Chen, Tongfei ; Chen, Yunmo ; Van Durme, Benjamin</creator><creatorcontrib>Chen, Tongfei ; Chen, Yunmo ; Van Durme, Benjamin</creatorcontrib><description>We propose a novel method for hierarchical entity classification that embraces ontological structure at both training and during prediction. At training, our novel multi-level learning-to-rank loss compares positive types against negative siblings according to the type tree. During prediction, we define a coarse-to-fine decoder that restricts viable candidates at each level of the ontology based on already predicted parent type(s). We achieve state-of-the-art across multiple datasets, particularly with respect to strict accuracy.</description><identifier>DOI: 10.48550/arxiv.2004.02286</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2020-04</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2004.02286$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2004.02286$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Chen, Tongfei</creatorcontrib><creatorcontrib>Chen, Yunmo</creatorcontrib><creatorcontrib>Van Durme, Benjamin</creatorcontrib><title>Hierarchical Entity Typing via Multi-level Learning to Rank</title><description>We propose a novel method for hierarchical entity classification that embraces ontological structure at both training and during prediction. At training, our novel multi-level learning-to-rank loss compares positive types against negative siblings according to the type tree. During prediction, we define a coarse-to-fine decoder that restricts viable candidates at each level of the ontology based on already predicted parent type(s). We achieve state-of-the-art across multiple datasets, particularly with respect to strict accuracy.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81Kw0AURmfThbQ-gCvnBRLn994JXUmpVogIkn24mUx06BjLGIN5e2l1dRYfHL7D2I0UpXHWijvKP3EulRCmFEo5uGLbQwyZsn-PnhLfj1OcFt4spzi-8TkSf_5OUyxSmEPidaA8nofpk7_SeNyw1UDpK1z_c82ah32zOxT1y-PT7r4uCBAKi9poVNJ04AgdgrLgFQb0Qgyi09ihrJxz2vf94CEQSAhWDqqiXpnK6DW7_dNe3renHD8oL-25or1U6F_6Y0Ci</recordid><startdate>20200405</startdate><enddate>20200405</enddate><creator>Chen, Tongfei</creator><creator>Chen, Yunmo</creator><creator>Van Durme, Benjamin</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200405</creationdate><title>Hierarchical Entity Typing via Multi-level Learning to Rank</title><author>Chen, Tongfei ; Chen, Yunmo ; Van Durme, Benjamin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-573437214b68a7876256c27e7c00f0b37b7198883cddfc6ea616e51f29ad24943</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Chen, Tongfei</creatorcontrib><creatorcontrib>Chen, Yunmo</creatorcontrib><creatorcontrib>Van Durme, Benjamin</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chen, Tongfei</au><au>Chen, Yunmo</au><au>Van Durme, Benjamin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Hierarchical Entity Typing via Multi-level Learning to Rank</atitle><date>2020-04-05</date><risdate>2020</risdate><abstract>We propose a novel method for hierarchical entity classification that embraces ontological structure at both training and during prediction. At training, our novel multi-level learning-to-rank loss compares positive types against negative siblings according to the type tree. During prediction, we define a coarse-to-fine decoder that restricts viable candidates at each level of the ontology based on already predicted parent type(s). We achieve state-of-the-art across multiple datasets, particularly with respect to strict accuracy.</abstract><doi>10.48550/arxiv.2004.02286</doi><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier	DOI: 10.48550/arxiv.2004.02286
ispartof
issn
language	eng
recordid	cdi_arxiv_primary_2004_02286
source	arXiv.org
subjects	Computer Science - Computation and Language
title	Hierarchical Entity Typing via Multi-level Learning to Rank
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T07%3A55%3A18IST&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=Hierarchical%20Entity%20Typing%20via%20Multi-level%20Learning%20to%20Rank&rft.au=Chen,%20Tongfei&rft.date=2020-04-05&rft_id=info:doi/10.48550/arxiv.2004.02286&rft_dat=%3Carxiv_GOX%3E2004_02286%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