Entity Disambiguation with Entity Definitions

Local models have recently attained astounding performances in Entity Disambiguation (ED), with generative and extractive formulations being the most promising research directions. However, previous works limited their studies to using, as the textual representation of each candidate, only its Wikip...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-10
Main Authors: Procopio, Luigi, Conia, Simone, Barba, Edoardo, Navigli, Roberto
Format: Article
Language:English
Subjects:
Benchmarks
Representations
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Procopio, Luigi
Conia, Simone
Barba, Edoardo
Navigli, Roberto
description Local models have recently attained astounding performances in Entity Disambiguation (ED), with generative and extractive formulations being the most promising research directions. However, previous works limited their studies to using, as the textual representation of each candidate, only its Wikipedia title. Although certainly effective, this strategy presents a few critical issues, especially when titles are not sufficiently informative or distinguishable from one another. In this paper, we address this limitation and investigate to what extent more expressive textual representations can mitigate it. We thoroughly evaluate our approach against standard benchmarks in ED and find extractive formulations to be particularly well-suited to these representations: we report a new state of the art on 2 out of 6 benchmarks we consider and strongly improve the generalization capability over unseen patterns. We release our code, data and model checkpoints at https://github.com/SapienzaNLP/extend.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2724079495</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2724079495</sourcerecordid><originalsourceid>FETCH-proquest_journals_27240794953</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQdc0rySypVHDJLE7MTcpML00syczPUyjPLMlQgEmlpmXmZYKEi3kYWNMSc4pTeaE0N4Oym2uIs4duQVF-YWlqcUl8Vn5pUR5QKt7I3MjEwNzSxNLUmDhVAO2AMnY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2724079495</pqid></control><display><type>article</type><title>Entity Disambiguation with Entity Definitions</title><source>Publicly Available Content Database</source><creator>Procopio, Luigi ; Conia, Simone ; Barba, Edoardo ; Navigli, Roberto</creator><creatorcontrib>Procopio, Luigi ; Conia, Simone ; Barba, Edoardo ; Navigli, Roberto</creatorcontrib><description>Local models have recently attained astounding performances in Entity Disambiguation (ED), with generative and extractive formulations being the most promising research directions. However, previous works limited their studies to using, as the textual representation of each candidate, only its Wikipedia title. Although certainly effective, this strategy presents a few critical issues, especially when titles are not sufficiently informative or distinguishable from one another. In this paper, we address this limitation and investigate to what extent more expressive textual representations can mitigate it. We thoroughly evaluate our approach against standard benchmarks in ED and find extractive formulations to be particularly well-suited to these representations: we report a new state of the art on 2 out of 6 benchmarks we consider and strongly improve the generalization capability over unseen patterns. We release our code, data and model checkpoints at https://github.com/SapienzaNLP/extend.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Benchmarks ; Representations</subject><ispartof>arXiv.org, 2022-10</ispartof><rights>2022. This work is published under http://creativecommons.org/licenses/by-nc-sa/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>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2724079495?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>776,780,25732,36991,44569</link.rule.ids></links><search><creatorcontrib>Procopio, Luigi</creatorcontrib><creatorcontrib>Conia, Simone</creatorcontrib><creatorcontrib>Barba, Edoardo</creatorcontrib><creatorcontrib>Navigli, Roberto</creatorcontrib><title>Entity Disambiguation with Entity Definitions</title><title>arXiv.org</title><description>Local models have recently attained astounding performances in Entity Disambiguation (ED), with generative and extractive formulations being the most promising research directions. However, previous works limited their studies to using, as the textual representation of each candidate, only its Wikipedia title. Although certainly effective, this strategy presents a few critical issues, especially when titles are not sufficiently informative or distinguishable from one another. In this paper, we address this limitation and investigate to what extent more expressive textual representations can mitigate it. We thoroughly evaluate our approach against standard benchmarks in ED and find extractive formulations to be particularly well-suited to these representations: we report a new state of the art on 2 out of 6 benchmarks we consider and strongly improve the generalization capability over unseen patterns. We release our code, data and model checkpoints at https://github.com/SapienzaNLP/extend.</description><subject>Benchmarks</subject><subject>Representations</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQdc0rySypVHDJLE7MTcpML00syczPUyjPLMlQgEmlpmXmZYKEi3kYWNMSc4pTeaE0N4Oym2uIs4duQVF-YWlqcUl8Vn5pUR5QKt7I3MjEwNzSxNLUmDhVAO2AMnY</recordid><startdate>20221011</startdate><enddate>20221011</enddate><creator>Procopio, Luigi</creator><creator>Conia, Simone</creator><creator>Barba, Edoardo</creator><creator>Navigli, Roberto</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>20221011</creationdate><title>Entity Disambiguation with Entity Definitions</title><author>Procopio, Luigi ; Conia, Simone ; Barba, Edoardo ; Navigli, Roberto</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27240794953</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Benchmarks</topic><topic>Representations</topic><toplevel>online_resources</toplevel><creatorcontrib>Procopio, Luigi</creatorcontrib><creatorcontrib>Conia, Simone</creatorcontrib><creatorcontrib>Barba, Edoardo</creatorcontrib><creatorcontrib>Navigli, Roberto</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</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 Korea</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>Procopio, Luigi</au><au>Conia, Simone</au><au>Barba, Edoardo</au><au>Navigli, Roberto</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Entity Disambiguation with Entity Definitions</atitle><jtitle>arXiv.org</jtitle><date>2022-10-11</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Local models have recently attained astounding performances in Entity Disambiguation (ED), with generative and extractive formulations being the most promising research directions. However, previous works limited their studies to using, as the textual representation of each candidate, only its Wikipedia title. Although certainly effective, this strategy presents a few critical issues, especially when titles are not sufficiently informative or distinguishable from one another. In this paper, we address this limitation and investigate to what extent more expressive textual representations can mitigate it. We thoroughly evaluate our approach against standard benchmarks in ED and find extractive formulations to be particularly well-suited to these representations: we report a new state of the art on 2 out of 6 benchmarks we consider and strongly improve the generalization capability over unseen patterns. We release our code, data and model checkpoints at https://github.com/SapienzaNLP/extend.</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, 2022-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_2724079495
source Publicly Available Content Database
subjects Benchmarks
Representations
title Entity Disambiguation with Entity Definitions
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T17%3A23%3A29IST&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=Entity%20Disambiguation%20with%20Entity%20Definitions&rft.jtitle=arXiv.org&rft.au=Procopio,%20Luigi&rft.date=2022-10-11&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2724079495%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_27240794953%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2724079495&rft_id=info:pmid/&rfr_iscdi=true