ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations

ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations

The current workflow for Information Extraction (IE) analysts involves the definition of the entities/relations of interest and a training corpus with annotated examples. In this demonstration we introduce a new workflow where the analyst directly verbalizes the entities/relations, which are then us...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sainz, Oscar, Qiu, Haoling, de Lacalle, Oier Lopez, Agirre, Eneko, Min, Bonan
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 Sainz, Oscar
Qiu, Haoling
de Lacalle, Oier Lopez
Agirre, Eneko
Min, Bonan
description The current workflow for Information Extraction (IE) analysts involves the definition of the entities/relations of interest and a training corpus with annotated examples. In this demonstration we introduce a new workflow where the analyst directly verbalizes the entities/relations, which are then used by a Textual Entailment model to perform zero-shot IE. We present the design and implementation of a toolkit with a user interface, as well as experiments on four IE tasks that show that the system achieves very good performance at zero-shot learning using only 5--15 minutes per type of a user's effort. Our demonstration system is open-sourced at https://github.com/BBN-E/ZS4IE . A demonstration video is available at https://vimeo.com/676138340 .
doi_str_mv 10.48550/arxiv.2203.13602
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2203_13602</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2203_13602</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-7aada50ddc14f69109a4cb7ccd078b2e6145d88ece3d99190304bd0430975ccc3</originalsourceid><addsrcrecordid>eNotj81Kw0AUhWfjQqoP4Mp5gcQ7f0nGXSlRAwWFFhfdhJuZCR1MOmUyaPXpW6Orcw58HPgIuWOQy0opeMB48p855yByJgrg1-Rtt5FN_UiXNIUwfPhE-xDpzsWQbfYh0eZw2SMmHw60PqWIZq5fPu3p5Mfj4Oi7ix0O_meGphty1eMwudv_XJDtU71dvWTr1-dmtVxnWJQ8KxEtKrDWMNkXmoFGabrSGAtl1XFXMKlsVTnjhNWaaRAgOwtSgC6VMUYsyP3f7azUHqMfMX63v2rtrCbOAVRJkA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations</title><source>arXiv.org</source><creator>Sainz, Oscar ; Qiu, Haoling ; de Lacalle, Oier Lopez ; Agirre, Eneko ; Min, Bonan</creator><creatorcontrib>Sainz, Oscar ; Qiu, Haoling ; de Lacalle, Oier Lopez ; Agirre, Eneko ; Min, Bonan</creatorcontrib><description>The current workflow for Information Extraction (IE) analysts involves the definition of the entities/relations of interest and a training corpus with annotated examples. In this demonstration we introduce a new workflow where the analyst directly verbalizes the entities/relations, which are then used by a Textual Entailment model to perform zero-shot IE. We present the design and implementation of a toolkit with a user interface, as well as experiments on four IE tasks that show that the system achieves very good performance at zero-shot learning using only 5--15 minutes per type of a user's effort. Our demonstration system is open-sourced at https://github.com/BBN-E/ZS4IE . A demonstration video is available at https://vimeo.com/676138340 .</description><identifier>DOI: 10.48550/arxiv.2203.13602</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2022-03</creationdate><rights>http://creativecommons.org/licenses/by-sa/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/2203.13602$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2203.13602$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Sainz, Oscar</creatorcontrib><creatorcontrib>Qiu, Haoling</creatorcontrib><creatorcontrib>de Lacalle, Oier Lopez</creatorcontrib><creatorcontrib>Agirre, Eneko</creatorcontrib><creatorcontrib>Min, Bonan</creatorcontrib><title>ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations</title><description>The current workflow for Information Extraction (IE) analysts involves the definition of the entities/relations of interest and a training corpus with annotated examples. In this demonstration we introduce a new workflow where the analyst directly verbalizes the entities/relations, which are then used by a Textual Entailment model to perform zero-shot IE. We present the design and implementation of a toolkit with a user interface, as well as experiments on four IE tasks that show that the system achieves very good performance at zero-shot learning using only 5--15 minutes per type of a user's effort. Our demonstration system is open-sourced at https://github.com/BBN-E/ZS4IE . A demonstration video is available at https://vimeo.com/676138340 .</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81Kw0AUhWfjQqoP4Mp5gcQ7f0nGXSlRAwWFFhfdhJuZCR1MOmUyaPXpW6Orcw58HPgIuWOQy0opeMB48p855yByJgrg1-Rtt5FN_UiXNIUwfPhE-xDpzsWQbfYh0eZw2SMmHw60PqWIZq5fPu3p5Mfj4Oi7ix0O_meGphty1eMwudv_XJDtU71dvWTr1-dmtVxnWJQ8KxEtKrDWMNkXmoFGabrSGAtl1XFXMKlsVTnjhNWaaRAgOwtSgC6VMUYsyP3f7azUHqMfMX63v2rtrCbOAVRJkA</recordid><startdate>20220325</startdate><enddate>20220325</enddate><creator>Sainz, Oscar</creator><creator>Qiu, Haoling</creator><creator>de Lacalle, Oier Lopez</creator><creator>Agirre, Eneko</creator><creator>Min, Bonan</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220325</creationdate><title>ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations</title><author>Sainz, Oscar ; Qiu, Haoling ; de Lacalle, Oier Lopez ; Agirre, Eneko ; Min, Bonan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-7aada50ddc14f69109a4cb7ccd078b2e6145d88ece3d99190304bd0430975ccc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Sainz, Oscar</creatorcontrib><creatorcontrib>Qiu, Haoling</creatorcontrib><creatorcontrib>de Lacalle, Oier Lopez</creatorcontrib><creatorcontrib>Agirre, Eneko</creatorcontrib><creatorcontrib>Min, Bonan</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sainz, Oscar</au><au>Qiu, Haoling</au><au>de Lacalle, Oier Lopez</au><au>Agirre, Eneko</au><au>Min, Bonan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations</atitle><date>2022-03-25</date><risdate>2022</risdate><abstract>The current workflow for Information Extraction (IE) analysts involves the definition of the entities/relations of interest and a training corpus with annotated examples. In this demonstration we introduce a new workflow where the analyst directly verbalizes the entities/relations, which are then used by a Textual Entailment model to perform zero-shot IE. We present the design and implementation of a toolkit with a user interface, as well as experiments on four IE tasks that show that the system achieves very good performance at zero-shot learning using only 5--15 minutes per type of a user's effort. Our demonstration system is open-sourced at https://github.com/BBN-E/ZS4IE . A demonstration video is available at https://vimeo.com/676138340 .</abstract><doi>10.48550/arxiv.2203.13602</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2203.13602
ispartof
issn
language eng
recordid cdi_arxiv_primary_2203_13602
source arXiv.org
subjects Computer Science - Computation and Language
title ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-16T03%3A21%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=ZS4IE:%20A%20toolkit%20for%20Zero-Shot%20Information%20Extraction%20with%20simple%20Verbalizations&rft.au=Sainz,%20Oscar&rft.date=2022-03-25&rft_id=info:doi/10.48550/arxiv.2203.13602&rft_dat=%3Carxiv_GOX%3E2203_13602%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