SPE: Symmetrical Prompt Enhancement for Fact Probing

Pretrained language models (PLMs) have been shown to accumulate factual knowledge during pretrainingng (Petroni et al., 2019). Recent works probe PLMs for the extent of this knowledge through prompts either in discrete or continuous forms. However, these methods do not consider symmetry of the task:...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-11
Main Authors: Li, Yiyuan, Tong Che, Wang, Yezhen, Jiang, Zhengbao, Xiong, Caiming, Chaturvedi, Snigdha
Format: Article
Language:English
Subjects:
Symmetry
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 Li, Yiyuan
Tong Che
Wang, Yezhen
Jiang, Zhengbao
Xiong, Caiming
Chaturvedi, Snigdha
description Pretrained language models (PLMs) have been shown to accumulate factual knowledge during pretrainingng (Petroni et al., 2019). Recent works probe PLMs for the extent of this knowledge through prompts either in discrete or continuous forms. However, these methods do not consider symmetry of the task: object prediction and subject prediction. In this work, we propose Symmetrical Prompt Enhancement (SPE), a continuous prompt-based method for factual probing in PLMs that leverages the symmetry of the task by constructing symmetrical prompts for subject and object prediction. Our results on a popular factual probing dataset, LAMA, show significant improvement of SPE over previous probing methods.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2736486917</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2736486917</sourcerecordid><originalsourceid>FETCH-proquest_journals_27364869173</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQwCQ5wtVIIrszNTS0pykxOzFEIKMrPLShRcM3LSMxLTs1NzStRSMsvUnBLTC4BySVl5qXzMLCmJeYUp_JCaW4GZTfXEGcP3YKi_MLS1OKS-Kz80qI8oFS8kbmxmYmFmaWhuTFxqgAHKDQN</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2736486917</pqid></control><display><type>article</type><title>SPE: Symmetrical Prompt Enhancement for Fact Probing</title><source>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</source><creator>Li, Yiyuan ; Tong Che ; Wang, Yezhen ; Jiang, Zhengbao ; Xiong, Caiming ; Chaturvedi, Snigdha</creator><creatorcontrib>Li, Yiyuan ; Tong Che ; Wang, Yezhen ; Jiang, Zhengbao ; Xiong, Caiming ; Chaturvedi, Snigdha</creatorcontrib><description>Pretrained language models (PLMs) have been shown to accumulate factual knowledge during pretrainingng (Petroni et al., 2019). Recent works probe PLMs for the extent of this knowledge through prompts either in discrete or continuous forms. However, these methods do not consider symmetry of the task: object prediction and subject prediction. In this work, we propose Symmetrical Prompt Enhancement (SPE), a continuous prompt-based method for factual probing in PLMs that leverages the symmetry of the task by constructing symmetrical prompts for subject and object prediction. Our results on a popular factual probing dataset, LAMA, show significant improvement of SPE over previous probing methods.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Symmetry</subject><ispartof>arXiv.org, 2022-11</ispartof><rights>2022. This work is published under http://creativecommons.org/licenses/by-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/2736486917?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Li, Yiyuan</creatorcontrib><creatorcontrib>Tong Che</creatorcontrib><creatorcontrib>Wang, Yezhen</creatorcontrib><creatorcontrib>Jiang, Zhengbao</creatorcontrib><creatorcontrib>Xiong, Caiming</creatorcontrib><creatorcontrib>Chaturvedi, Snigdha</creatorcontrib><title>SPE: Symmetrical Prompt Enhancement for Fact Probing</title><title>arXiv.org</title><description>Pretrained language models (PLMs) have been shown to accumulate factual knowledge during pretrainingng (Petroni et al., 2019). Recent works probe PLMs for the extent of this knowledge through prompts either in discrete or continuous forms. However, these methods do not consider symmetry of the task: object prediction and subject prediction. In this work, we propose Symmetrical Prompt Enhancement (SPE), a continuous prompt-based method for factual probing in PLMs that leverages the symmetry of the task by constructing symmetrical prompts for subject and object prediction. Our results on a popular factual probing dataset, LAMA, show significant improvement of SPE over previous probing methods.</description><subject>Symmetry</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQwCQ5wtVIIrszNTS0pykxOzFEIKMrPLShRcM3LSMxLTs1NzStRSMsvUnBLTC4BySVl5qXzMLCmJeYUp_JCaW4GZTfXEGcP3YKi_MLS1OKS-Kz80qI8oFS8kbmxmYmFmaWhuTFxqgAHKDQN</recordid><startdate>20221114</startdate><enddate>20221114</enddate><creator>Li, Yiyuan</creator><creator>Tong Che</creator><creator>Wang, Yezhen</creator><creator>Jiang, Zhengbao</creator><creator>Xiong, Caiming</creator><creator>Chaturvedi, Snigdha</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>20221114</creationdate><title>SPE: Symmetrical Prompt Enhancement for Fact Probing</title><author>Li, Yiyuan ; Tong Che ; Wang, Yezhen ; Jiang, Zhengbao ; Xiong, Caiming ; Chaturvedi, Snigdha</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27364869173</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Symmetry</topic><toplevel>online_resources</toplevel><creatorcontrib>Li, Yiyuan</creatorcontrib><creatorcontrib>Tong Che</creatorcontrib><creatorcontrib>Wang, Yezhen</creatorcontrib><creatorcontrib>Jiang, Zhengbao</creatorcontrib><creatorcontrib>Xiong, Caiming</creatorcontrib><creatorcontrib>Chaturvedi, Snigdha</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>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</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>Li, Yiyuan</au><au>Tong Che</au><au>Wang, Yezhen</au><au>Jiang, Zhengbao</au><au>Xiong, Caiming</au><au>Chaturvedi, Snigdha</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>SPE: Symmetrical Prompt Enhancement for Fact Probing</atitle><jtitle>arXiv.org</jtitle><date>2022-11-14</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Pretrained language models (PLMs) have been shown to accumulate factual knowledge during pretrainingng (Petroni et al., 2019). Recent works probe PLMs for the extent of this knowledge through prompts either in discrete or continuous forms. However, these methods do not consider symmetry of the task: object prediction and subject prediction. In this work, we propose Symmetrical Prompt Enhancement (SPE), a continuous prompt-based method for factual probing in PLMs that leverages the symmetry of the task by constructing symmetrical prompts for subject and object prediction. Our results on a popular factual probing dataset, LAMA, show significant improvement of SPE over previous probing methods.</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, 2022-11
issn 2331-8422
language eng
recordid cdi_proquest_journals_2736486917
source Publicly Available Content Database (Proquest) (PQ_SDU_P3)
subjects Symmetry
title SPE: Symmetrical Prompt Enhancement for Fact Probing
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T00%3A03%3A51IST&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=SPE:%20Symmetrical%20Prompt%20Enhancement%20for%20Fact%20Probing&rft.jtitle=arXiv.org&rft.au=Li,%20Yiyuan&rft.date=2022-11-14&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2736486917%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_27364869173%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2736486917&rft_id=info:pmid/&rfr_iscdi=true