Implicit discourse relation identification method and system based on comparative learning and Adapter network

The invention provides an implicit chapter relation identification method and system based on comparative learning and Adapter network, and the method comprises the steps: obtaining a naturally-labeled explicit chapter relation instance, and carrying out the combined training of a conjunction classi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: WU CHANGXING, XIE ZIRUO, LI XIONG, XIONG JINHUI, YAO HAO
Format: Patent
Sprache:chi ; eng
Schlagworte:
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 WU CHANGXING
XIE ZIRUO
LI XIONG
XIONG JINHUI
YAO HAO
description The invention provides an implicit chapter relation identification method and system based on comparative learning and Adapter network, and the method comprises the steps: obtaining a naturally-labeled explicit chapter relation instance, and carrying out the combined training of a conjunction classification model through the classification cost and the comparative learning cost based on the obtained explicit chapter relation instance, and constructing an implicit chapter relationship recognition model based on the trained conjunction classification model and the Adapter network, optimizing the implicit chapter relationship recognition model based on the manually labeled implicit chapter relationship instance, and recognizing the category of the implicit chapter relationship instance based on the implicit chapter relationship recognition model. According to the method, the problems that in the existing pre-training stage, explicit chapter relation data of natural annotation is not fully and effectively utilize
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116028630A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116028630A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116028630A3</originalsourceid><addsrcrecordid>eNqNykEKwjAQheFuXIh6h_EAQmuhuC1F0Y0r92VMpjqYTEImKt7eoh7A1ePnfdNCDj46NpzBsppwT0qQyGHmIMCWJPPA5pue8jVYQLGgL83k4YxKFsbLBB8xjexB4AiTsFw-sLUYMyUQys-QbvNiMqBTWvx2Vix321O3X1EMPWlEQ6Psu2NVNeV609RlW_9j3jGLQz0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Implicit discourse relation identification method and system based on comparative learning and Adapter network</title><source>esp@cenet</source><creator>WU CHANGXING ; XIE ZIRUO ; LI XIONG ; XIONG JINHUI ; YAO HAO</creator><creatorcontrib>WU CHANGXING ; XIE ZIRUO ; LI XIONG ; XIONG JINHUI ; YAO HAO</creatorcontrib><description>The invention provides an implicit chapter relation identification method and system based on comparative learning and Adapter network, and the method comprises the steps: obtaining a naturally-labeled explicit chapter relation instance, and carrying out the combined training of a conjunction classification model through the classification cost and the comparative learning cost based on the obtained explicit chapter relation instance, and constructing an implicit chapter relationship recognition model based on the trained conjunction classification model and the Adapter network, optimizing the implicit chapter relationship recognition model based on the manually labeled implicit chapter relationship instance, and recognizing the category of the implicit chapter relationship instance based on the implicit chapter relationship recognition model. According to the method, the problems that in the existing pre-training stage, explicit chapter relation data of natural annotation is not fully and effectively utilize</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2023</creationdate><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://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230428&amp;DB=EPODOC&amp;CC=CN&amp;NR=116028630A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230428&amp;DB=EPODOC&amp;CC=CN&amp;NR=116028630A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WU CHANGXING</creatorcontrib><creatorcontrib>XIE ZIRUO</creatorcontrib><creatorcontrib>LI XIONG</creatorcontrib><creatorcontrib>XIONG JINHUI</creatorcontrib><creatorcontrib>YAO HAO</creatorcontrib><title>Implicit discourse relation identification method and system based on comparative learning and Adapter network</title><description>The invention provides an implicit chapter relation identification method and system based on comparative learning and Adapter network, and the method comprises the steps: obtaining a naturally-labeled explicit chapter relation instance, and carrying out the combined training of a conjunction classification model through the classification cost and the comparative learning cost based on the obtained explicit chapter relation instance, and constructing an implicit chapter relationship recognition model based on the trained conjunction classification model and the Adapter network, optimizing the implicit chapter relationship recognition model based on the manually labeled implicit chapter relationship instance, and recognizing the category of the implicit chapter relationship instance based on the implicit chapter relationship recognition model. According to the method, the problems that in the existing pre-training stage, explicit chapter relation data of natural annotation is not fully and effectively utilize</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNykEKwjAQheFuXIh6h_EAQmuhuC1F0Y0r92VMpjqYTEImKt7eoh7A1ePnfdNCDj46NpzBsppwT0qQyGHmIMCWJPPA5pue8jVYQLGgL83k4YxKFsbLBB8xjexB4AiTsFw-sLUYMyUQys-QbvNiMqBTWvx2Vix321O3X1EMPWlEQ6Psu2NVNeV609RlW_9j3jGLQz0</recordid><startdate>20230428</startdate><enddate>20230428</enddate><creator>WU CHANGXING</creator><creator>XIE ZIRUO</creator><creator>LI XIONG</creator><creator>XIONG JINHUI</creator><creator>YAO HAO</creator><scope>EVB</scope></search><sort><creationdate>20230428</creationdate><title>Implicit discourse relation identification method and system based on comparative learning and Adapter network</title><author>WU CHANGXING ; XIE ZIRUO ; LI XIONG ; XIONG JINHUI ; YAO HAO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116028630A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>WU CHANGXING</creatorcontrib><creatorcontrib>XIE ZIRUO</creatorcontrib><creatorcontrib>LI XIONG</creatorcontrib><creatorcontrib>XIONG JINHUI</creatorcontrib><creatorcontrib>YAO HAO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WU CHANGXING</au><au>XIE ZIRUO</au><au>LI XIONG</au><au>XIONG JINHUI</au><au>YAO HAO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Implicit discourse relation identification method and system based on comparative learning and Adapter network</title><date>2023-04-28</date><risdate>2023</risdate><abstract>The invention provides an implicit chapter relation identification method and system based on comparative learning and Adapter network, and the method comprises the steps: obtaining a naturally-labeled explicit chapter relation instance, and carrying out the combined training of a conjunction classification model through the classification cost and the comparative learning cost based on the obtained explicit chapter relation instance, and constructing an implicit chapter relationship recognition model based on the trained conjunction classification model and the Adapter network, optimizing the implicit chapter relationship recognition model based on the manually labeled implicit chapter relationship instance, and recognizing the category of the implicit chapter relationship instance based on the implicit chapter relationship recognition model. According to the method, the problems that in the existing pre-training stage, explicit chapter relation data of natural annotation is not fully and effectively utilize</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116028630A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Implicit discourse relation identification method and system based on comparative learning and Adapter network
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T18%3A58%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=WU%20CHANGXING&rft.date=2023-04-28&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116028630A%3C/epo_EVB%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