Zero sample event extraction system and method based on comparative learning and data enhancement
The invention discloses a zero sample event extraction system and method based on comparative learning and data enhancement in the technical field of natural language processing, and the method comprises the steps: obtaining a data set, and dividing the data set into known events and unknown events;...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| 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 | QIU ZHENYU JI TAO KONG WEIJING ZHOU YIHANG JI WENDI ZHANG SENHUI WU YUANBIN ZHU DEWEI ZHU BING WANG XIAOLING |
| description | The invention discloses a zero sample event extraction system and method based on comparative learning and data enhancement in the technical field of natural language processing, and the method comprises the steps: obtaining a data set, and dividing the data set into known events and unknown events; rewriting the event description text of the unknown event; forming a positive and negative sample pair by the known event, the unknown event and the unknown event subjected to event description rewriting; inputting the positive and negative sample pairs into an event encoder to generate corresponding feature vectors; after a comparison loss function value is calculated based on the feature vector, model parameters in the event encoder are updated through gradient return; and performing classification and clustering based on the updated feature vector input output by the event encoder. According to the method, by comparing similar and heterogeneous samples, the annotation data of the known event and the unannotated |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114707483A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114707483A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114707483A3</originalsourceid><addsrcrecordid>eNqNjLEKwkAQBdNYiPoP6wcIhgRiG4JiZWVlE9a7pznI7R13S9C_N4gfYDXFDLMs-IYUKLOPIwgTRAkvTWzUBaH8zgpPLJY8dAiW7pxhaVYm-MiJ1U2gEZzEyfMbWlYmyMBi4Offulg8eMzY_LgqtqfjtTvvEEOPHNlAoH13Kcu62Tf1oWqrf5oPKZI95g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Zero sample event extraction system and method based on comparative learning and data enhancement</title><source>esp@cenet</source><creator>QIU ZHENYU ; JI TAO ; KONG WEIJING ; ZHOU YIHANG ; JI WENDI ; ZHANG SENHUI ; WU YUANBIN ; ZHU DEWEI ; ZHU BING ; WANG XIAOLING</creator><creatorcontrib>QIU ZHENYU ; JI TAO ; KONG WEIJING ; ZHOU YIHANG ; JI WENDI ; ZHANG SENHUI ; WU YUANBIN ; ZHU DEWEI ; ZHU BING ; WANG XIAOLING</creatorcontrib><description>The invention discloses a zero sample event extraction system and method based on comparative learning and data enhancement in the technical field of natural language processing, and the method comprises the steps: obtaining a data set, and dividing the data set into known events and unknown events; rewriting the event description text of the unknown event; forming a positive and negative sample pair by the known event, the unknown event and the unknown event subjected to event description rewriting; inputting the positive and negative sample pairs into an event encoder to generate corresponding feature vectors; after a comparison loss function value is calculated based on the feature vector, model parameters in the event encoder are updated through gradient return; and performing classification and clustering based on the updated feature vector input output by the event encoder. According to the method, by comparing similar and heterogeneous samples, the annotation data of the known event and the unannotated</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2022</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&date=20220705&DB=EPODOC&CC=CN&NR=114707483A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220705&DB=EPODOC&CC=CN&NR=114707483A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>QIU ZHENYU</creatorcontrib><creatorcontrib>JI TAO</creatorcontrib><creatorcontrib>KONG WEIJING</creatorcontrib><creatorcontrib>ZHOU YIHANG</creatorcontrib><creatorcontrib>JI WENDI</creatorcontrib><creatorcontrib>ZHANG SENHUI</creatorcontrib><creatorcontrib>WU YUANBIN</creatorcontrib><creatorcontrib>ZHU DEWEI</creatorcontrib><creatorcontrib>ZHU BING</creatorcontrib><creatorcontrib>WANG XIAOLING</creatorcontrib><title>Zero sample event extraction system and method based on comparative learning and data enhancement</title><description>The invention discloses a zero sample event extraction system and method based on comparative learning and data enhancement in the technical field of natural language processing, and the method comprises the steps: obtaining a data set, and dividing the data set into known events and unknown events; rewriting the event description text of the unknown event; forming a positive and negative sample pair by the known event, the unknown event and the unknown event subjected to event description rewriting; inputting the positive and negative sample pairs into an event encoder to generate corresponding feature vectors; after a comparison loss function value is calculated based on the feature vector, model parameters in the event encoder are updated through gradient return; and performing classification and clustering based on the updated feature vector input output by the event encoder. According to the method, by comparing similar and heterogeneous samples, the annotation data of the known event and the unannotated</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjLEKwkAQBdNYiPoP6wcIhgRiG4JiZWVlE9a7pznI7R13S9C_N4gfYDXFDLMs-IYUKLOPIwgTRAkvTWzUBaH8zgpPLJY8dAiW7pxhaVYm-MiJ1U2gEZzEyfMbWlYmyMBi4Offulg8eMzY_LgqtqfjtTvvEEOPHNlAoH13Kcu62Tf1oWqrf5oPKZI95g</recordid><startdate>20220705</startdate><enddate>20220705</enddate><creator>QIU ZHENYU</creator><creator>JI TAO</creator><creator>KONG WEIJING</creator><creator>ZHOU YIHANG</creator><creator>JI WENDI</creator><creator>ZHANG SENHUI</creator><creator>WU YUANBIN</creator><creator>ZHU DEWEI</creator><creator>ZHU BING</creator><creator>WANG XIAOLING</creator><scope>EVB</scope></search><sort><creationdate>20220705</creationdate><title>Zero sample event extraction system and method based on comparative learning and data enhancement</title><author>QIU ZHENYU ; JI TAO ; KONG WEIJING ; ZHOU YIHANG ; JI WENDI ; ZHANG SENHUI ; WU YUANBIN ; ZHU DEWEI ; ZHU BING ; WANG XIAOLING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114707483A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>QIU ZHENYU</creatorcontrib><creatorcontrib>JI TAO</creatorcontrib><creatorcontrib>KONG WEIJING</creatorcontrib><creatorcontrib>ZHOU YIHANG</creatorcontrib><creatorcontrib>JI WENDI</creatorcontrib><creatorcontrib>ZHANG SENHUI</creatorcontrib><creatorcontrib>WU YUANBIN</creatorcontrib><creatorcontrib>ZHU DEWEI</creatorcontrib><creatorcontrib>ZHU BING</creatorcontrib><creatorcontrib>WANG XIAOLING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>QIU ZHENYU</au><au>JI TAO</au><au>KONG WEIJING</au><au>ZHOU YIHANG</au><au>JI WENDI</au><au>ZHANG SENHUI</au><au>WU YUANBIN</au><au>ZHU DEWEI</au><au>ZHU BING</au><au>WANG XIAOLING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Zero sample event extraction system and method based on comparative learning and data enhancement</title><date>2022-07-05</date><risdate>2022</risdate><abstract>The invention discloses a zero sample event extraction system and method based on comparative learning and data enhancement in the technical field of natural language processing, and the method comprises the steps: obtaining a data set, and dividing the data set into known events and unknown events; rewriting the event description text of the unknown event; forming a positive and negative sample pair by the known event, the unknown event and the unknown event subjected to event description rewriting; inputting the positive and negative sample pairs into an event encoder to generate corresponding feature vectors; after a comparison loss function value is calculated based on the feature vector, model parameters in the event encoder are updated through gradient return; and performing classification and clustering based on the updated feature vector input output by the event encoder. According to the method, by comparing similar and heterogeneous samples, the annotation data of the known event and the unannotated</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN114707483A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Zero sample event extraction system and method based on comparative learning and data enhancement |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T21%3A32%3A52IST&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=QIU%20ZHENYU&rft.date=2022-07-05&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114707483A%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 |