Event extraction method and device
The invention provides an event extraction method and device, and the method comprises the steps: carrying out the fine adjustment of a general information extraction model according to small sample data, inputting raw corpus data into the fine-adjusted general information extraction model, and carr...
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 | MENG FANSHEN MIAO LIN LIU XIULEI GUO DONGDONG LI NING |
| description | The invention provides an event extraction method and device, and the method comprises the steps: carrying out the fine adjustment of a general information extraction model according to small sample data, inputting raw corpus data into the fine-adjusted general information extraction model, and carrying out the prediction, so as to obtain new sample data, the method comprises the following steps of: firstly, extracting UIE (User Identity Element), newly added sample data, then taking the small sample data and the newly added sample data as training data to train an ERNIE model, encoding a target text according to the trained ERNIE model to obtain a corresponding feature vector, and finally, decoding the feature vector according to a Global Pointer model to obtain an event element, extracting the event element based on the UIE, the ERNIE and the Global Pointer, and finally, extracting the event element based on the UIE, the ERNIE and the Global Pointer. According to the method, the training samples can be expa |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116663545A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116663545A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116663545A3</originalsourceid><addsrcrecordid>eNrjZFByLUvNK1FIrSgpSkwuyczPU8hNLcnIT1FIzEtRSEkty0xO5WFgTUvMKU7lhdLcDIpuriHOHrqpBfnxqcUFicmpeakl8c5-hoZmZmbGpiamjsbEqAEArLIl-g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Event extraction method and device</title><source>esp@cenet</source><creator>MENG FANSHEN ; MIAO LIN ; LIU XIULEI ; GUO DONGDONG ; LI NING</creator><creatorcontrib>MENG FANSHEN ; MIAO LIN ; LIU XIULEI ; GUO DONGDONG ; LI NING</creatorcontrib><description>The invention provides an event extraction method and device, and the method comprises the steps: carrying out the fine adjustment of a general information extraction model according to small sample data, inputting raw corpus data into the fine-adjusted general information extraction model, and carrying out the prediction, so as to obtain new sample data, the method comprises the following steps of: firstly, extracting UIE (User Identity Element), newly added sample data, then taking the small sample data and the newly added sample data as training data to train an ERNIE model, encoding a target text according to the trained ERNIE model to obtain a corresponding feature vector, and finally, decoding the feature vector according to a Global Pointer model to obtain an event element, extracting the event element based on the UIE, the ERNIE and the Global Pointer, and finally, extracting the event element based on the UIE, the ERNIE and the Global Pointer. According to the method, the training samples can be expa</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&date=20230829&DB=EPODOC&CC=CN&NR=116663545A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230829&DB=EPODOC&CC=CN&NR=116663545A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>MENG FANSHEN</creatorcontrib><creatorcontrib>MIAO LIN</creatorcontrib><creatorcontrib>LIU XIULEI</creatorcontrib><creatorcontrib>GUO DONGDONG</creatorcontrib><creatorcontrib>LI NING</creatorcontrib><title>Event extraction method and device</title><description>The invention provides an event extraction method and device, and the method comprises the steps: carrying out the fine adjustment of a general information extraction model according to small sample data, inputting raw corpus data into the fine-adjusted general information extraction model, and carrying out the prediction, so as to obtain new sample data, the method comprises the following steps of: firstly, extracting UIE (User Identity Element), newly added sample data, then taking the small sample data and the newly added sample data as training data to train an ERNIE model, encoding a target text according to the trained ERNIE model to obtain a corresponding feature vector, and finally, decoding the feature vector according to a Global Pointer model to obtain an event element, extracting the event element based on the UIE, the ERNIE and the Global Pointer, and finally, extracting the event element based on the UIE, the ERNIE and the Global Pointer. According to the method, the training samples can be expa</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>eNrjZFByLUvNK1FIrSgpSkwuyczPU8hNLcnIT1FIzEtRSEkty0xO5WFgTUvMKU7lhdLcDIpuriHOHrqpBfnxqcUFicmpeakl8c5-hoZmZmbGpiamjsbEqAEArLIl-g</recordid><startdate>20230829</startdate><enddate>20230829</enddate><creator>MENG FANSHEN</creator><creator>MIAO LIN</creator><creator>LIU XIULEI</creator><creator>GUO DONGDONG</creator><creator>LI NING</creator><scope>EVB</scope></search><sort><creationdate>20230829</creationdate><title>Event extraction method and device</title><author>MENG FANSHEN ; MIAO LIN ; LIU XIULEI ; GUO DONGDONG ; LI NING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116663545A3</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>MENG FANSHEN</creatorcontrib><creatorcontrib>MIAO LIN</creatorcontrib><creatorcontrib>LIU XIULEI</creatorcontrib><creatorcontrib>GUO DONGDONG</creatorcontrib><creatorcontrib>LI NING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>MENG FANSHEN</au><au>MIAO LIN</au><au>LIU XIULEI</au><au>GUO DONGDONG</au><au>LI NING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Event extraction method and device</title><date>2023-08-29</date><risdate>2023</risdate><abstract>The invention provides an event extraction method and device, and the method comprises the steps: carrying out the fine adjustment of a general information extraction model according to small sample data, inputting raw corpus data into the fine-adjusted general information extraction model, and carrying out the prediction, so as to obtain new sample data, the method comprises the following steps of: firstly, extracting UIE (User Identity Element), newly added sample data, then taking the small sample data and the newly added sample data as training data to train an ERNIE model, encoding a target text according to the trained ERNIE model to obtain a corresponding feature vector, and finally, decoding the feature vector according to a Global Pointer model to obtain an event element, extracting the event element based on the UIE, the ERNIE and the Global Pointer, and finally, extracting the event element based on the UIE, the ERNIE and the Global Pointer. According to the method, the training samples can be expa</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN116663545A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Event extraction method and device |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T12%3A20%3A11IST&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=MENG%20FANSHEN&rft.date=2023-08-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116663545A%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 |