Transform-XL-based keyword article generation method
The invention discloses a transform-XL-based keyword article generation method, and relates to the field of NLP text generation. The method for generating the article based on the keywords of the transform-XL mainly comprises the links of data collection, data processing, network construction, model...
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 | CAO MENGJIA YU WENLI FAN SHUNGUO ZHAO BIN CAO LINA ZHANG SHUYU HOU SHENGWEN YAO KAI |
| description | The invention discloses a transform-XL-based keyword article generation method, and relates to the field of NLP text generation. The method for generating the article based on the keywords of the transform-XL mainly comprises the links of data collection, data processing, network construction, model training and effect verification. According to the method for generating the article through the keywords based on the transform-XL, the idea is innovated in the aspect of sample construction, topic requirements of public users are met by crawling hot topic construction, the limitation that samples are only constructed in a certain single field in the past is broken through, and the method for automatically verifying the effect of a text generation model is provided; the method has the advantages that model verification efficiency and iteration speed are greatly improved, a transform-XL depth model is applied to a keyword generation article task, long texts can be quickly processed, and the limitation that a tradi |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117829278A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117829278A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117829278A3</originalsourceid><addsrcrecordid>eNrjZDAJKUrMK07LL8rVjfDRTUosTk1RyE6tLM8vSlFILCrJTM5JVUhPzUstSizJzM9TyE0tychP4WFgTUvMKU7lhdLcDIpuriHOHrqpBfnxqcUFiclAHSXxzn6GhuYWRpZG5haOxsSoAQA-wC0E</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Transform-XL-based keyword article generation method</title><source>esp@cenet</source><creator>CAO MENGJIA ; YU WENLI ; FAN SHUNGUO ; ZHAO BIN ; CAO LINA ; ZHANG SHUYU ; HOU SHENGWEN ; YAO KAI</creator><creatorcontrib>CAO MENGJIA ; YU WENLI ; FAN SHUNGUO ; ZHAO BIN ; CAO LINA ; ZHANG SHUYU ; HOU SHENGWEN ; YAO KAI</creatorcontrib><description>The invention discloses a transform-XL-based keyword article generation method, and relates to the field of NLP text generation. The method for generating the article based on the keywords of the transform-XL mainly comprises the links of data collection, data processing, network construction, model training and effect verification. According to the method for generating the article through the keywords based on the transform-XL, the idea is innovated in the aspect of sample construction, topic requirements of public users are met by crawling hot topic construction, the limitation that samples are only constructed in a certain single field in the past is broken through, and the method for automatically verifying the effect of a text generation model is provided; the method has the advantages that model verification efficiency and iteration speed are greatly improved, a transform-XL depth model is applied to a keyword generation article task, long texts can be quickly processed, and the limitation that a tradi</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2024</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=20240405&DB=EPODOC&CC=CN&NR=117829278A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76318</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240405&DB=EPODOC&CC=CN&NR=117829278A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CAO MENGJIA</creatorcontrib><creatorcontrib>YU WENLI</creatorcontrib><creatorcontrib>FAN SHUNGUO</creatorcontrib><creatorcontrib>ZHAO BIN</creatorcontrib><creatorcontrib>CAO LINA</creatorcontrib><creatorcontrib>ZHANG SHUYU</creatorcontrib><creatorcontrib>HOU SHENGWEN</creatorcontrib><creatorcontrib>YAO KAI</creatorcontrib><title>Transform-XL-based keyword article generation method</title><description>The invention discloses a transform-XL-based keyword article generation method, and relates to the field of NLP text generation. The method for generating the article based on the keywords of the transform-XL mainly comprises the links of data collection, data processing, network construction, model training and effect verification. According to the method for generating the article through the keywords based on the transform-XL, the idea is innovated in the aspect of sample construction, topic requirements of public users are met by crawling hot topic construction, the limitation that samples are only constructed in a certain single field in the past is broken through, and the method for automatically verifying the effect of a text generation model is provided; the method has the advantages that model verification efficiency and iteration speed are greatly improved, a transform-XL depth model is applied to a keyword generation article task, long texts can be quickly processed, and the limitation that a tradi</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDAJKUrMK07LL8rVjfDRTUosTk1RyE6tLM8vSlFILCrJTM5JVUhPzUstSizJzM9TyE0tychP4WFgTUvMKU7lhdLcDIpuriHOHrqpBfnxqcUFiclAHSXxzn6GhuYWRpZG5haOxsSoAQA-wC0E</recordid><startdate>20240405</startdate><enddate>20240405</enddate><creator>CAO MENGJIA</creator><creator>YU WENLI</creator><creator>FAN SHUNGUO</creator><creator>ZHAO BIN</creator><creator>CAO LINA</creator><creator>ZHANG SHUYU</creator><creator>HOU SHENGWEN</creator><creator>YAO KAI</creator><scope>EVB</scope></search><sort><creationdate>20240405</creationdate><title>Transform-XL-based keyword article generation method</title><author>CAO MENGJIA ; YU WENLI ; FAN SHUNGUO ; ZHAO BIN ; CAO LINA ; ZHANG SHUYU ; HOU SHENGWEN ; YAO KAI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117829278A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</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>CAO MENGJIA</creatorcontrib><creatorcontrib>YU WENLI</creatorcontrib><creatorcontrib>FAN SHUNGUO</creatorcontrib><creatorcontrib>ZHAO BIN</creatorcontrib><creatorcontrib>CAO LINA</creatorcontrib><creatorcontrib>ZHANG SHUYU</creatorcontrib><creatorcontrib>HOU SHENGWEN</creatorcontrib><creatorcontrib>YAO KAI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CAO MENGJIA</au><au>YU WENLI</au><au>FAN SHUNGUO</au><au>ZHAO BIN</au><au>CAO LINA</au><au>ZHANG SHUYU</au><au>HOU SHENGWEN</au><au>YAO KAI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Transform-XL-based keyword article generation method</title><date>2024-04-05</date><risdate>2024</risdate><abstract>The invention discloses a transform-XL-based keyword article generation method, and relates to the field of NLP text generation. The method for generating the article based on the keywords of the transform-XL mainly comprises the links of data collection, data processing, network construction, model training and effect verification. According to the method for generating the article through the keywords based on the transform-XL, the idea is innovated in the aspect of sample construction, topic requirements of public users are met by crawling hot topic construction, the limitation that samples are only constructed in a certain single field in the past is broken through, and the method for automatically verifying the effect of a text generation model is provided; the method has the advantages that model verification efficiency and iteration speed are greatly improved, a transform-XL depth model is applied to a keyword generation article task, long texts can be quickly processed, and the limitation that a tradi</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN117829278A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Transform-XL-based keyword article generation method |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T19%3A13%3A45IST&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=CAO%20MENGJIA&rft.date=2024-04-05&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117829278A%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 |