Code annotation generation method based on dense retrieval
The invention discloses a code annotation generation method based on dense retrieval and relation modeling, which uses dense retrieval to retrieve related annotations as additional inputs, and extracts the relation between codes and the additional annotation inputs, thereby improving the annotation...
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 | FU HAN ZHANG PINHAN SUN JIANLING |
| description | The invention discloses a code annotation generation method based on dense retrieval and relation modeling, which uses dense retrieval to retrieve related annotations as additional inputs, and extracts the relation between codes and the additional annotation inputs, thereby improving the annotation generation quality. According to the method, a retriever is mainly used for retrieving related annotations of input codes in a retrieval set, the codes and the retrieved annotations are spliced and then input into a discriminator, a fusion representation vector, a relation representation vector and relation classification are obtained, the fusion representation vector and the relation representation vector are input into a second multi-layer decoder, and code annotations are generated. According to the method, the relation between the additional input and the original input is considered for the first time, the generator can be effectively prevented from being misled, and then the generation effect is improved.
本发明 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116974625A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116974625A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116974625A3</originalsourceid><addsrcrecordid>eNrjZLByzk9JVUjMy8svSSzJzM9TSE_NSy2CMHNTSzLyUxSSEotTUxSA_JTUvOJUhaLUkqLM1LLEHB4G1rTEnOJUXijNzaDo5hri7KGbWpAfn1pckJgMNKok3tnP0NDM0tzEzMjU0ZgYNQCBAC8v</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Code annotation generation method based on dense retrieval</title><source>esp@cenet</source><creator>FU HAN ; ZHANG PINHAN ; SUN JIANLING</creator><creatorcontrib>FU HAN ; ZHANG PINHAN ; SUN JIANLING</creatorcontrib><description>The invention discloses a code annotation generation method based on dense retrieval and relation modeling, which uses dense retrieval to retrieve related annotations as additional inputs, and extracts the relation between codes and the additional annotation inputs, thereby improving the annotation generation quality. According to the method, a retriever is mainly used for retrieving related annotations of input codes in a retrieval set, the codes and the retrieved annotations are spliced and then input into a discriminator, a fusion representation vector, a relation representation vector and relation classification are obtained, the fusion representation vector and the relation representation vector are input into a second multi-layer decoder, and code annotations are generated. According to the method, the relation between the additional input and the original input is considered for the first time, the generator can be effectively prevented from being misled, and then the generation effect is improved.
本发明</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=20231031&DB=EPODOC&CC=CN&NR=116974625A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,777,882,25545,76296</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231031&DB=EPODOC&CC=CN&NR=116974625A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>FU HAN</creatorcontrib><creatorcontrib>ZHANG PINHAN</creatorcontrib><creatorcontrib>SUN JIANLING</creatorcontrib><title>Code annotation generation method based on dense retrieval</title><description>The invention discloses a code annotation generation method based on dense retrieval and relation modeling, which uses dense retrieval to retrieve related annotations as additional inputs, and extracts the relation between codes and the additional annotation inputs, thereby improving the annotation generation quality. According to the method, a retriever is mainly used for retrieving related annotations of input codes in a retrieval set, the codes and the retrieved annotations are spliced and then input into a discriminator, a fusion representation vector, a relation representation vector and relation classification are obtained, the fusion representation vector and the relation representation vector are input into a second multi-layer decoder, and code annotations are generated. According to the method, the relation between the additional input and the original input is considered for the first time, the generator can be effectively prevented from being misled, and then the generation effect is improved.
本发明</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>eNrjZLByzk9JVUjMy8svSSzJzM9TSE_NSy2CMHNTSzLyUxSSEotTUxSA_JTUvOJUhaLUkqLM1LLEHB4G1rTEnOJUXijNzaDo5hri7KGbWpAfn1pckJgMNKok3tnP0NDM0tzEzMjU0ZgYNQCBAC8v</recordid><startdate>20231031</startdate><enddate>20231031</enddate><creator>FU HAN</creator><creator>ZHANG PINHAN</creator><creator>SUN JIANLING</creator><scope>EVB</scope></search><sort><creationdate>20231031</creationdate><title>Code annotation generation method based on dense retrieval</title><author>FU HAN ; ZHANG PINHAN ; SUN JIANLING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116974625A3</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>FU HAN</creatorcontrib><creatorcontrib>ZHANG PINHAN</creatorcontrib><creatorcontrib>SUN JIANLING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>FU HAN</au><au>ZHANG PINHAN</au><au>SUN JIANLING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Code annotation generation method based on dense retrieval</title><date>2023-10-31</date><risdate>2023</risdate><abstract>The invention discloses a code annotation generation method based on dense retrieval and relation modeling, which uses dense retrieval to retrieve related annotations as additional inputs, and extracts the relation between codes and the additional annotation inputs, thereby improving the annotation generation quality. According to the method, a retriever is mainly used for retrieving related annotations of input codes in a retrieval set, the codes and the retrieved annotations are spliced and then input into a discriminator, a fusion representation vector, a relation representation vector and relation classification are obtained, the fusion representation vector and the relation representation vector are input into a second multi-layer decoder, and code annotations are generated. According to the method, the relation between the additional input and the original input is considered for the first time, the generator can be effectively prevented from being misled, and then the generation effect is improved.
本发明</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN116974625A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Code annotation generation method based on dense retrieval |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T07%3A32%3A06IST&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=FU%20HAN&rft.date=2023-10-31&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116974625A%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 |