SYSTEMS AND METHODS FOR SEMANTIC CODE SEARCH

Embodiments described herein provides a contrastive learning framework that leverages hard negative examples, that are mined globally from the entire training corpus for a given query to improve the quality of code and natural language representations. Specifically, similar examples from the trainin...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Joty, Shafiq Rayhan, Gotmare, Akhilesh Deepak, Li, Junnan, Hoi, Chu Hong
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS
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	Joty, Shafiq Rayhan Gotmare, Akhilesh Deepak Li, Junnan Hoi, Chu Hong
description	Embodiments described herein provides a contrastive learning framework that leverages hard negative examples, that are mined globally from the entire training corpus for a given query to improve the quality of code and natural language representations. Specifically, similar examples from the training corpus are extracted and used as hard negatives in an online manner during training while keeping the minibatch construction random.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2022374595A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2022374595A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2022374595A13</originalsourceid><addsrcrecordid>eNrjZNAJjgwOcfUNVnD0c1HwdQ3x8HcJVnDzD1IIdvV19AvxdFZw9ndxBfIcg5w9eBhY0xJzilN5oTQ3g7Kba4izh25qQX58anFBYnJqXmpJfGiwkYGRkbG5iamlqaOhMXGqAB_hJgA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>SYSTEMS AND METHODS FOR SEMANTIC CODE SEARCH</title><source>esp@cenet</source><creator>Joty, Shafiq Rayhan ; Gotmare, Akhilesh Deepak ; Li, Junnan ; Hoi, Chu Hong</creator><creatorcontrib>Joty, Shafiq Rayhan ; Gotmare, Akhilesh Deepak ; Li, Junnan ; Hoi, Chu Hong</creatorcontrib><description>Embodiments described herein provides a contrastive learning framework that leverages hard negative examples, that are mined globally from the entire training corpus for a given query to improve the quality of code and natural language representations. Specifically, similar examples from the training corpus are extracted and used as hard negatives in an online manner during training while keeping the minibatch construction random.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</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=20221124&DB=EPODOC&CC=US&NR=2022374595A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76318</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221124&DB=EPODOC&CC=US&NR=2022374595A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Joty, Shafiq Rayhan</creatorcontrib><creatorcontrib>Gotmare, Akhilesh Deepak</creatorcontrib><creatorcontrib>Li, Junnan</creatorcontrib><creatorcontrib>Hoi, Chu Hong</creatorcontrib><title>SYSTEMS AND METHODS FOR SEMANTIC CODE SEARCH</title><description>Embodiments described herein provides a contrastive learning framework that leverages hard negative examples, that are mined globally from the entire training corpus for a given query to improve the quality of code and natural language representations. Specifically, similar examples from the training corpus are extracted and used as hard negatives in an online manner during training while keeping the minibatch construction random.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNAJjgwOcfUNVnD0c1HwdQ3x8HcJVnDzD1IIdvV19AvxdFZw9ndxBfIcg5w9eBhY0xJzilN5oTQ3g7Kba4izh25qQX58anFBYnJqXmpJfGiwkYGRkbG5iamlqaOhMXGqAB_hJgA</recordid><startdate>20221124</startdate><enddate>20221124</enddate><creator>Joty, Shafiq Rayhan</creator><creator>Gotmare, Akhilesh Deepak</creator><creator>Li, Junnan</creator><creator>Hoi, Chu Hong</creator><scope>EVB</scope></search><sort><creationdate>20221124</creationdate><title>SYSTEMS AND METHODS FOR SEMANTIC CODE SEARCH</title><author>Joty, Shafiq Rayhan ; Gotmare, Akhilesh Deepak ; Li, Junnan ; Hoi, Chu Hong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2022374595A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Joty, Shafiq Rayhan</creatorcontrib><creatorcontrib>Gotmare, Akhilesh Deepak</creatorcontrib><creatorcontrib>Li, Junnan</creatorcontrib><creatorcontrib>Hoi, Chu Hong</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Joty, Shafiq Rayhan</au><au>Gotmare, Akhilesh Deepak</au><au>Li, Junnan</au><au>Hoi, Chu Hong</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>SYSTEMS AND METHODS FOR SEMANTIC CODE SEARCH</title><date>2022-11-24</date><risdate>2022</risdate><abstract>Embodiments described herein provides a contrastive learning framework that leverages hard negative examples, that are mined globally from the entire training corpus for a given query to improve the quality of code and natural language representations. Specifically, similar examples from the training corpus are extracted and used as hard negatives in an online manner during training while keeping the minibatch construction random.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US2022374595A1
source	esp@cenet
subjects	CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS
title	SYSTEMS AND METHODS FOR SEMANTIC CODE SEARCH
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T04%3A47%3A08IST&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=Joty,%20Shafiq%20Rayhan&rft.date=2022-11-24&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2022374595A1%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