SYSTEM AND METHOD FOR CONTENT COMPREHENSION AND RESPONSE
A method, apparatus and system for training an embedding space for content comprehension and response includes, for each layer of a hierarchical taxonomy having at least two layers including respective words resulting in layers of varying complexity, determining a set of words associated with a laye...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | 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 | DIVAKARAN, Ajay YAO, Yi SIKKA, Karan NUNN, Stephanie RUTHERFORD-QUACH, Sara HOSTETLER, Jesse SAHU, Pritish COGSWELL, Michael A GONG, Yunye |
| description | A method, apparatus and system for training an embedding space for content comprehension and response includes, for each layer of a hierarchical taxonomy having at least two layers including respective words resulting in layers of varying complexity, determining a set of words associated with a layer of the hierarchical taxonomy, determining a question answer pair based on a question generated using at least one word of the set of words and at least one content domain, determining a vector representation for the generated question and for content related to the at least one content domain of the question answer pair, and embedding the question vector representation and the content vector representations into a common embedding space where vector representations that are related, are closer in the embedding space than unrelated embedded vector representations. Requests for content can then be fulfilled using the trained, common embedding space. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2022138433A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2022138433A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2022138433A13</originalsourceid><addsrcrecordid>eNrjZLAIjgwOcfVVcPRzUfB1DfHwd1Fw8w9ScPb3C3H1CwHSvgFBrh6ufsGe_n5gRUGuwQH-fsGuPAysaYk5xam8UJqbQdnNNcTZQze1ID8-tbggMTk1L7UkPjTYyMDIyNDYwsTY2NHQmDhVABM4KYI</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>SYSTEM AND METHOD FOR CONTENT COMPREHENSION AND RESPONSE</title><source>esp@cenet</source><creator>DIVAKARAN, Ajay ; YAO, Yi ; SIKKA, Karan ; NUNN, Stephanie ; RUTHERFORD-QUACH, Sara ; HOSTETLER, Jesse ; SAHU, Pritish ; COGSWELL, Michael A ; GONG, Yunye</creator><creatorcontrib>DIVAKARAN, Ajay ; YAO, Yi ; SIKKA, Karan ; NUNN, Stephanie ; RUTHERFORD-QUACH, Sara ; HOSTETLER, Jesse ; SAHU, Pritish ; COGSWELL, Michael A ; GONG, Yunye</creatorcontrib><description>A method, apparatus and system for training an embedding space for content comprehension and response includes, for each layer of a hierarchical taxonomy having at least two layers including respective words resulting in layers of varying complexity, determining a set of words associated with a layer of the hierarchical taxonomy, determining a question answer pair based on a question generated using at least one word of the set of words and at least one content domain, determining a vector representation for the generated question and for content related to the at least one content domain of the question answer pair, and embedding the question vector representation and the content vector representations into a common embedding space where vector representations that are related, are closer in the embedding space than unrelated embedded vector representations. Requests for content can then be fulfilled using the trained, common embedding space.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; 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=20220505&DB=EPODOC&CC=US&NR=2022138433A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25562,76317</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220505&DB=EPODOC&CC=US&NR=2022138433A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>DIVAKARAN, Ajay</creatorcontrib><creatorcontrib>YAO, Yi</creatorcontrib><creatorcontrib>SIKKA, Karan</creatorcontrib><creatorcontrib>NUNN, Stephanie</creatorcontrib><creatorcontrib>RUTHERFORD-QUACH, Sara</creatorcontrib><creatorcontrib>HOSTETLER, Jesse</creatorcontrib><creatorcontrib>SAHU, Pritish</creatorcontrib><creatorcontrib>COGSWELL, Michael A</creatorcontrib><creatorcontrib>GONG, Yunye</creatorcontrib><title>SYSTEM AND METHOD FOR CONTENT COMPREHENSION AND RESPONSE</title><description>A method, apparatus and system for training an embedding space for content comprehension and response includes, for each layer of a hierarchical taxonomy having at least two layers including respective words resulting in layers of varying complexity, determining a set of words associated with a layer of the hierarchical taxonomy, determining a question answer pair based on a question generated using at least one word of the set of words and at least one content domain, determining a vector representation for the generated question and for content related to the at least one content domain of the question answer pair, and embedding the question vector representation and the content vector representations into a common embedding space where vector representations that are related, are closer in the embedding space than unrelated embedded vector representations. Requests for content can then be fulfilled using the trained, common embedding space.</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLAIjgwOcfVVcPRzUfB1DfHwd1Fw8w9ScPb3C3H1CwHSvgFBrh6ufsGe_n5gRUGuwQH-fsGuPAysaYk5xam8UJqbQdnNNcTZQze1ID8-tbggMTk1L7UkPjTYyMDIyNDYwsTY2NHQmDhVABM4KYI</recordid><startdate>20220505</startdate><enddate>20220505</enddate><creator>DIVAKARAN, Ajay</creator><creator>YAO, Yi</creator><creator>SIKKA, Karan</creator><creator>NUNN, Stephanie</creator><creator>RUTHERFORD-QUACH, Sara</creator><creator>HOSTETLER, Jesse</creator><creator>SAHU, Pritish</creator><creator>COGSWELL, Michael A</creator><creator>GONG, Yunye</creator><scope>EVB</scope></search><sort><creationdate>20220505</creationdate><title>SYSTEM AND METHOD FOR CONTENT COMPREHENSION AND RESPONSE</title><author>DIVAKARAN, Ajay ; YAO, Yi ; SIKKA, Karan ; NUNN, Stephanie ; RUTHERFORD-QUACH, Sara ; HOSTETLER, Jesse ; SAHU, Pritish ; COGSWELL, Michael A ; GONG, Yunye</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2022138433A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2022</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>DIVAKARAN, Ajay</creatorcontrib><creatorcontrib>YAO, Yi</creatorcontrib><creatorcontrib>SIKKA, Karan</creatorcontrib><creatorcontrib>NUNN, Stephanie</creatorcontrib><creatorcontrib>RUTHERFORD-QUACH, Sara</creatorcontrib><creatorcontrib>HOSTETLER, Jesse</creatorcontrib><creatorcontrib>SAHU, Pritish</creatorcontrib><creatorcontrib>COGSWELL, Michael A</creatorcontrib><creatorcontrib>GONG, Yunye</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>DIVAKARAN, Ajay</au><au>YAO, Yi</au><au>SIKKA, Karan</au><au>NUNN, Stephanie</au><au>RUTHERFORD-QUACH, Sara</au><au>HOSTETLER, Jesse</au><au>SAHU, Pritish</au><au>COGSWELL, Michael A</au><au>GONG, Yunye</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>SYSTEM AND METHOD FOR CONTENT COMPREHENSION AND RESPONSE</title><date>2022-05-05</date><risdate>2022</risdate><abstract>A method, apparatus and system for training an embedding space for content comprehension and response includes, for each layer of a hierarchical taxonomy having at least two layers including respective words resulting in layers of varying complexity, determining a set of words associated with a layer of the hierarchical taxonomy, determining a question answer pair based on a question generated using at least one word of the set of words and at least one content domain, determining a vector representation for the generated question and for content related to the at least one content domain of the question answer pair, and embedding the question vector representation and the content vector representations into a common embedding space where vector representations that are related, are closer in the embedding space than unrelated embedded vector representations. Requests for content can then be fulfilled using the trained, common embedding space.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2022138433A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | SYSTEM AND METHOD FOR CONTENT COMPREHENSION AND RESPONSE |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T12%3A19%3A58IST&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=DIVAKARAN,%20Ajay&rft.date=2022-05-05&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2022138433A1%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 |