THEME DETECTION WITHIN A CORPUS OF INFORMATION
Systems and methods are used to detect underlying themes from a collection of documents at an aggregated level. A representative set of documents may be selected from a cluster of documents, with the representative set of documents corresponding to a general theme of the cluster. Candidate theme phr...
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 | Shapira, Sharon Chidambaram, Senthil C Kapoor, Ankit Nadig, Deepak Seetharam Gangadharaiah, Rashmi Bhattacharjee, Kasturi Ng, Tony Chun Tung |
| description | Systems and methods are used to detect underlying themes from a collection of documents at an aggregated level. A representative set of documents may be selected from a cluster of documents, with the representative set of documents corresponding to a general theme of the cluster. Candidate theme phrases may then be extracted from the documents and used to generate document embeddings and candidate phrase embeddings, which may be ranked, such as with a diversity-based ranking approach. Certain candidates may be selected from the ranking. Each of the documents forming the representative set may then be concatenated and a query embedding may be generated and ranked against the candidate phrases. In this manner, a collection of phrases associated with both the general underlying theme of the cluster, along with granular topics associated with that theme, may be identified. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024160651A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024160651A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024160651A13</originalsourceid><addsrcrecordid>eNrjZNAL8XD1dVVwcQ1xdQ7x9PdTCPcM8fD0U3BUcPYPCggNVvB3U_D0c_MP8nUESfMwsKYl5hSn8kJpbgZlN9cQZw_d1IL8-NTigsTk1LzUkvjQYCMDIxNDMwMzU0NHQ2PiVAEAdAcmnA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>THEME DETECTION WITHIN A CORPUS OF INFORMATION</title><source>esp@cenet</source><creator>Shapira, Sharon ; Chidambaram, Senthil C ; Kapoor, Ankit ; Nadig, Deepak Seetharam ; Gangadharaiah, Rashmi ; Bhattacharjee, Kasturi ; Ng, Tony Chun Tung</creator><creatorcontrib>Shapira, Sharon ; Chidambaram, Senthil C ; Kapoor, Ankit ; Nadig, Deepak Seetharam ; Gangadharaiah, Rashmi ; Bhattacharjee, Kasturi ; Ng, Tony Chun Tung</creatorcontrib><description>Systems and methods are used to detect underlying themes from a collection of documents at an aggregated level. A representative set of documents may be selected from a cluster of documents, with the representative set of documents corresponding to a general theme of the cluster. Candidate theme phrases may then be extracted from the documents and used to generate document embeddings and candidate phrase embeddings, which may be ranked, such as with a diversity-based ranking approach. Certain candidates may be selected from the ranking. Each of the documents forming the representative set may then be concatenated and a query embedding may be generated and ranked against the candidate phrases. In this manner, a collection of phrases associated with both the general underlying theme of the cluster, along with granular topics associated with that theme, may be identified.</description><language>eng</language><subject>CALCULATING ; 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=20240516&DB=EPODOC&CC=US&NR=2024160651A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240516&DB=EPODOC&CC=US&NR=2024160651A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Shapira, Sharon</creatorcontrib><creatorcontrib>Chidambaram, Senthil C</creatorcontrib><creatorcontrib>Kapoor, Ankit</creatorcontrib><creatorcontrib>Nadig, Deepak Seetharam</creatorcontrib><creatorcontrib>Gangadharaiah, Rashmi</creatorcontrib><creatorcontrib>Bhattacharjee, Kasturi</creatorcontrib><creatorcontrib>Ng, Tony Chun Tung</creatorcontrib><title>THEME DETECTION WITHIN A CORPUS OF INFORMATION</title><description>Systems and methods are used to detect underlying themes from a collection of documents at an aggregated level. A representative set of documents may be selected from a cluster of documents, with the representative set of documents corresponding to a general theme of the cluster. Candidate theme phrases may then be extracted from the documents and used to generate document embeddings and candidate phrase embeddings, which may be ranked, such as with a diversity-based ranking approach. Certain candidates may be selected from the ranking. Each of the documents forming the representative set may then be concatenated and a query embedding may be generated and ranked against the candidate phrases. In this manner, a collection of phrases associated with both the general underlying theme of the cluster, along with granular topics associated with that theme, may be identified.</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNAL8XD1dVVwcQ1xdQ7x9PdTCPcM8fD0U3BUcPYPCggNVvB3U_D0c_MP8nUESfMwsKYl5hSn8kJpbgZlN9cQZw_d1IL8-NTigsTk1LzUkvjQYCMDIxNDMwMzU0NHQ2PiVAEAdAcmnA</recordid><startdate>20240516</startdate><enddate>20240516</enddate><creator>Shapira, Sharon</creator><creator>Chidambaram, Senthil C</creator><creator>Kapoor, Ankit</creator><creator>Nadig, Deepak Seetharam</creator><creator>Gangadharaiah, Rashmi</creator><creator>Bhattacharjee, Kasturi</creator><creator>Ng, Tony Chun Tung</creator><scope>EVB</scope></search><sort><creationdate>20240516</creationdate><title>THEME DETECTION WITHIN A CORPUS OF INFORMATION</title><author>Shapira, Sharon ; Chidambaram, Senthil C ; Kapoor, Ankit ; Nadig, Deepak Seetharam ; Gangadharaiah, Rashmi ; Bhattacharjee, Kasturi ; Ng, Tony Chun Tung</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024160651A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Shapira, Sharon</creatorcontrib><creatorcontrib>Chidambaram, Senthil C</creatorcontrib><creatorcontrib>Kapoor, Ankit</creatorcontrib><creatorcontrib>Nadig, Deepak Seetharam</creatorcontrib><creatorcontrib>Gangadharaiah, Rashmi</creatorcontrib><creatorcontrib>Bhattacharjee, Kasturi</creatorcontrib><creatorcontrib>Ng, Tony Chun Tung</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Shapira, Sharon</au><au>Chidambaram, Senthil C</au><au>Kapoor, Ankit</au><au>Nadig, Deepak Seetharam</au><au>Gangadharaiah, Rashmi</au><au>Bhattacharjee, Kasturi</au><au>Ng, Tony Chun Tung</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>THEME DETECTION WITHIN A CORPUS OF INFORMATION</title><date>2024-05-16</date><risdate>2024</risdate><abstract>Systems and methods are used to detect underlying themes from a collection of documents at an aggregated level. A representative set of documents may be selected from a cluster of documents, with the representative set of documents corresponding to a general theme of the cluster. Candidate theme phrases may then be extracted from the documents and used to generate document embeddings and candidate phrase embeddings, which may be ranked, such as with a diversity-based ranking approach. Certain candidates may be selected from the ranking. Each of the documents forming the representative set may then be concatenated and a query embedding may be generated and ranked against the candidate phrases. In this manner, a collection of phrases associated with both the general underlying theme of the cluster, along with granular topics associated with that theme, may be identified.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2024160651A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | THEME DETECTION WITHIN A CORPUS OF INFORMATION |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-25T16%3A54%3A33IST&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=Shapira,%20Sharon&rft.date=2024-05-16&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024160651A1%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 |