Systems and methods for analysis explainability

Systems and methods for analysis explainability

Methods and systems for providing mechanisms for presenting artificial intelligence (AI) explainability metrics associated with model-based results are provided. In embodiments, a model is applied to a source document to generate a summary. An attention score is determined for each token of a plural...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HRISTOZOVA, Nina Stamenova, MULDER, Andrew Timothy, SKYLAKI, Stavroula, NORKUTE, Milda, HERGER, Nadja, GIOFRÉ, Daniele, MICHALAK, Leszek
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
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 HRISTOZOVA, Nina Stamenova
MULDER, Andrew Timothy
SKYLAKI, Stavroula
NORKUTE, Milda
HERGER, Nadja
GIOFRÉ, Daniele
MICHALAK, Leszek
description Methods and systems for providing mechanisms for presenting artificial intelligence (AI) explainability metrics associated with model-based results are provided. In embodiments, a model is applied to a source document to generate a summary. An attention score is determined for each token of a plurality of tokens of the source document. The attention score for a token indicates a level of relevance of the token to the model-based summary. The tokens are aligned to at least one word of a plurality of words included in the source document, and the attention scores of the tokens aligned to the each word are combined to generate an overall attention score for each word of the source document. At least one word of the source document is displayed with an indication of the overall attention score associated with the at least one word.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_AU2021346958A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>AU2021346958A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_AU2021346958A13</originalsourceid><addsrcrecordid>eNrjZNAPriwuSc0tVkjMS1HITS3JyE8pVkjLLwLyE3MqizOLFVIrCnISM_MSkzJzMksqeRhY0xJzilN5oTQ3g7Kba4izh25qQX58anFBYnJqXmpJvGOokYGRobGJmaWphaOhMXGqAAWGLD8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Systems and methods for analysis explainability</title><source>esp@cenet</source><creator>HRISTOZOVA, Nina Stamenova ; MULDER, Andrew Timothy ; SKYLAKI, Stavroula ; NORKUTE, Milda ; HERGER, Nadja ; GIOFRÉ, Daniele ; MICHALAK, Leszek</creator><creatorcontrib>HRISTOZOVA, Nina Stamenova ; MULDER, Andrew Timothy ; SKYLAKI, Stavroula ; NORKUTE, Milda ; HERGER, Nadja ; GIOFRÉ, Daniele ; MICHALAK, Leszek</creatorcontrib><description>Methods and systems for providing mechanisms for presenting artificial intelligence (AI) explainability metrics associated with model-based results are provided. In embodiments, a model is applied to a source document to generate a summary. An attention score is determined for each token of a plurality of tokens of the source document. The attention score for a token indicates a level of relevance of the token to the model-based summary. The tokens are aligned to at least one word of a plurality of words included in the source document, and the attention scores of the tokens aligned to the each word are combined to generate an overall attention score for each word of the source document. At least one word of the source document is displayed with an indication of the overall attention score associated with the at least one word.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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&amp;date=20230316&amp;DB=EPODOC&amp;CC=AU&amp;NR=2021346958A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230316&amp;DB=EPODOC&amp;CC=AU&amp;NR=2021346958A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HRISTOZOVA, Nina Stamenova</creatorcontrib><creatorcontrib>MULDER, Andrew Timothy</creatorcontrib><creatorcontrib>SKYLAKI, Stavroula</creatorcontrib><creatorcontrib>NORKUTE, Milda</creatorcontrib><creatorcontrib>HERGER, Nadja</creatorcontrib><creatorcontrib>GIOFRÉ, Daniele</creatorcontrib><creatorcontrib>MICHALAK, Leszek</creatorcontrib><title>Systems and methods for analysis explainability</title><description>Methods and systems for providing mechanisms for presenting artificial intelligence (AI) explainability metrics associated with model-based results are provided. In embodiments, a model is applied to a source document to generate a summary. An attention score is determined for each token of a plurality of tokens of the source document. The attention score for a token indicates a level of relevance of the token to the model-based summary. The tokens are aligned to at least one word of a plurality of words included in the source document, and the attention scores of the tokens aligned to the each word are combined to generate an overall attention score for each word of the source document. At least one word of the source document is displayed with an indication of the overall attention score associated with the at least one word.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNAPriwuSc0tVkjMS1HITS3JyE8pVkjLLwLyE3MqizOLFVIrCnISM_MSkzJzMksqeRhY0xJzilN5oTQ3g7Kba4izh25qQX58anFBYnJqXmpJvGOokYGRobGJmaWphaOhMXGqAAWGLD8</recordid><startdate>20230316</startdate><enddate>20230316</enddate><creator>HRISTOZOVA, Nina Stamenova</creator><creator>MULDER, Andrew Timothy</creator><creator>SKYLAKI, Stavroula</creator><creator>NORKUTE, Milda</creator><creator>HERGER, Nadja</creator><creator>GIOFRÉ, Daniele</creator><creator>MICHALAK, Leszek</creator><scope>EVB</scope></search><sort><creationdate>20230316</creationdate><title>Systems and methods for analysis explainability</title><author>HRISTOZOVA, Nina Stamenova ; MULDER, Andrew Timothy ; SKYLAKI, Stavroula ; NORKUTE, Milda ; HERGER, Nadja ; GIOFRÉ, Daniele ; MICHALAK, Leszek</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_AU2021346958A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>HRISTOZOVA, Nina Stamenova</creatorcontrib><creatorcontrib>MULDER, Andrew Timothy</creatorcontrib><creatorcontrib>SKYLAKI, Stavroula</creatorcontrib><creatorcontrib>NORKUTE, Milda</creatorcontrib><creatorcontrib>HERGER, Nadja</creatorcontrib><creatorcontrib>GIOFRÉ, Daniele</creatorcontrib><creatorcontrib>MICHALAK, Leszek</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HRISTOZOVA, Nina Stamenova</au><au>MULDER, Andrew Timothy</au><au>SKYLAKI, Stavroula</au><au>NORKUTE, Milda</au><au>HERGER, Nadja</au><au>GIOFRÉ, Daniele</au><au>MICHALAK, Leszek</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Systems and methods for analysis explainability</title><date>2023-03-16</date><risdate>2023</risdate><abstract>Methods and systems for providing mechanisms for presenting artificial intelligence (AI) explainability metrics associated with model-based results are provided. In embodiments, a model is applied to a source document to generate a summary. An attention score is determined for each token of a plurality of tokens of the source document. The attention score for a token indicates a level of relevance of the token to the model-based summary. The tokens are aligned to at least one word of a plurality of words included in the source document, and the attention scores of the tokens aligned to the each word are combined to generate an overall attention score for each word of the source document. At least one word of the source document is displayed with an indication of the overall attention score associated with the at least one word.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_AU2021346958A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Systems and methods for analysis explainability
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T18%3A49%3A09IST&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=HRISTOZOVA,%20Nina%20Stamenova&rft.date=2023-03-16&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EAU2021346958A1%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