ARTIFICIAL INTELLIGENCE EXPLAINABILITY FOR INTENT CLASSIFICATION

ARTIFICIAL INTELLIGENCE EXPLAINABILITY FOR INTENT CLASSIFICATION

Systems and methods for providing an explainability framework for use with AI systems are described. In one example, such an AI explainability system for intent classification uses a surrogate Bert-Siamese model approach. For example, a prediction from an intent classification model is paired with a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Upadhyayula, Raghavender Surya, De, Tanusree, Mukherjee, Debapriya, Kotala, Raghavendra
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 Upadhyayula, Raghavender Surya
De, Tanusree
Mukherjee, Debapriya
Kotala, Raghavendra
description Systems and methods for providing an explainability framework for use with AI systems are described. In one example, such an AI explainability system for intent classification uses a surrogate Bert-Siamese model approach. For example, a prediction from an intent classification model is paired with a top matching sentence and used as input to train a Bert-Siamese model for sentence similarity. Using the sentence similarity, the token/word level embedding can be extracted from attention weights of the sentences and correlations between query tokens/words, and the best matching sentences may be used for explanations.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024232664A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024232664A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024232664A13</originalsourceid><addsrcrecordid>eNrjZHBwDArxdPN09nT0UfD0C3H18fF0d_VzdlVwjQjwcfT0c3Ty9PEMiVRw8w8Cy_uFKDj7OAYHg_Q4hnj6-_EwsKYl5hSn8kJpbgZlN9cQZw_d1IL8-NTigsTk1LzUkvjQYCMDIxMjYyMzMxNHQ2PiVAEAfGsr6A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>ARTIFICIAL INTELLIGENCE EXPLAINABILITY FOR INTENT CLASSIFICATION</title><source>esp@cenet</source><creator>Upadhyayula, Raghavender Surya ; De, Tanusree ; Mukherjee, Debapriya ; Kotala, Raghavendra</creator><creatorcontrib>Upadhyayula, Raghavender Surya ; De, Tanusree ; Mukherjee, Debapriya ; Kotala, Raghavendra</creatorcontrib><description>Systems and methods for providing an explainability framework for use with AI systems are described. In one example, such an AI explainability system for intent classification uses a surrogate Bert-Siamese model approach. For example, a prediction from an intent classification model is paired with a top matching sentence and used as input to train a Bert-Siamese model for sentence similarity. Using the sentence similarity, the token/word level embedding can be extracted from attention weights of the sentences and correlations between query tokens/words, and the best matching sentences may be used for explanations.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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&amp;date=20240711&amp;DB=EPODOC&amp;CC=US&amp;NR=2024232664A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240711&amp;DB=EPODOC&amp;CC=US&amp;NR=2024232664A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Upadhyayula, Raghavender Surya</creatorcontrib><creatorcontrib>De, Tanusree</creatorcontrib><creatorcontrib>Mukherjee, Debapriya</creatorcontrib><creatorcontrib>Kotala, Raghavendra</creatorcontrib><title>ARTIFICIAL INTELLIGENCE EXPLAINABILITY FOR INTENT CLASSIFICATION</title><description>Systems and methods for providing an explainability framework for use with AI systems are described. In one example, such an AI explainability system for intent classification uses a surrogate Bert-Siamese model approach. For example, a prediction from an intent classification model is paired with a top matching sentence and used as input to train a Bert-Siamese model for sentence similarity. Using the sentence similarity, the token/word level embedding can be extracted from attention weights of the sentences and correlations between query tokens/words, and the best matching sentences may be used for explanations.</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHBwDArxdPN09nT0UfD0C3H18fF0d_VzdlVwjQjwcfT0c3Ty9PEMiVRw8w8Cy_uFKDj7OAYHg_Q4hnj6-_EwsKYl5hSn8kJpbgZlN9cQZw_d1IL8-NTigsTk1LzUkvjQYCMDIxMjYyMzMxNHQ2PiVAEAfGsr6A</recordid><startdate>20240711</startdate><enddate>20240711</enddate><creator>Upadhyayula, Raghavender Surya</creator><creator>De, Tanusree</creator><creator>Mukherjee, Debapriya</creator><creator>Kotala, Raghavendra</creator><scope>EVB</scope></search><sort><creationdate>20240711</creationdate><title>ARTIFICIAL INTELLIGENCE EXPLAINABILITY FOR INTENT CLASSIFICATION</title><author>Upadhyayula, Raghavender Surya ; De, Tanusree ; Mukherjee, Debapriya ; Kotala, Raghavendra</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024232664A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</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>Upadhyayula, Raghavender Surya</creatorcontrib><creatorcontrib>De, Tanusree</creatorcontrib><creatorcontrib>Mukherjee, Debapriya</creatorcontrib><creatorcontrib>Kotala, Raghavendra</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Upadhyayula, Raghavender Surya</au><au>De, Tanusree</au><au>Mukherjee, Debapriya</au><au>Kotala, Raghavendra</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>ARTIFICIAL INTELLIGENCE EXPLAINABILITY FOR INTENT CLASSIFICATION</title><date>2024-07-11</date><risdate>2024</risdate><abstract>Systems and methods for providing an explainability framework for use with AI systems are described. In one example, such an AI explainability system for intent classification uses a surrogate Bert-Siamese model approach. For example, a prediction from an intent classification model is paired with a top matching sentence and used as input to train a Bert-Siamese model for sentence similarity. Using the sentence similarity, the token/word level embedding can be extracted from attention weights of the sentences and correlations between query tokens/words, and the best matching sentences may be used for explanations.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2024232664A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title ARTIFICIAL INTELLIGENCE EXPLAINABILITY FOR INTENT CLASSIFICATION
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T05%3A48%3A15IST&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=Upadhyayula,%20Raghavender%20Surya&rft.date=2024-07-11&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024232664A1%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