ARTIFICIAL INTELLIGENCE EXPLAINING FOR NATURAL LANGUAGE PROCESSING

ARTIFICIAL INTELLIGENCE EXPLAINING FOR NATURAL LANGUAGE PROCESSING

In an approach to AI explaining for natural language processing, responsive to receiving an input text for a machine learning model, an output is generated from the machine learning model. A plurality of alteration techniques are applied to the input text to generate one or more alternate outputs, w...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: TERUI, FUMIHIKO, Yanagawa, Takumi, MATSUOKA, KENSUKE, FURUKAWA, SAYAKA
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
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 TERUI, FUMIHIKO
Yanagawa, Takumi
MATSUOKA, KENSUKE
FURUKAWA, SAYAKA
description In an approach to AI explaining for natural language processing, responsive to receiving an input text for a machine learning model, an output is generated from the machine learning model. A plurality of alteration techniques are applied to the input text to generate one or more alternate outputs, where each alternate output corresponds to an alteration technique. A variation rate of the alternate output is calculated for each alteration technique. A preferred technique of generating neighboring data of the input text is generated based on a comparison of the variation rate of the alternate output for each alteration technique.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2022067558A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2022067558A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2022067558A13</originalsourceid><addsrcrecordid>eNrjZHByDArxdPN09nT0UfD0C3H18fF0d_VzdlVwjQjwcfT08_RzV3DzD1LwcwwJDQKq8XH0cw91dHdVCAjyd3YNDgbK8zCwpiXmFKfyQmluBmU31xBnD93Ugvz41OKCxOTUvNSS-NBgIwMjIwMzc1NTC0dDY-JUAQDGJyxg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>ARTIFICIAL INTELLIGENCE EXPLAINING FOR NATURAL LANGUAGE PROCESSING</title><source>esp@cenet</source><creator>TERUI, FUMIHIKO ; Yanagawa, Takumi ; MATSUOKA, KENSUKE ; FURUKAWA, SAYAKA</creator><creatorcontrib>TERUI, FUMIHIKO ; Yanagawa, Takumi ; MATSUOKA, KENSUKE ; FURUKAWA, SAYAKA</creatorcontrib><description>In an approach to AI explaining for natural language processing, responsive to receiving an input text for a machine learning model, an output is generated from the machine learning model. A plurality of alteration techniques are applied to the input text to generate one or more alternate outputs, where each alternate output corresponds to an alteration technique. A variation rate of the alternate output is calculated for each alteration technique. A preferred technique of generating neighboring data of the input text is generated based on a comparison of the variation rate of the alternate output for each alteration technique.</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&amp;date=20220303&amp;DB=EPODOC&amp;CC=US&amp;NR=2022067558A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76294</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220303&amp;DB=EPODOC&amp;CC=US&amp;NR=2022067558A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>TERUI, FUMIHIKO</creatorcontrib><creatorcontrib>Yanagawa, Takumi</creatorcontrib><creatorcontrib>MATSUOKA, KENSUKE</creatorcontrib><creatorcontrib>FURUKAWA, SAYAKA</creatorcontrib><title>ARTIFICIAL INTELLIGENCE EXPLAINING FOR NATURAL LANGUAGE PROCESSING</title><description>In an approach to AI explaining for natural language processing, responsive to receiving an input text for a machine learning model, an output is generated from the machine learning model. A plurality of alteration techniques are applied to the input text to generate one or more alternate outputs, where each alternate output corresponds to an alteration technique. A variation rate of the alternate output is calculated for each alteration technique. A preferred technique of generating neighboring data of the input text is generated based on a comparison of the variation rate of the alternate output for each alteration technique.</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>eNrjZHByDArxdPN09nT0UfD0C3H18fF0d_VzdlVwjQjwcfT08_RzV3DzD1LwcwwJDQKq8XH0cw91dHdVCAjyd3YNDgbK8zCwpiXmFKfyQmluBmU31xBnD93Ugvz41OKCxOTUvNSS-NBgIwMjIwMzc1NTC0dDY-JUAQDGJyxg</recordid><startdate>20220303</startdate><enddate>20220303</enddate><creator>TERUI, FUMIHIKO</creator><creator>Yanagawa, Takumi</creator><creator>MATSUOKA, KENSUKE</creator><creator>FURUKAWA, SAYAKA</creator><scope>EVB</scope></search><sort><creationdate>20220303</creationdate><title>ARTIFICIAL INTELLIGENCE EXPLAINING FOR NATURAL LANGUAGE PROCESSING</title><author>TERUI, FUMIHIKO ; Yanagawa, Takumi ; MATSUOKA, KENSUKE ; FURUKAWA, SAYAKA</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2022067558A13</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>TERUI, FUMIHIKO</creatorcontrib><creatorcontrib>Yanagawa, Takumi</creatorcontrib><creatorcontrib>MATSUOKA, KENSUKE</creatorcontrib><creatorcontrib>FURUKAWA, SAYAKA</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>TERUI, FUMIHIKO</au><au>Yanagawa, Takumi</au><au>MATSUOKA, KENSUKE</au><au>FURUKAWA, SAYAKA</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>ARTIFICIAL INTELLIGENCE EXPLAINING FOR NATURAL LANGUAGE PROCESSING</title><date>2022-03-03</date><risdate>2022</risdate><abstract>In an approach to AI explaining for natural language processing, responsive to receiving an input text for a machine learning model, an output is generated from the machine learning model. A plurality of alteration techniques are applied to the input text to generate one or more alternate outputs, where each alternate output corresponds to an alteration technique. A variation rate of the alternate output is calculated for each alteration technique. A preferred technique of generating neighboring data of the input text is generated based on a comparison of the variation rate of the alternate output for each alteration technique.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2022067558A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title ARTIFICIAL INTELLIGENCE EXPLAINING FOR NATURAL LANGUAGE PROCESSING
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T07%3A50%3A00IST&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=TERUI,%20FUMIHIKO&rft.date=2022-03-03&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2022067558A1%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