Understanding Is a Process

How do we gauge understanding? Tests of understanding, such as Turing's imitation game, are numerous; yet, attempts to achieve a state of understanding are not satisfactory assessments. Intelligent agents designed to pass one test of understanding often fall short of others. Rather than approac...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in systems neuroscience 2022-03, Vol.16, p.800280-800280
Main Authors: Blaha, Leslie M, Abrams, Mitchell, Bibyk, Sarah A, Bonial, Claire, Hartzler, Beth M, Hsu, Christopher D, Khemlani, Sangeet, King, Jayde, St Amant, Robert, Trafton, J Gregory, Wong, Rachel
Format: Article
Language:English
Subjects:
behavioral measurement
common ground
human-machine teaming
human-robot interaction
mutual understanding
natural language processing
Neuroscience
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c417t-83c44fc02590fcafbd431b6545507c0163ecc63f13dfbd64c8c7bb31211d4d553
container_end_page 800280
container_issue
container_start_page 800280
container_title Frontiers in systems neuroscience
container_volume 16
creator Blaha, Leslie M
Abrams, Mitchell
Bibyk, Sarah A
Bonial, Claire
Hartzler, Beth M
Hsu, Christopher D
Khemlani, Sangeet
King, Jayde
St Amant, Robert
Trafton, J Gregory
Wong, Rachel
description How do we gauge understanding? Tests of understanding, such as Turing's imitation game, are numerous; yet, attempts to achieve a state of understanding are not satisfactory assessments. Intelligent agents designed to pass one test of understanding often fall short of others. Rather than approaching understanding as a system state, in this paper, we argue that understanding is a process that changes over time and experience. The only window into the process is through the lens of natural language. Usefully, failures of understanding reveal breakdowns in the process. We propose a set of natural language-based probes that can be used to map the degree of understanding a human or intelligent system has achieved through combinations of successes and failures.
doi_str_mv 10.3389/fnsys.2022.800280
format article
fullrecord <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_6cde3c534734414290de278fc48fc597</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_6cde3c534734414290de278fc48fc597</doaj_id><sourcerecordid>2652034379</sourcerecordid><originalsourceid>FETCH-LOGICAL-c417t-83c44fc02590fcafbd431b6545507c0163ecc63f13dfbd64c8c7bb31211d4d553</originalsourceid><addsrcrecordid>eNpVkctKAzEUhoMotlYfQBfSpZvWk-vMbAQpXgoFXdh1yJxk6pTpTE2mQt_e9GJpFyEh5z_fCfkIuaUw5DzNHos6rMOQAWPDFIClcEa6VCk2kJQn50fnDrkKYQ6gmJLZJelwKThNGXTJ3bS2zofW1LasZ_1x6Jv-p2_QhXBNLgpTBXez33tk-vryNXofTD7exqPnyQAFTdpBylGIAoHJDAo0RW4jO1dSSAkJAlXcISpeUG5jTQlMMclzThmlVlgpeY-Md1zbmLle-nJh_Fo3ptTbi8bPtPFtiZXTCq3jKLlIuBBUsAysY0laoIhLZklkPe1Yy1W-cBZd3XpTnUBPK3X5rWfNr84AUspFBDzsAb75WbnQ6kUZ0FWVqV2zCjp-IIOYS7IYpbso-iYE74rDGAp640dv_eiNH73zE3vuj9936PgXwv8AhJuLRw</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2652034379</pqid></control><display><type>article</type><title>Understanding Is a Process</title><source>PubMed Central</source><creator>Blaha, Leslie M ; Abrams, Mitchell ; Bibyk, Sarah A ; Bonial, Claire ; Hartzler, Beth M ; Hsu, Christopher D ; Khemlani, Sangeet ; King, Jayde ; St Amant, Robert ; Trafton, J Gregory ; Wong, Rachel</creator><creatorcontrib>Blaha, Leslie M ; Abrams, Mitchell ; Bibyk, Sarah A ; Bonial, Claire ; Hartzler, Beth M ; Hsu, Christopher D ; Khemlani, Sangeet ; King, Jayde ; St Amant, Robert ; Trafton, J Gregory ; Wong, Rachel</creatorcontrib><description>How do we gauge understanding? Tests of understanding, such as Turing's imitation game, are numerous; yet, attempts to achieve a state of understanding are not satisfactory assessments. Intelligent agents designed to pass one test of understanding often fall short of others. Rather than approaching understanding as a system state, in this paper, we argue that understanding is a process that changes over time and experience. The only window into the process is through the lens of natural language. Usefully, failures of understanding reveal breakdowns in the process. We propose a set of natural language-based probes that can be used to map the degree of understanding a human or intelligent system has achieved through combinations of successes and failures.</description><identifier>ISSN: 1662-5137</identifier><identifier>EISSN: 1662-5137</identifier><identifier>DOI: 10.3389/fnsys.2022.800280</identifier><identifier>PMID: 35431820</identifier><language>eng</language><publisher>Switzerland: Frontiers Media S.A</publisher><subject>behavioral measurement ; common ground ; human-machine teaming ; human-robot interaction ; mutual understanding ; natural language processing ; Neuroscience</subject><ispartof>Frontiers in systems neuroscience, 2022-03, Vol.16, p.800280-800280</ispartof><rights>Copyright © 2022 Blaha, Abrams, Bibyk, Bonial, Hartzler, Hsu, Khemlani, King, St. Amant, Trafton and Wong.</rights><rights>Copyright © 2022 Blaha, Abrams, Bibyk, Bonial, Hartzler, Hsu, Khemlani, King, St. Amant, Trafton and Wong. 2022 Blaha, Abrams, Bibyk, Bonial, Hartzler, Hsu, Khemlani, King, St. Amant, Trafton and Wong</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c417t-83c44fc02590fcafbd431b6545507c0163ecc63f13dfbd64c8c7bb31211d4d553</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9008134/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9008134/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,27922,27923,53789,53791</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/35431820$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Blaha, Leslie M</creatorcontrib><creatorcontrib>Abrams, Mitchell</creatorcontrib><creatorcontrib>Bibyk, Sarah A</creatorcontrib><creatorcontrib>Bonial, Claire</creatorcontrib><creatorcontrib>Hartzler, Beth M</creatorcontrib><creatorcontrib>Hsu, Christopher D</creatorcontrib><creatorcontrib>Khemlani, Sangeet</creatorcontrib><creatorcontrib>King, Jayde</creatorcontrib><creatorcontrib>St Amant, Robert</creatorcontrib><creatorcontrib>Trafton, J Gregory</creatorcontrib><creatorcontrib>Wong, Rachel</creatorcontrib><title>Understanding Is a Process</title><title>Frontiers in systems neuroscience</title><addtitle>Front Syst Neurosci</addtitle><description>How do we gauge understanding? Tests of understanding, such as Turing's imitation game, are numerous; yet, attempts to achieve a state of understanding are not satisfactory assessments. Intelligent agents designed to pass one test of understanding often fall short of others. Rather than approaching understanding as a system state, in this paper, we argue that understanding is a process that changes over time and experience. The only window into the process is through the lens of natural language. Usefully, failures of understanding reveal breakdowns in the process. We propose a set of natural language-based probes that can be used to map the degree of understanding a human or intelligent system has achieved through combinations of successes and failures.</description><subject>behavioral measurement</subject><subject>common ground</subject><subject>human-machine teaming</subject><subject>human-robot interaction</subject><subject>mutual understanding</subject><subject>natural language processing</subject><subject>Neuroscience</subject><issn>1662-5137</issn><issn>1662-5137</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNpVkctKAzEUhoMotlYfQBfSpZvWk-vMbAQpXgoFXdh1yJxk6pTpTE2mQt_e9GJpFyEh5z_fCfkIuaUw5DzNHos6rMOQAWPDFIClcEa6VCk2kJQn50fnDrkKYQ6gmJLZJelwKThNGXTJ3bS2zofW1LasZ_1x6Jv-p2_QhXBNLgpTBXez33tk-vryNXofTD7exqPnyQAFTdpBylGIAoHJDAo0RW4jO1dSSAkJAlXcISpeUG5jTQlMMclzThmlVlgpeY-Md1zbmLle-nJh_Fo3ptTbi8bPtPFtiZXTCq3jKLlIuBBUsAysY0laoIhLZklkPe1Yy1W-cBZd3XpTnUBPK3X5rWfNr84AUspFBDzsAb75WbnQ6kUZ0FWVqV2zCjp-IIOYS7IYpbso-iYE74rDGAp640dv_eiNH73zE3vuj9936PgXwv8AhJuLRw</recordid><startdate>20220331</startdate><enddate>20220331</enddate><creator>Blaha, Leslie M</creator><creator>Abrams, Mitchell</creator><creator>Bibyk, Sarah A</creator><creator>Bonial, Claire</creator><creator>Hartzler, Beth M</creator><creator>Hsu, Christopher D</creator><creator>Khemlani, Sangeet</creator><creator>King, Jayde</creator><creator>St Amant, Robert</creator><creator>Trafton, J Gregory</creator><creator>Wong, Rachel</creator><general>Frontiers Media S.A</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope></search><sort><creationdate>20220331</creationdate><title>Understanding Is a Process</title><author>Blaha, Leslie M ; Abrams, Mitchell ; Bibyk, Sarah A ; Bonial, Claire ; Hartzler, Beth M ; Hsu, Christopher D ; Khemlani, Sangeet ; King, Jayde ; St Amant, Robert ; Trafton, J Gregory ; Wong, Rachel</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c417t-83c44fc02590fcafbd431b6545507c0163ecc63f13dfbd64c8c7bb31211d4d553</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>behavioral measurement</topic><topic>common ground</topic><topic>human-machine teaming</topic><topic>human-robot interaction</topic><topic>mutual understanding</topic><topic>natural language processing</topic><topic>Neuroscience</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Blaha, Leslie M</creatorcontrib><creatorcontrib>Abrams, Mitchell</creatorcontrib><creatorcontrib>Bibyk, Sarah A</creatorcontrib><creatorcontrib>Bonial, Claire</creatorcontrib><creatorcontrib>Hartzler, Beth M</creatorcontrib><creatorcontrib>Hsu, Christopher D</creatorcontrib><creatorcontrib>Khemlani, Sangeet</creatorcontrib><creatorcontrib>King, Jayde</creatorcontrib><creatorcontrib>St Amant, Robert</creatorcontrib><creatorcontrib>Trafton, J Gregory</creatorcontrib><creatorcontrib>Wong, Rachel</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Frontiers in systems neuroscience</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Blaha, Leslie M</au><au>Abrams, Mitchell</au><au>Bibyk, Sarah A</au><au>Bonial, Claire</au><au>Hartzler, Beth M</au><au>Hsu, Christopher D</au><au>Khemlani, Sangeet</au><au>King, Jayde</au><au>St Amant, Robert</au><au>Trafton, J Gregory</au><au>Wong, Rachel</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Understanding Is a Process</atitle><jtitle>Frontiers in systems neuroscience</jtitle><addtitle>Front Syst Neurosci</addtitle><date>2022-03-31</date><risdate>2022</risdate><volume>16</volume><spage>800280</spage><epage>800280</epage><pages>800280-800280</pages><issn>1662-5137</issn><eissn>1662-5137</eissn><abstract>How do we gauge understanding? Tests of understanding, such as Turing's imitation game, are numerous; yet, attempts to achieve a state of understanding are not satisfactory assessments. Intelligent agents designed to pass one test of understanding often fall short of others. Rather than approaching understanding as a system state, in this paper, we argue that understanding is a process that changes over time and experience. The only window into the process is through the lens of natural language. Usefully, failures of understanding reveal breakdowns in the process. We propose a set of natural language-based probes that can be used to map the degree of understanding a human or intelligent system has achieved through combinations of successes and failures.</abstract><cop>Switzerland</cop><pub>Frontiers Media S.A</pub><pmid>35431820</pmid><doi>10.3389/fnsys.2022.800280</doi><tpages>1</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1662-5137
ispartof Frontiers in systems neuroscience, 2022-03, Vol.16, p.800280-800280
issn 1662-5137
1662-5137
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_6cde3c534734414290de278fc48fc597
source PubMed Central
subjects behavioral measurement
common ground
human-machine teaming
human-robot interaction
mutual understanding
natural language processing
Neuroscience
title Understanding Is a Process
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T09%3A39%3A44IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Understanding%20Is%20a%20Process&rft.jtitle=Frontiers%20in%20systems%20neuroscience&rft.au=Blaha,%20Leslie%20M&rft.date=2022-03-31&rft.volume=16&rft.spage=800280&rft.epage=800280&rft.pages=800280-800280&rft.issn=1662-5137&rft.eissn=1662-5137&rft_id=info:doi/10.3389/fnsys.2022.800280&rft_dat=%3Cproquest_doaj_%3E2652034379%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c417t-83c44fc02590fcafbd431b6545507c0163ecc63f13dfbd64c8c7bb31211d4d553%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2652034379&rft_id=info:pmid/35431820&rfr_iscdi=true