Using spoken words to guide open-ended category formation.
Identifieur interne : 000696 ( Main/Exploration ); précédent : 000695; suivant : 000697Using spoken words to guide open-ended category formation.
Auteurs : Aneesh Chauhan [Portugal] ; Luís Seabra LopesSource :
- Cognitive processing [ 1612-4790 ] ; 2011.
Descripteurs français
- KwdFr :
- MESH :
- physiologie : Apprentissage verbal, Formation de concepts, Parole.
- Humains, Intelligence artificielle, Noms, Robotique, Vocabulaire.
English descriptors
- KwdEn :
- MESH :
- physiology : Concept Formation, Speech, Verbal Learning.
- Artificial Intelligence, Humans, Names, Robotics, Vocabulary.
Abstract
Naming is a powerful cognitive tool that facilitates categorization by forming an association between words and their referents. There is evidence in child development literature that strong links exist between early word-learning and conceptual development. A growing view is also emerging that language is a cultural product created and acquired through social interactions. Inspired by these studies, this paper presents a novel learning architecture for category formation and vocabulary acquisition in robots through active interaction with humans. This architecture is open-ended and is capable of acquiring new categories and category names incrementally. The process can be compared to language grounding in children at single-word stage. The robot is embodied with visual and auditory sensors for world perception. A human instructor uses speech to teach the robot the names of the objects present in a visually shared environment. The robot uses its perceptual input to ground these spoken words and dynamically form/organize category descriptions in order to achieve better categorization. To evaluate the learning system at word-learning and category formation tasks, two experiments were conducted using a simple language game involving naming and corrective feedback actions from the human user. The obtained results are presented and discussed in detail.
DOI: 10.1007/s10339-011-0407-y
PubMed: 21614526
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PubMed, to step Corpus: 000325
- to stream PubMed, to step Curation: 000325
- to stream PubMed, to step Checkpoint: 000325
- to stream Ncbi, to step Merge: 000731
- to stream Ncbi, to step Curation: 000731
- to stream Ncbi, to step Checkpoint: 000731
- to stream Main, to step Merge: 000696
- to stream Main, to step Curation: 000696
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Using spoken words to guide open-ended category formation.</title>
<author><name sortKey="Chauhan, Aneesh" sort="Chauhan, Aneesh" uniqKey="Chauhan A" first="Aneesh" last="Chauhan">Aneesh Chauhan</name>
<affiliation wicri:level="1"><nlm:affiliation>Instituto de Engenharia Electrónica e Telemática de Aveiro (IEETA), Universidade de Aveiro, Portugal. aneesh.chauhan@ua.pt</nlm:affiliation>
<country xml:lang="fr">Portugal</country>
<wicri:regionArea>Instituto de Engenharia Electrónica e Telemática de Aveiro (IEETA), Universidade de Aveiro</wicri:regionArea>
<wicri:noRegion>Universidade de Aveiro</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Seabra Lopes, Luis" sort="Seabra Lopes, Luis" uniqKey="Seabra Lopes L" first="Luís" last="Seabra Lopes">Luís Seabra Lopes</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2011">2011</date>
<idno type="doi">10.1007/s10339-011-0407-y</idno>
<idno type="RBID">pubmed:21614526</idno>
<idno type="pmid">21614526</idno>
<idno type="wicri:Area/PubMed/Corpus">000325</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">000325</idno>
<idno type="wicri:Area/PubMed/Curation">000325</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Curation">000325</idno>
<idno type="wicri:Area/PubMed/Checkpoint">000325</idno>
<idno type="wicri:explorRef" wicri:stream="Checkpoint" wicri:step="PubMed">000325</idno>
<idno type="wicri:Area/Ncbi/Merge">000731</idno>
<idno type="wicri:Area/Ncbi/Curation">000731</idno>
<idno type="wicri:Area/Ncbi/Checkpoint">000731</idno>
<idno type="wicri:Area/Main/Merge">000696</idno>
<idno type="wicri:Area/Main/Curation">000696</idno>
<idno type="wicri:Area/Main/Exploration">000696</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Using spoken words to guide open-ended category formation.</title>
<author><name sortKey="Chauhan, Aneesh" sort="Chauhan, Aneesh" uniqKey="Chauhan A" first="Aneesh" last="Chauhan">Aneesh Chauhan</name>
<affiliation wicri:level="1"><nlm:affiliation>Instituto de Engenharia Electrónica e Telemática de Aveiro (IEETA), Universidade de Aveiro, Portugal. aneesh.chauhan@ua.pt</nlm:affiliation>
<country xml:lang="fr">Portugal</country>
<wicri:regionArea>Instituto de Engenharia Electrónica e Telemática de Aveiro (IEETA), Universidade de Aveiro</wicri:regionArea>
<wicri:noRegion>Universidade de Aveiro</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Seabra Lopes, Luis" sort="Seabra Lopes, Luis" uniqKey="Seabra Lopes L" first="Luís" last="Seabra Lopes">Luís Seabra Lopes</name>
</author>
</analytic>
<series><title level="j">Cognitive processing</title>
<idno type="eISSN">1612-4790</idno>
<imprint><date when="2011" type="published">2011</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Artificial Intelligence</term>
<term>Concept Formation (physiology)</term>
<term>Humans</term>
<term>Names</term>
<term>Robotics</term>
<term>Speech (physiology)</term>
<term>Verbal Learning (physiology)</term>
<term>Vocabulary</term>
</keywords>
<keywords scheme="KwdFr" xml:lang="fr"><term>Apprentissage verbal (physiologie)</term>
<term>Formation de concepts (physiologie)</term>
<term>Humains</term>
<term>Intelligence artificielle</term>
<term>Noms</term>
<term>Parole (physiologie)</term>
<term>Robotique</term>
<term>Vocabulaire</term>
</keywords>
<keywords scheme="MESH" qualifier="physiologie" xml:lang="fr"><term>Apprentissage verbal</term>
<term>Formation de concepts</term>
<term>Parole</term>
</keywords>
<keywords scheme="MESH" qualifier="physiology" xml:lang="en"><term>Concept Formation</term>
<term>Speech</term>
<term>Verbal Learning</term>
</keywords>
<keywords scheme="MESH" xml:lang="en"><term>Artificial Intelligence</term>
<term>Humans</term>
<term>Names</term>
<term>Robotics</term>
<term>Vocabulary</term>
</keywords>
<keywords scheme="MESH" xml:lang="fr"><term>Humains</term>
<term>Intelligence artificielle</term>
<term>Noms</term>
<term>Robotique</term>
<term>Vocabulaire</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Naming is a powerful cognitive tool that facilitates categorization by forming an association between words and their referents. There is evidence in child development literature that strong links exist between early word-learning and conceptual development. A growing view is also emerging that language is a cultural product created and acquired through social interactions. Inspired by these studies, this paper presents a novel learning architecture for category formation and vocabulary acquisition in robots through active interaction with humans. This architecture is open-ended and is capable of acquiring new categories and category names incrementally. The process can be compared to language grounding in children at single-word stage. The robot is embodied with visual and auditory sensors for world perception. A human instructor uses speech to teach the robot the names of the objects present in a visually shared environment. The robot uses its perceptual input to ground these spoken words and dynamically form/organize category descriptions in order to achieve better categorization. To evaluate the learning system at word-learning and category formation tasks, two experiments were conducted using a simple language game involving naming and corrective feedback actions from the human user. The obtained results are presented and discussed in detail.</div>
</front>
</TEI>
<affiliations><list><country><li>Portugal</li>
</country>
</list>
<tree><noCountry><name sortKey="Seabra Lopes, Luis" sort="Seabra Lopes, Luis" uniqKey="Seabra Lopes L" first="Luís" last="Seabra Lopes">Luís Seabra Lopes</name>
</noCountry>
<country name="Portugal"><noRegion><name sortKey="Chauhan, Aneesh" sort="Chauhan, Aneesh" uniqKey="Chauhan A" first="Aneesh" last="Chauhan">Aneesh Chauhan</name>
</noRegion>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/TelematiV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000696 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000696 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= TelematiV1 |flux= Main |étape= Exploration |type= RBID |clé= pubmed:21614526 |texte= Using spoken words to guide open-ended category formation. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:21614526" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \ | NlmPubMed2Wicri -a TelematiV1
This area was generated with Dilib version V0.6.31. |