PaulMeyerV1, Main, Exploration, bibRecord, 000701

Comprehension Grammars Generated from Machine Learning of Natural Languages

Identifieur interne : 000701 ( Main/Exploration ); précédent : 000700; suivant : 000702

Comprehension Grammars Generated from Machine Learning of Natural Languages

Auteurs : Patrick Suppes [États-Unis] ; Michael Böttner [Pays-Bas] ; Lin Liang [États-Unis]

Source :

Machine Learning [ 0885-6125 ] ; 1995.

RBID : ISTEX:E5A0F4BFBF00C07B85AFF3FFDF204971B765E73F

English descriptors

Entity :
- org : Netherlands LIN LIANG CSL, Stanford University.
- pers : Association, In, LIANG Table, Michael Bottner, Michael Böttner, Michael Donio, Paul Meyer.
- place : Amsterdam, Nijmegen, Stanford.
Teeft :
- Action structure, Association computation, Association relation, Axiom, Befindliche schraube, Black screw, Bottner, Category symbol, Certain relation, Cognitive science, Common noun, Comprehension, Comprehension grammar, Comprehensiongrammarsfrom machinelearning, Congruence class, Congruence computation, Contiguous constituent, Corresponding grammatical rule, Definite article, Denotational, Denotational value, Elementary assembly action, English command, English lexical semantics, English preposition, English word, Finite sample, First language, Form association, Form generalization, Grammar, Grammatical, Grammatical form, Grammatical generalization, Grammatical rule, Greek letter, High level rule, Internal language, Internal representation, Internal symbol, Language acquisition, Large screw, Lexical, Lexical rule, Liang, Lisp, Lisp regimentation, Loch, More natural, Nage, Natural language, Noncontiguous constituent, Nondenoting, Nondenoting word, Object phrase, Object structure, Other hand, Other language, Parse, Particular command, Probabilistic, Probabilistic association, Robot, Robotic instruction, Rule common, Rule generation, Schraube, Screw, Second occurrence, Semantic category, Semantic operation, Semantics, Spatial relation, Special rule, Sscrew, Stanford university, Substring, Suppes, Uniform procedure, Various event, Ventura hall, Verbal command, Verbal stimulus, Washer, Word association.

Abstract

Abstract: We are developing a theory of probabilistic language learning in the context of robotic instruction in elementary assembly actions. We describe the process of machine learning in terms of the various events that happen on a given trial, including the crucial association of words with internal representations of their meaning. Of central importance in learning is the generalization from utterances to grammatical forms. Our system derives a comprehension grammar for a superset of a natural language from pairs of verbal stimuli like Go to the screw! and corresponding internal representations of coerced actions. For the derivation of a grammar no knowledge of the language to be learned is assumed but only knowledge of an internal language. We present grammars for English, Chinese, and German generated from a finite sample of about 500 commands that are roughly equivalent across the three languages. All of the three grammars, which are context-free in form, accept an infinite set of commands in the given language.

Url:

DOI: 10.1023/A:1022663208628

Affiliations:

Le document en format XML

<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Comprehension Grammars Generated from Machine Learning of Natural Languages</title>
<author><name sortKey="Suppes, Patrick" sort="Suppes, Patrick" uniqKey="Suppes P" first="Patrick" last="Suppes">Patrick Suppes</name>
</author>
<author><name sortKey="Bottner, Michael" sort="Bottner, Michael" uniqKey="Bottner M" first="Michael" last="Böttner">Michael Böttner</name>
</author>
<author><name sortKey="Liang, Lin" sort="Liang, Lin" uniqKey="Liang L" first="Lin" last="Liang">Lin Liang</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:E5A0F4BFBF00C07B85AFF3FFDF204971B765E73F</idno>
<date when="1995" year="1995">1995</date>
<idno type="doi">10.1023/A:1022663208628</idno>
<idno type="url">https://api.istex.fr/ark:/67375/1BB-VM7NQLSR-T/fulltext.pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000449</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000449</idno>
<idno type="wicri:Area/Istex/Curation">000359</idno>
<idno type="wicri:Area/Istex/Checkpoint">000685</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000685</idno>
<idno type="wicri:doubleKey">0885-6125:1995:Suppes P:comprehension:grammars:generated</idno>
<idno type="wicri:Area/Main/Merge">000710</idno>
<idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:DAAD1A6C94D22458A61AB947249D4021A9B49A64</idno>
<idno type="url">https://api.istex.fr/ark:/67375/1BB-R5WVH8ZL-4/fulltext.pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000446</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000446</idno>
<idno type="wicri:Area/Istex/Curation">000357</idno>
<idno type="wicri:Area/Istex/Checkpoint">000684</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000684</idno>
<idno type="wicri:doubleKey">0885-6125:1995:Suppes P:comprehension:grammars:generated</idno>
<idno type="wicri:Area/Main/Merge">000709</idno>
<idno type="wicri:Area/Main/Curation">000701</idno>
<idno type="wicri:Area/Main/Exploration">000701</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Comprehension Grammars Generated from Machine Learning of Natural Languages</title>
<author><name sortKey="Suppes, Patrick" sort="Suppes, Patrick" uniqKey="Suppes P" first="Patrick" last="Suppes">Patrick Suppes</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<placeName><region type="state">Californie</region>
<settlement type="city">Stanford (Californie)</settlement>
</placeName>
<wicri:cityArea>CSLI, Ventura Hall, Stanford University, 94305-4115, Stanford</wicri:cityArea>
<orgName type="university">Université Stanford</orgName>
</affiliation>
</author>
<author><name sortKey="Bottner, Michael" sort="Bottner, Michael" uniqKey="Bottner M" first="Michael" last="Böttner">Michael Böttner</name>
<affiliation wicri:level="3"><country xml:lang="fr">Pays-Bas</country>
<wicri:regionArea>Max-Planck-lnstitutfür Psycholinguistik, 6526 XD, Nijmegen</wicri:regionArea>
<placeName><settlement type="city">Nimègue</settlement>
<region type="province" nuts="2">Gueldre</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Liang, Lin" sort="Liang, Lin" uniqKey="Liang L" first="Lin" last="Liang">Lin Liang</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<placeName><region type="state">Californie</region>
<settlement type="city">Stanford (Californie)</settlement>
</placeName>
<wicri:cityArea>CSLI, Ventura Hall, Stanford University, 94305-4115, Stanford</wicri:cityArea>
<orgName type="university">Université Stanford</orgName>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j" type="main">Machine Learning</title>
<title level="j" type="abbrev">Machine Learning</title>
<idno type="ISSN">0885-6125</idno>
<idno type="eISSN">1573-0565</idno>
<imprint><publisher>Kluwer Academic Publishers-Plenum Publishers</publisher>
<pubPlace>New York</pubPlace>
<date type="published" when="1995">1995</date>
<biblScope unit="vol" from="19" to="19">19</biblScope>
<biblScope unit="issue" from="2" to="2">2</biblScope>
<biblScope unit="page" from="133">133</biblScope>
<biblScope unit="page" to="152">152</biblScope>
</imprint>
<idno type="ISSN">0885-6125</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0885-6125</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="Entity" type="org" xml:lang="en"><term>Netherlands LIN LIANG CSL</term>
<term>Stanford University</term>
</keywords>
<keywords scheme="Entity" type="pers" xml:lang="en"><term>Association</term>
<term>In</term>
<term>LIANG Table</term>
<term>Michael Bottner</term>
<term>Michael Böttner</term>
<term>Michael Donio</term>
<term>Paul Meyer</term>
</keywords>
<keywords scheme="Entity" type="place" xml:lang="en"><term>Amsterdam</term>
<term>Nijmegen</term>
<term>Stanford</term>
</keywords>
<keywords scheme="Teeft" xml:lang="en"><term>Action structure</term>
<term>Association computation</term>
<term>Association relation</term>
<term>Axiom</term>
<term>Befindliche schraube</term>
<term>Black screw</term>
<term>Bottner</term>
<term>Category symbol</term>
<term>Certain relation</term>
<term>Cognitive science</term>
<term>Common noun</term>
<term>Comprehension</term>
<term>Comprehension grammar</term>
<term>Comprehensiongrammarsfrom machinelearning</term>
<term>Congruence class</term>
<term>Congruence computation</term>
<term>Contiguous constituent</term>
<term>Corresponding grammatical rule</term>
<term>Definite article</term>
<term>Denotational</term>
<term>Denotational value</term>
<term>Elementary assembly action</term>
<term>English command</term>
<term>English lexical semantics</term>
<term>English preposition</term>
<term>English word</term>
<term>Finite sample</term>
<term>First language</term>
<term>Form association</term>
<term>Form generalization</term>
<term>Grammar</term>
<term>Grammatical</term>
<term>Grammatical form</term>
<term>Grammatical generalization</term>
<term>Grammatical rule</term>
<term>Greek letter</term>
<term>High level rule</term>
<term>Internal language</term>
<term>Internal representation</term>
<term>Internal symbol</term>
<term>Language acquisition</term>
<term>Large screw</term>
<term>Lexical</term>
<term>Lexical rule</term>
<term>Liang</term>
<term>Lisp</term>
<term>Lisp regimentation</term>
<term>Loch</term>
<term>More natural</term>
<term>Nage</term>
<term>Natural language</term>
<term>Noncontiguous constituent</term>
<term>Nondenoting</term>
<term>Nondenoting word</term>
<term>Object phrase</term>
<term>Object structure</term>
<term>Other hand</term>
<term>Other language</term>
<term>Parse</term>
<term>Particular command</term>
<term>Probabilistic</term>
<term>Probabilistic association</term>
<term>Robot</term>
<term>Robotic instruction</term>
<term>Rule common</term>
<term>Rule generation</term>
<term>Schraube</term>
<term>Screw</term>
<term>Second occurrence</term>
<term>Semantic category</term>
<term>Semantic operation</term>
<term>Semantics</term>
<term>Spatial relation</term>
<term>Special rule</term>
<term>Sscrew</term>
<term>Stanford university</term>
<term>Substring</term>
<term>Suppes</term>
<term>Uniform procedure</term>
<term>Various event</term>
<term>Ventura hall</term>
<term>Verbal command</term>
<term>Verbal stimulus</term>
<term>Washer</term>
<term>Word association</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: We are developing a theory of probabilistic language learning in the context of robotic instruction in elementary assembly actions. We describe the process of machine learning in terms of the various events that happen on a given trial, including the crucial association of words with internal representations of their meaning. Of central importance in learning is the generalization from utterances to grammatical forms. Our system derives a comprehension grammar for a superset of a natural language from pairs of verbal stimuli like Go to the screw! and corresponding internal representations of coerced actions. For the derivation of a grammar no knowledge of the language to be learned is assumed but only knowledge of an internal language. We present grammars for English, Chinese, and German generated from a finite sample of about 500 commands that are roughly equivalent across the three languages. All of the three grammars, which are context-free in form, accept an infinite set of commands in the given language.</div>
</front>
</TEI>
<affiliations><list><country><li>Pays-Bas</li>
<li>États-Unis</li>
</country>
<region><li>Californie</li>
<li>Gueldre</li>
</region>
<settlement><li>Nimègue</li>
<li>Stanford (Californie)</li>
</settlement>
<orgName><li>Université Stanford</li>
</orgName>
</list>
<tree><country name="États-Unis"><region name="Californie"><name sortKey="Suppes, Patrick" sort="Suppes, Patrick" uniqKey="Suppes P" first="Patrick" last="Suppes">Patrick Suppes</name>
</region>
<name sortKey="Liang, Lin" sort="Liang, Lin" uniqKey="Liang L" first="Lin" last="Liang">Lin Liang</name>
</country>
<country name="Pays-Bas"><region name="Gueldre"><name sortKey="Bottner, Michael" sort="Bottner, Michael" uniqKey="Bottner M" first="Michael" last="Böttner">Michael Böttner</name>
</region>
</country>
</tree>
</affiliations>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/ChansonRoland/explor/PaulMeyerV1/Data/Main/Exploration

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000701 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000701 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    ChansonRoland
   |area=    PaulMeyerV1
   |flux=    Main
   |étape=   Exploration
   |type=    RBID
   |clé=     ISTEX:E5A0F4BFBF00C07B85AFF3FFDF204971B765E73F
   |texte=   Comprehension Grammars Generated from Machine Learning of Natural Languages
}}

This area was generated with Dilib version V0.6.39.
Data generation: Wed Nov 24 15:28:42 2021. Site generation: Wed Nov 24 15:32:21 2021

Serveur d'exploration Paul Meyer

Comprehension Grammars Generated from Machine Learning of Natural Languages

Comprehension Grammars Generated from Machine Learning of Natural Languages

Source :

English descriptors

Abstract

Links toward previous steps (curation, corpus...)

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri

	Serveur d'exploration Paul Meyer
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.