Learning tree languages from positive examples and membership queries
Identifieur interne : 007031 ( Main/Merge ); précédent : 007030; suivant : 007032Learning tree languages from positive examples and membership queries
Auteurs : Jérome Besombes [France] ; Jean-Yves Marion [France]Source :
- Lecture notes in computer science [ 0302-9743 ] ; 2004.
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Intelligence artificielle.
English descriptors
- KwdEn :
Abstract
We investigate regular tree languages exact learning from positive examples and membership queries. Input data are trees of the language to infer. The learner computes new trees from the inputs and asks to the oracle whether or not they belong to the language. From the answers, the learner may ask further membership queries until he finds the correct grammar that generates the target language. This paradigm was introduced by Angluin in the seminal work [1] for the case of regular word language. Neither negative examples, equivalence queries nor counter examples are allowed in this paradigm. We describe an efficient algorithm which is polynomial in the size of the examples for learning the whole class of regular tree languages. The convergence is insured when the set of examples contains a representative sample of the language to guess. A finite subset ε of a regular tree language £ is representative for L if every transition of the minimal tree automaton for L is used at least once for the derivation of an element of the set ε.
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000615
- to stream PascalFrancis, to step Curation: 000426
- to stream PascalFrancis, to step Checkpoint: 000596
Links to Exploration step
Pascal:04-0542613Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Learning tree languages from positive examples and membership queries</title><author><name sortKey="Besombes, Jerome" sort="Besombes, Jerome" uniqKey="Besombes J" first="Jérome" last="Besombes">Jérome Besombes</name><affiliation wicri:level="3"><inist:fA14 i1="01"><s1>LORIA - INPL, Ecole Nationale Supérieure des Mines de Nancy, 615, rue du jardin botanique</s1><s2>54602 Villers-lès-Nancy</s2><s3>FRA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>France</country><placeName><region type="region" nuts="2">Grand Est</region><region type="old region" nuts="2">Lorraine (région)</region><settlement type="city">Villers-lès-Nancy</settlement></placeName></affiliation></author><author><name sortKey="Marion, Jean Yves" sort="Marion, Jean Yves" uniqKey="Marion J" first="Jean-Yves" last="Marion">Jean-Yves Marion</name><affiliation wicri:level="3"><inist:fA14 i1="01"><s1>LORIA - INPL, Ecole Nationale Supérieure des Mines de Nancy, 615, rue du jardin botanique</s1><s2>54602 Villers-lès-Nancy</s2><s3>FRA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>France</country><placeName><region type="region" nuts="2">Grand Est</region><region type="old region" nuts="2">Lorraine (région)</region><settlement type="city">Villers-lès-Nancy</settlement></placeName></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">04-0542613</idno><date when="2004">2004</date><idno type="stanalyst">PASCAL 04-0542613 INIST</idno><idno type="RBID">Pascal:04-0542613</idno><idno type="wicri:Area/PascalFrancis/Corpus">000615</idno><idno type="wicri:Area/PascalFrancis/Curation">000426</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000596</idno><idno type="wicri:explorRef" wicri:stream="PascalFrancis" wicri:step="Checkpoint">000596</idno><idno type="wicri:doubleKey">0302-9743:2004:Besombes J:learning:tree:languages</idno><idno type="wicri:Area/Main/Merge">007031</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Learning tree languages from positive examples and membership queries</title><author><name sortKey="Besombes, Jerome" sort="Besombes, Jerome" uniqKey="Besombes J" first="Jérome" last="Besombes">Jérome Besombes</name><affiliation wicri:level="3"><inist:fA14 i1="01"><s1>LORIA - INPL, Ecole Nationale Supérieure des Mines de Nancy, 615, rue du jardin botanique</s1><s2>54602 Villers-lès-Nancy</s2><s3>FRA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>France</country><placeName><region type="region" nuts="2">Grand Est</region><region type="old region" nuts="2">Lorraine (région)</region><settlement type="city">Villers-lès-Nancy</settlement></placeName></affiliation></author><author><name sortKey="Marion, Jean Yves" sort="Marion, Jean Yves" uniqKey="Marion J" first="Jean-Yves" last="Marion">Jean-Yves Marion</name><affiliation wicri:level="3"><inist:fA14 i1="01"><s1>LORIA - INPL, Ecole Nationale Supérieure des Mines de Nancy, 615, rue du jardin botanique</s1><s2>54602 Villers-lès-Nancy</s2><s3>FRA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>France</country><placeName><region type="region" nuts="2">Grand Est</region><region type="old region" nuts="2">Lorraine (région)</region><settlement type="city">Villers-lès-Nancy</settlement></placeName></affiliation></author></analytic><series><title level="j" type="main">Lecture notes in computer science</title><idno type="ISSN">0302-9743</idno><imprint><date when="2004">2004</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">Lecture notes in computer science</title><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Artificial intelligence</term><term>Database query</term><term>Grammar</term><term>Language class</term><term>Learning algorithm</term><term>Learning by example</term><term>Minimal tree</term><term>Oracle</term><term>Polynomial method</term><term>Regular language</term><term>Target language</term><term>Tree automaton</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Algorithme apprentissage</term><term>Intelligence artificielle</term><term>Interrogation base donnée</term><term>Langage rationnel</term><term>Apprentissage à partir d'exemple</term><term>Classe langage</term><term>Automate arbre</term><term>Oracle</term><term>Grammaire</term><term>Langue cible</term><term>Arbre minimal</term><term>Méthode polynomiale</term><term>Langage régulier</term></keywords><keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Intelligence artificielle</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">We investigate regular tree languages exact learning from positive examples and membership queries. Input data are trees of the language to infer. The learner computes new trees from the inputs and asks to the oracle whether or not they belong to the language. From the answers, the learner may ask further membership queries until he finds the correct grammar that generates the target language. This paradigm was introduced by Angluin in the seminal work [1] for the case of regular word language. Neither negative examples, equivalence queries nor counter examples are allowed in this paradigm. We describe an efficient algorithm which is polynomial in the size of the examples for learning the whole class of regular tree languages. The convergence is insured when the set of examples contains a representative sample of the language to guess. A finite subset ε of a regular tree language £ is representative for L if every transition of the minimal tree automaton for L is used at least once for the derivation of an element of the set ε.</div></front></TEI><affiliations><list><country><li>France</li></country><region><li>Grand Est</li><li>Lorraine (région)</li></region><settlement><li>Villers-lès-Nancy</li></settlement></list><tree><country name="France"><region name="Grand Est"><name sortKey="Besombes, Jerome" sort="Besombes, Jerome" uniqKey="Besombes J" first="Jérome" last="Besombes">Jérome Besombes</name></region><name sortKey="Marion, Jean Yves" sort="Marion, Jean Yves" uniqKey="Marion J" first="Jean-Yves" last="Marion">Jean-Yves Marion</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 007031 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 007031 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Main
|étape= Merge
|type= RBID
|clé= Pascal:04-0542613
|texte= Learning tree languages from positive examples and membership queries
}}
| This area was generated with Dilib version V0.6.33. |  |