An Overview of Probabilistic Tree Transducers for Natural Language Processing
Identifieur interne : 000A34 ( Main/Exploration ); précédent : 000A33; suivant : 000A35An Overview of Probabilistic Tree Transducers for Natural Language Processing
Auteurs : Kevin Knight [États-Unis] ; Jonathan Graehl [États-Unis]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2005.
English descriptors
- Teeft :
- Algorithm, Automaton, Cascade, Computational, Computational linguistics, Computational properties, Computer science, Daisuki desu, Della pietra, Derivation tree, Derivation trees, Deterministic ones, Extensive literature, Fsas, Fsts, Generic operations, Good news, Good properties, Graehl, Grammar, Green witch, Input tree, International conference, International workshop, Inverse image, Language model, Language modeling, Language models, Machine translation, Machine translation model, Masters tournament, Modeling, Natural language, Natural language literature, Natural language problems, Natural language processing, Nite, Nite state automata, Object position, Output trees, Overview, Pcfg models, Probabilistic, Probabilistic tree transducer, Probabilistic tree transducers, Proc, Recognition device, Recursively process middle child, Regular expressions, Regular string languages, Regular tree grammar, Regular tree language, Right branch, Root symbol, Rtgs, Statistical machine translation, String automata, String case, Subject position, Subtree, Synchronous grammars, Syntax models, Systems theory, Transducer, Tree acceptors, Tree automata, Tree automata literature, Tree language, Tree language classes, Tree languages, Tree transducer, Tree transducer hierarchy, Tree transducers.
Abstract
Abstract: Probabilistic finite-state string transducers (FSTs) are extremely popular in natural language processing, due to powerful generic methods for applying, composing, and learning them. Unfortunately, FSTs are not a good fit for much of the current work on probabilistic modeling for machine translation, summarization, paraphrasing, and language modeling. These methods operate directly on trees, rather than strings. We show that tree acceptors and tree transducers subsume most of this work, and we discuss algorithms for realizing the same benefits found in probabilistic string transduction.
Url:
DOI: 10.1007/978-3-540-30586-6_1
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000A21
- to stream Istex, to step Curation: 000966
- to stream Istex, to step Checkpoint: 000833
- to stream Main, to step Merge: 000A33
- to stream Main, to step Curation: 000A34
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">An Overview of Probabilistic Tree Transducers for Natural Language Processing</title>
<author><name sortKey="Knight, Kevin" sort="Knight, Kevin" uniqKey="Knight K" first="Kevin" last="Knight">Kevin Knight</name>
</author>
<author><name sortKey="Graehl, Jonathan" sort="Graehl, Jonathan" uniqKey="Graehl J" first="Jonathan" last="Graehl">Jonathan Graehl</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:605AAB4D91D0F341BE34BFB01616A4CE779376EB</idno>
<date when="2005" year="2005">2005</date>
<idno type="doi">10.1007/978-3-540-30586-6_1</idno>
<idno type="url">https://api.istex.fr/document/605AAB4D91D0F341BE34BFB01616A4CE779376EB/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000A21</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000A21</idno>
<idno type="wicri:Area/Istex/Curation">000966</idno>
<idno type="wicri:Area/Istex/Checkpoint">000833</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000833</idno>
<idno type="wicri:doubleKey">0302-9743:2005:Knight K:an:overview:of</idno>
<idno type="wicri:Area/Main/Merge">000A33</idno>
<idno type="wicri:Area/Main/Curation">000A34</idno>
<idno type="wicri:Area/Main/Exploration">000A34</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">An Overview of Probabilistic Tree Transducers for Natural Language Processing</title>
<author><name sortKey="Knight, Kevin" sort="Knight, Kevin" uniqKey="Knight K" first="Kevin" last="Knight">Kevin Knight</name>
<affiliation wicri:level="4"><country>États-Unis</country>
<placeName><settlement type="city">Los Angeles</settlement>
<region type="state">Californie</region>
</placeName>
<orgName type="university">Université de Californie du Sud</orgName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Graehl, Jonathan" sort="Graehl, Jonathan" uniqKey="Graehl J" first="Jonathan" last="Graehl">Jonathan Graehl</name>
<affiliation wicri:level="4"><country>États-Unis</country>
<placeName><settlement type="city">Los Angeles</settlement>
<region type="state">Californie</region>
</placeName>
<orgName type="university">Université de Californie du Sud</orgName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2005</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="Teeft" xml:lang="en"><term>Algorithm</term>
<term>Automaton</term>
<term>Cascade</term>
<term>Computational</term>
<term>Computational linguistics</term>
<term>Computational properties</term>
<term>Computer science</term>
<term>Daisuki desu</term>
<term>Della pietra</term>
<term>Derivation tree</term>
<term>Derivation trees</term>
<term>Deterministic ones</term>
<term>Extensive literature</term>
<term>Fsas</term>
<term>Fsts</term>
<term>Generic operations</term>
<term>Good news</term>
<term>Good properties</term>
<term>Graehl</term>
<term>Grammar</term>
<term>Green witch</term>
<term>Input tree</term>
<term>International conference</term>
<term>International workshop</term>
<term>Inverse image</term>
<term>Language model</term>
<term>Language modeling</term>
<term>Language models</term>
<term>Machine translation</term>
<term>Machine translation model</term>
<term>Masters tournament</term>
<term>Modeling</term>
<term>Natural language</term>
<term>Natural language literature</term>
<term>Natural language problems</term>
<term>Natural language processing</term>
<term>Nite</term>
<term>Nite state automata</term>
<term>Object position</term>
<term>Output trees</term>
<term>Overview</term>
<term>Pcfg models</term>
<term>Probabilistic</term>
<term>Probabilistic tree transducer</term>
<term>Probabilistic tree transducers</term>
<term>Proc</term>
<term>Recognition device</term>
<term>Recursively process middle child</term>
<term>Regular expressions</term>
<term>Regular string languages</term>
<term>Regular tree grammar</term>
<term>Regular tree language</term>
<term>Right branch</term>
<term>Root symbol</term>
<term>Rtgs</term>
<term>Statistical machine translation</term>
<term>String automata</term>
<term>String case</term>
<term>Subject position</term>
<term>Subtree</term>
<term>Synchronous grammars</term>
<term>Syntax models</term>
<term>Systems theory</term>
<term>Transducer</term>
<term>Tree acceptors</term>
<term>Tree automata</term>
<term>Tree automata literature</term>
<term>Tree language</term>
<term>Tree language classes</term>
<term>Tree languages</term>
<term>Tree transducer</term>
<term>Tree transducer hierarchy</term>
<term>Tree transducers</term>
</keywords>
</textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: Probabilistic finite-state string transducers (FSTs) are extremely popular in natural language processing, due to powerful generic methods for applying, composing, and learning them. Unfortunately, FSTs are not a good fit for much of the current work on probabilistic modeling for machine translation, summarization, paraphrasing, and language modeling. These methods operate directly on trees, rather than strings. We show that tree acceptors and tree transducers subsume most of this work, and we discuss algorithms for realizing the same benefits found in probabilistic string transduction.</div>
</front>
</TEI>
<affiliations><list><country><li>États-Unis</li>
</country>
<region><li>Californie</li>
</region>
<settlement><li>Los Angeles</li>
</settlement>
<orgName><li>Université de Californie du Sud</li>
</orgName>
</list>
<tree><country name="États-Unis"><region name="Californie"><name sortKey="Knight, Kevin" sort="Knight, Kevin" uniqKey="Knight K" first="Kevin" last="Knight">Kevin Knight</name>
</region>
<name sortKey="Graehl, Jonathan" sort="Graehl, Jonathan" uniqKey="Graehl J" first="Jonathan" last="Graehl">Jonathan Graehl</name>
<name sortKey="Graehl, Jonathan" sort="Graehl, Jonathan" uniqKey="Graehl J" first="Jonathan" last="Graehl">Jonathan Graehl</name>
<name sortKey="Knight, Kevin" sort="Knight, Kevin" uniqKey="Knight K" first="Kevin" last="Knight">Kevin Knight</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Sarre/explor/MusicSarreV3/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000A34 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000A34 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Sarre |area= MusicSarreV3 |flux= Main |étape= Exploration |type= RBID |clé= ISTEX:605AAB4D91D0F341BE34BFB01616A4CE779376EB |texte= An Overview of Probabilistic Tree Transducers for Natural Language Processing }}
This area was generated with Dilib version V0.6.33. |