Natural Language as the Basis for Meaning Representation and Inference
Identifieur interne : 000666 ( Istex/Curation ); précédent : 000665; suivant : 000667Natural Language as the Basis for Meaning Representation and Inference
Auteurs : Ido Dagan [Israël] ; Roy Bar-Haim [Israël] ; Idan Szpektor [Israël] ; Iddo Greental [Israël] ; Eyal Shnarch [Israël]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2008.
Abstract
Abstract: Semantic inference is an important component in many natural language understanding applications. Classical approaches to semantic inference rely on logical representations for meaning, which may be viewed as being “external” to the natural language itself. However, practical applications usually adopt shallower lexical or lexical-syntactic representations, which correspond closely to language structure. In many cases, such approaches lack a principled meaning representation and inference framework. We describe a generic semantic inference framework that operates directly on language-based structures, particularly syntactic trees. New trees are inferred by applying entailment rules, which provide a unified representation for varying types of inferences. Rules were generated by manual and automatic methods, covering generic linguistic structures as well as specific lexical-based inferences. Initial empirical evaluation in a Relation Extraction setting supports the validity and potential of our approach. Additionally, such inference is shown to improve the critical step of unsupervised learning of entailment rules, which in turn enhances the scope of the inference system. This paper corresponds to the invited talk of the first author at CICLING 2008.
Url:
DOI: 10.1007/978-3-540-78135-6_14
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000826
Links to Exploration step
ISTEX:24F5DD27816CB6A013D84B652F4D4BB13BAFFE96Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Natural Language as the Basis for Meaning Representation and Inference</title>
<author><name sortKey="Dagan, Ido" sort="Dagan, Ido" uniqKey="Dagan I" first="Ido" last="Dagan">Ido Dagan</name>
<affiliation wicri:level="1"><mods:affiliation>Bar Ilan University, 52900, Ramat Gan, Israel</mods:affiliation>
<country xml:lang="fr">Israël</country>
<wicri:regionArea>Bar Ilan University, 52900, Ramat Gan</wicri:regionArea>
</affiliation>
<affiliation wicri:level="1"><mods:affiliation>E-mail: dagan@cs.biu.ac.il</mods:affiliation>
<country wicri:rule="url">Israël</country>
</affiliation>
</author>
<author><name sortKey="Bar Haim, Roy" sort="Bar Haim, Roy" uniqKey="Bar Haim R" first="Roy" last="Bar-Haim">Roy Bar-Haim</name>
<affiliation wicri:level="1"><mods:affiliation>Bar Ilan University, 52900, Ramat Gan, Israel</mods:affiliation>
<country xml:lang="fr">Israël</country>
<wicri:regionArea>Bar Ilan University, 52900, Ramat Gan</wicri:regionArea>
</affiliation>
</author>
<author><name sortKey="Szpektor, Idan" sort="Szpektor, Idan" uniqKey="Szpektor I" first="Idan" last="Szpektor">Idan Szpektor</name>
<affiliation wicri:level="1"><mods:affiliation>Bar Ilan University, 52900, Ramat Gan, Israel</mods:affiliation>
<country xml:lang="fr">Israël</country>
<wicri:regionArea>Bar Ilan University, 52900, Ramat Gan</wicri:regionArea>
</affiliation>
</author>
<author><name sortKey="Greental, Iddo" sort="Greental, Iddo" uniqKey="Greental I" first="Iddo" last="Greental">Iddo Greental</name>
<affiliation wicri:level="1"><mods:affiliation>Tel Aviv University, 69978, Tel Aviv, Israel</mods:affiliation>
<country xml:lang="fr">Israël</country>
<wicri:regionArea>Tel Aviv University, 69978, Tel Aviv</wicri:regionArea>
</affiliation>
</author>
<author><name sortKey="Shnarch, Eyal" sort="Shnarch, Eyal" uniqKey="Shnarch E" first="Eyal" last="Shnarch">Eyal Shnarch</name>
<affiliation wicri:level="1"><mods:affiliation>Bar Ilan University, 52900, Ramat Gan, Israel</mods:affiliation>
<country xml:lang="fr">Israël</country>
<wicri:regionArea>Bar Ilan University, 52900, Ramat Gan</wicri:regionArea>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:24F5DD27816CB6A013D84B652F4D4BB13BAFFE96</idno>
<date when="2008" year="2008">2008</date>
<idno type="doi">10.1007/978-3-540-78135-6_14</idno>
<idno type="url">https://api.istex.fr/document/24F5DD27816CB6A013D84B652F4D4BB13BAFFE96/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000826</idno>
<idno type="wicri:Area/Istex/Curation">000666</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Natural Language as the Basis for Meaning Representation and Inference</title>
<author><name sortKey="Dagan, Ido" sort="Dagan, Ido" uniqKey="Dagan I" first="Ido" last="Dagan">Ido Dagan</name>
<affiliation wicri:level="1"><mods:affiliation>Bar Ilan University, 52900, Ramat Gan, Israel</mods:affiliation>
<country xml:lang="fr">Israël</country>
<wicri:regionArea>Bar Ilan University, 52900, Ramat Gan</wicri:regionArea>
</affiliation>
<affiliation wicri:level="1"><mods:affiliation>E-mail: dagan@cs.biu.ac.il</mods:affiliation>
<country wicri:rule="url">Israël</country>
</affiliation>
</author>
<author><name sortKey="Bar Haim, Roy" sort="Bar Haim, Roy" uniqKey="Bar Haim R" first="Roy" last="Bar-Haim">Roy Bar-Haim</name>
<affiliation wicri:level="1"><mods:affiliation>Bar Ilan University, 52900, Ramat Gan, Israel</mods:affiliation>
<country xml:lang="fr">Israël</country>
<wicri:regionArea>Bar Ilan University, 52900, Ramat Gan</wicri:regionArea>
</affiliation>
</author>
<author><name sortKey="Szpektor, Idan" sort="Szpektor, Idan" uniqKey="Szpektor I" first="Idan" last="Szpektor">Idan Szpektor</name>
<affiliation wicri:level="1"><mods:affiliation>Bar Ilan University, 52900, Ramat Gan, Israel</mods:affiliation>
<country xml:lang="fr">Israël</country>
<wicri:regionArea>Bar Ilan University, 52900, Ramat Gan</wicri:regionArea>
</affiliation>
</author>
<author><name sortKey="Greental, Iddo" sort="Greental, Iddo" uniqKey="Greental I" first="Iddo" last="Greental">Iddo Greental</name>
<affiliation wicri:level="1"><mods:affiliation>Tel Aviv University, 69978, Tel Aviv, Israel</mods:affiliation>
<country xml:lang="fr">Israël</country>
<wicri:regionArea>Tel Aviv University, 69978, Tel Aviv</wicri:regionArea>
</affiliation>
</author>
<author><name sortKey="Shnarch, Eyal" sort="Shnarch, Eyal" uniqKey="Shnarch E" first="Eyal" last="Shnarch">Eyal Shnarch</name>
<affiliation wicri:level="1"><mods:affiliation>Bar Ilan University, 52900, Ramat Gan, Israel</mods:affiliation>
<country xml:lang="fr">Israël</country>
<wicri:regionArea>Bar Ilan University, 52900, Ramat Gan</wicri:regionArea>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2008</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
</series>
<idno type="istex">24F5DD27816CB6A013D84B652F4D4BB13BAFFE96</idno>
<idno type="DOI">10.1007/978-3-540-78135-6_14</idno>
<idno type="ChapterID">Chap14</idno>
<idno type="ChapterID">14</idno>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: Semantic inference is an important component in many natural language understanding applications. Classical approaches to semantic inference rely on logical representations for meaning, which may be viewed as being “external” to the natural language itself. However, practical applications usually adopt shallower lexical or lexical-syntactic representations, which correspond closely to language structure. In many cases, such approaches lack a principled meaning representation and inference framework. We describe a generic semantic inference framework that operates directly on language-based structures, particularly syntactic trees. New trees are inferred by applying entailment rules, which provide a unified representation for varying types of inferences. Rules were generated by manual and automatic methods, covering generic linguistic structures as well as specific lexical-based inferences. Initial empirical evaluation in a Relation Extraction setting supports the validity and potential of our approach. Additionally, such inference is shown to improve the critical step of unsupervised learning of entailment rules, which in turn enhances the scope of the inference system. This paper corresponds to the invited talk of the first author at CICLING 2008.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Musique/explor/MozartV1/Data/Istex/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000666 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Curation/biblio.hfd -nk 000666 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Musique |area= MozartV1 |flux= Istex |étape= Curation |type= RBID |clé= ISTEX:24F5DD27816CB6A013D84B652F4D4BB13BAFFE96 |texte= Natural Language as the Basis for Meaning Representation and Inference }}
This area was generated with Dilib version V0.6.20. |