Enhancing Relation Extraction by Eliciting Selectional Constraint Features from Wikipedia
Identifieur interne : 000599 ( Main/Exploration ); précédent : 000598; suivant : 000600Enhancing Relation Extraction by Eliciting Selectional Constraint Features from Wikipedia
Auteurs : Gang Wang [République populaire de Chine] ; Huajie Zhang [République populaire de Chine] ; Haofen Wang [République populaire de Chine] ; Yong Yu [République populaire de Chine]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2007.
Abstract
Abstract: Selectional Con straints are usually checked for detecting semantic relations. Previous work usually defined the constraints manually based on hand crafted concept taxonomy, which is time-consuming and impractical for large scale relation extraction. Further, the determination of entity type (e.g. NER) based on the taxonomy cannot achieve sufficiently high accuracy. In this paper, we propose a novel approach to extracting relation instances using the features elicited from Wikipedia, a free online encyclopedia. The features are represented as selectional constraints and further employed to enhance the extrac tion of relations. We conduct case stud ies on the validation of the ex tracted instances for two common relations hasAr tist(album, artist) andhasDirector(film, director). Substantially high extraction precision (around 0.95) and validation accuracy (near 0.90) are obtained.
Url:
DOI: 10.1007/978-3-540-73351-5_29
Affiliations:
Links toward previous steps (curation, corpus...)
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Enhancing Relation Extraction by Eliciting Selectional Constraint Features from Wikipedia</title><author><name sortKey="Wang, Gang" sort="Wang, Gang" uniqKey="Wang G" first="Gang" last="Wang">Gang Wang</name></author><author><name sortKey="Zhang, Huajie" sort="Zhang, Huajie" uniqKey="Zhang H" first="Huajie" last="Zhang">Huajie Zhang</name></author><author><name sortKey="Wang, Haofen" sort="Wang, Haofen" uniqKey="Wang H" first="Haofen" last="Wang">Haofen Wang</name></author><author><name sortKey="Yu, Yong" sort="Yu, Yong" uniqKey="Yu Y" first="Yong" last="Yu">Yong Yu</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:A272EFDCA7D95C9D4F87BB1621FBEF7DE8DE25DA</idno><date when="2007" year="2007">2007</date><idno type="doi">10.1007/978-3-540-73351-5_29</idno><idno type="url">https://api.istex.fr/document/A272EFDCA7D95C9D4F87BB1621FBEF7DE8DE25DA/fulltext/pdf</idno><idno type="wicri:Area/Main/Corpus">000A51</idno><idno type="wicri:Area/Main/Curation">000A39</idno><idno type="wicri:Area/Main/Exploration">000599</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Exploration">000599</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Enhancing Relation Extraction by Eliciting Selectional Constraint Features from Wikipedia</title><author><name sortKey="Wang, Gang" sort="Wang, Gang" uniqKey="Wang G" first="Gang" last="Wang">Gang Wang</name><affiliation wicri:level="1"><country xml:lang="fr">République populaire de Chine</country><wicri:regionArea>Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai, 200240</wicri:regionArea><wicri:noRegion>200240</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">République populaire de Chine</country></affiliation></author><author><name sortKey="Zhang, Huajie" sort="Zhang, Huajie" uniqKey="Zhang H" first="Huajie" last="Zhang">Huajie Zhang</name><affiliation wicri:level="1"><country xml:lang="fr">République populaire de Chine</country><wicri:regionArea>Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai, 200240</wicri:regionArea><wicri:noRegion>200240</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">République populaire de Chine</country></affiliation></author><author><name sortKey="Wang, Haofen" sort="Wang, Haofen" uniqKey="Wang H" first="Haofen" last="Wang">Haofen Wang</name><affiliation wicri:level="1"><country xml:lang="fr">République populaire de Chine</country><wicri:regionArea>Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai, 200240</wicri:regionArea><wicri:noRegion>200240</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">République populaire de Chine</country></affiliation></author><author><name sortKey="Yu, Yong" sort="Yu, Yong" uniqKey="Yu Y" first="Yong" last="Yu">Yong Yu</name><affiliation wicri:level="1"><country xml:lang="fr">République populaire de Chine</country><wicri:regionArea>Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai, 200240</wicri:regionArea><wicri:noRegion>200240</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">République populaire de Chine</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2007</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">A272EFDCA7D95C9D4F87BB1621FBEF7DE8DE25DA</idno><idno type="DOI">10.1007/978-3-540-73351-5_29</idno><idno type="ChapterID">Chap29</idno><idno type="ChapterID">29</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: Selectional Con straints are usually checked for detecting semantic relations. Previous work usually defined the constraints manually based on hand crafted concept taxonomy, which is time-consuming and impractical for large scale relation extraction. Further, the determination of entity type (e.g. NER) based on the taxonomy cannot achieve sufficiently high accuracy. In this paper, we propose a novel approach to extracting relation instances using the features elicited from Wikipedia, a free online encyclopedia. The features are represented as selectional constraints and further employed to enhance the extrac tion of relations. We conduct case stud ies on the validation of the ex tracted instances for two common relations hasAr tist(album, artist) andhasDirector(film, director). Substantially high extraction precision (around 0.95) and validation accuracy (near 0.90) are obtained.</div></front></TEI><affiliations><list><country><li>République populaire de Chine</li></country></list><tree><country name="République populaire de Chine"><noRegion><name sortKey="Wang, Gang" sort="Wang, Gang" uniqKey="Wang G" first="Gang" last="Wang">Gang Wang</name></noRegion><name sortKey="Wang, Gang" sort="Wang, Gang" uniqKey="Wang G" first="Gang" last="Wang">Gang Wang</name><name sortKey="Wang, Haofen" sort="Wang, Haofen" uniqKey="Wang H" first="Haofen" last="Wang">Haofen Wang</name><name sortKey="Wang, Haofen" sort="Wang, Haofen" uniqKey="Wang H" first="Haofen" last="Wang">Haofen Wang</name><name sortKey="Yu, Yong" sort="Yu, Yong" uniqKey="Yu Y" first="Yong" last="Yu">Yong Yu</name><name sortKey="Yu, Yong" sort="Yu, Yong" uniqKey="Yu Y" first="Yong" last="Yu">Yong Yu</name><name sortKey="Zhang, Huajie" sort="Zhang, Huajie" uniqKey="Zhang H" first="Huajie" last="Zhang">Huajie Zhang</name><name sortKey="Zhang, Huajie" sort="Zhang, Huajie" uniqKey="Zhang H" first="Huajie" last="Zhang">Huajie Zhang</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Musique/explor/SchutzV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000599 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000599 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Musique
|area= SchutzV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:A272EFDCA7D95C9D4F87BB1621FBEF7DE8DE25DA
|texte= Enhancing Relation Extraction by Eliciting Selectional Constraint Features from Wikipedia
}}
| This area was generated with Dilib version V0.6.38. |  |