A multimodal alignment framework for spoken documents
Identifieur interne : 000678 ( Istex/Checkpoint ); précédent : 000677; suivant : 000679A multimodal alignment framework for spoken documents
Auteurs : Dalila Mekhaldi [Royaume-Uni] ; Denis Lalanne [Suisse] ; Rolf Ingold [Suisse]Source :
- Multimedia Tools and Applications [ 1380-7501 ] ; 2012-11-01.
English descriptors
- KwdEn :
Abstract
Abstract: We present a multimodal document alignment framework, which highlights existing alignment relationships between documents that are discussed and recorded during multimedia events such as meetings. These relationships that should help indexing the archives of these events are detected using various techniques from natural language processing and information retrieval. The main alignment strategies studied are based on thematic, quotation and reference relationships. At the analysis level, the alignment framework was applied at several levels of granularity of documents, requiring specific document segmentation techniques. Our framework that is language independent was evaluated on corpora in French and English, including meetings and scientific presentations. The satisfactory evaluation results obtained at several stages show the importance of our approach in bridging the gap between meeting documents, independently from the language and domain. They highlight also the utility of the multimodal alignment in advanced applications, e.g. multimedia document browsing, content-based / temporal-based searching, etc.
Url:
DOI: 10.1007/s11042-011-0842-x
Affiliations:
Links toward previous steps (curation, corpus...)
Links to Exploration step
ISTEX:2AC75FC89E722D405FE84188DCDF855B37E84BC9Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">A multimodal alignment framework for spoken documents</title><author><name sortKey="Mekhaldi, Dalila" sort="Mekhaldi, Dalila" uniqKey="Mekhaldi D" first="Dalila" last="Mekhaldi">Dalila Mekhaldi</name></author><author><name sortKey="Lalanne, Denis" sort="Lalanne, Denis" uniqKey="Lalanne D" first="Denis" last="Lalanne">Denis Lalanne</name></author><author><name sortKey="Ingold, Rolf" sort="Ingold, Rolf" uniqKey="Ingold R" first="Rolf" last="Ingold">Rolf Ingold</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:2AC75FC89E722D405FE84188DCDF855B37E84BC9</idno><date when="2011" year="2011">2011</date><idno type="doi">10.1007/s11042-011-0842-x</idno><idno type="url">https://api.istex.fr/ark:/67375/VQC-023H9GL0-6/fulltext.pdf</idno><idno type="wicri:Area/Istex/Corpus">000998</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000998</idno><idno type="wicri:Area/Istex/Curation">000992</idno><idno type="wicri:Area/Istex/Checkpoint">000678</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000678</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">A multimodal alignment framework for spoken documents</title><author><name sortKey="Mekhaldi, Dalila" sort="Mekhaldi, Dalila" uniqKey="Mekhaldi D" first="Dalila" last="Mekhaldi">Dalila Mekhaldi</name><affiliation wicri:level="1"><country xml:lang="fr">Royaume-Uni</country><wicri:regionArea>Computational Linguistics Group, University of Wolverhampton, Wolverhampton</wicri:regionArea><wicri:noRegion>Wolverhampton</wicri:noRegion></affiliation><affiliation></affiliation></author><author><name sortKey="Lalanne, Denis" sort="Lalanne, Denis" uniqKey="Lalanne D" first="Denis" last="Lalanne">Denis Lalanne</name><affiliation wicri:level="4"><country xml:lang="fr">Suisse</country><wicri:regionArea>Department of Informatics, University of Fribourg, Fribourg</wicri:regionArea><orgName type="university">Université de Fribourg</orgName><placeName><settlement type="city">Fribourg</settlement><region nuts="3" type="region">Canton de Fribourg</region></placeName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Suisse</country></affiliation></author><author><name sortKey="Ingold, Rolf" sort="Ingold, Rolf" uniqKey="Ingold R" first="Rolf" last="Ingold">Rolf Ingold</name><affiliation wicri:level="4"><country xml:lang="fr">Suisse</country><wicri:regionArea>Department of Informatics, University of Fribourg, Fribourg</wicri:regionArea><orgName type="university">Université de Fribourg</orgName><placeName><settlement type="city">Fribourg</settlement><region nuts="3" type="region">Canton de Fribourg</region></placeName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Suisse</country></affiliation></author></analytic><monogr></monogr><series><title level="j">Multimedia Tools and Applications</title><title level="j" type="sub">An International Journal</title><title level="j" type="abbrev">Multimed Tools Appl</title><idno type="ISSN">1380-7501</idno><idno type="eISSN">1573-7721</idno><imprint><publisher>Springer US; http://www.springer-ny.com</publisher><pubPlace>Boston</pubPlace><date type="published" when="2012-11-01">2012-11-01</date><biblScope unit="volume">61</biblScope><biblScope unit="issue">2</biblScope><biblScope unit="page" from="353">353</biblScope><biblScope unit="page" to="388">388</biblScope></imprint><idno type="ISSN">1380-7501</idno></series></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">1380-7501</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Document structure</term><term>Multimodal document</term><term>Quotation alignment</term><term>Reference alignment</term><term>Thematic alignment</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: We present a multimodal document alignment framework, which highlights existing alignment relationships between documents that are discussed and recorded during multimedia events such as meetings. These relationships that should help indexing the archives of these events are detected using various techniques from natural language processing and information retrieval. The main alignment strategies studied are based on thematic, quotation and reference relationships. At the analysis level, the alignment framework was applied at several levels of granularity of documents, requiring specific document segmentation techniques. Our framework that is language independent was evaluated on corpora in French and English, including meetings and scientific presentations. The satisfactory evaluation results obtained at several stages show the importance of our approach in bridging the gap between meeting documents, independently from the language and domain. They highlight also the utility of the multimodal alignment in advanced applications, e.g. multimedia document browsing, content-based / temporal-based searching, etc.</div></front></TEI><affiliations><list><country><li>Royaume-Uni</li><li>Suisse</li></country><region><li>Canton de Fribourg</li></region><settlement><li>Fribourg</li></settlement><orgName><li>Université de Fribourg</li></orgName></list><tree><country name="Royaume-Uni"><noRegion><name sortKey="Mekhaldi, Dalila" sort="Mekhaldi, Dalila" uniqKey="Mekhaldi D" first="Dalila" last="Mekhaldi">Dalila Mekhaldi</name></noRegion></country><country name="Suisse"><region name="Canton de Fribourg"><name sortKey="Lalanne, Denis" sort="Lalanne, Denis" uniqKey="Lalanne D" first="Denis" last="Lalanne">Denis Lalanne</name></region><name sortKey="Ingold, Rolf" sort="Ingold, Rolf" uniqKey="Ingold R" first="Rolf" last="Ingold">Rolf Ingold</name><name sortKey="Ingold, Rolf" sort="Ingold, Rolf" uniqKey="Ingold R" first="Rolf" last="Ingold">Rolf Ingold</name><name sortKey="Lalanne, Denis" sort="Lalanne, Denis" uniqKey="Lalanne D" first="Denis" last="Lalanne">Denis Lalanne</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Istex/Checkpoint
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000678 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Checkpoint/biblio.hfd -nk 000678 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Istex
|étape= Checkpoint
|type= RBID
|clé= ISTEX:2AC75FC89E722D405FE84188DCDF855B37E84BC9
|texte= A multimodal alignment framework for spoken documents
}}
| This area was generated with Dilib version V0.6.33. |  |