Information Retrieval Strategies for Digitized Handwritten Medieval Documents
Identifieur interne : 000467 ( Main/Exploration ); précédent : 000466; suivant : 000468Information Retrieval Strategies for Digitized Handwritten Medieval Documents
Auteurs : Nada Naji [Suisse] ; Jacques Savoy [Suisse]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2011.
Abstract
Abstract: This paper describes and evaluates different IR models and search strategies for digitized manuscripts. Written during the thirteenth century, these manuscripts were digitized using an imperfect recognition system with a word error rate of around 6%. Having access to the internal representation during the recognition stage, we were able to produce four automatic transcriptions, each introducing some form of spelling correction as an attempt to improve the retrieval effectiveness. We evaluated the retrieval effectiveness for each of these versions using three text representations combined with five IR models, three stemming strategies and two query formulations. We employed a manually-transcribed error-free version to define the ground-truth. Based on our experiments, we conclude that taking account of the single best recognition word or all possible top-k recognition alternatives does not provide the best performance. Selecting all possible words each having a log-likelihood close to the best alternative yields the best text surrogate. Within this representation, different retrieval strategies tend to produce similar performance levels.
Url:
DOI: 10.1007/978-3-642-25631-8_10
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000257
- to stream Istex, to step Curation: 000253
- to stream Istex, to step Checkpoint: 000124
- to stream Main, to step Merge: 000473
- to stream Main, to step Curation: 000467
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Information Retrieval Strategies for Digitized Handwritten Medieval Documents</title><author><name sortKey="Naji, Nada" sort="Naji, Nada" uniqKey="Naji N" first="Nada" last="Naji">Nada Naji</name></author><author><name sortKey="Savoy, Jacques" sort="Savoy, Jacques" uniqKey="Savoy J" first="Jacques" last="Savoy">Jacques Savoy</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:C91D592F774C00982EE4EC0D095E758DDCDE70F5</idno><date when="2011" year="2011">2011</date><idno type="doi">10.1007/978-3-642-25631-8_10</idno><idno type="url">https://api.istex.fr/document/C91D592F774C00982EE4EC0D095E758DDCDE70F5/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000257</idno><idno type="wicri:Area/Istex/Curation">000253</idno><idno type="wicri:Area/Istex/Checkpoint">000124</idno><idno type="wicri:doubleKey">0302-9743:2011:Naji N:information:retrieval:strategies</idno><idno type="wicri:Area/Main/Merge">000473</idno><idno type="wicri:Area/Main/Curation">000467</idno><idno type="wicri:Area/Main/Exploration">000467</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Information Retrieval Strategies for Digitized Handwritten Medieval Documents</title><author><name sortKey="Naji, Nada" sort="Naji, Nada" uniqKey="Naji N" first="Nada" last="Naji">Nada Naji</name><affiliation wicri:level="1"><country xml:lang="fr">Suisse</country><wicri:regionArea>Computer Science Department, University of Neuchatel, Rue Emile-Argand 11, 2000, Neuchatel</wicri:regionArea><wicri:noRegion>Neuchatel</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Suisse</country></affiliation></author><author><name sortKey="Savoy, Jacques" sort="Savoy, Jacques" uniqKey="Savoy J" first="Jacques" last="Savoy">Jacques Savoy</name><affiliation wicri:level="1"><country xml:lang="fr">Suisse</country><wicri:regionArea>Computer Science Department, University of Neuchatel, Rue Emile-Argand 11, 2000, Neuchatel</wicri:regionArea><wicri:noRegion>Neuchatel</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Suisse</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2011</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">C91D592F774C00982EE4EC0D095E758DDCDE70F5</idno><idno type="DOI">10.1007/978-3-642-25631-8_10</idno><idno type="ChapterID">10</idno><idno type="ChapterID">Chap10</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: This paper describes and evaluates different IR models and search strategies for digitized manuscripts. Written during the thirteenth century, these manuscripts were digitized using an imperfect recognition system with a word error rate of around 6%. Having access to the internal representation during the recognition stage, we were able to produce four automatic transcriptions, each introducing some form of spelling correction as an attempt to improve the retrieval effectiveness. We evaluated the retrieval effectiveness for each of these versions using three text representations combined with five IR models, three stemming strategies and two query formulations. We employed a manually-transcribed error-free version to define the ground-truth. Based on our experiments, we conclude that taking account of the single best recognition word or all possible top-k recognition alternatives does not provide the best performance. Selecting all possible words each having a log-likelihood close to the best alternative yields the best text surrogate. Within this representation, different retrieval strategies tend to produce similar performance levels.</div></front></TEI><affiliations><list><country><li>Suisse</li></country></list><tree><country name="Suisse"><noRegion><name sortKey="Naji, Nada" sort="Naji, Nada" uniqKey="Naji N" first="Nada" last="Naji">Nada Naji</name></noRegion><name sortKey="Naji, Nada" sort="Naji, Nada" uniqKey="Naji N" first="Nada" last="Naji">Nada Naji</name><name sortKey="Savoy, Jacques" sort="Savoy, Jacques" uniqKey="Savoy J" first="Jacques" last="Savoy">Jacques Savoy</name><name sortKey="Savoy, Jacques" sort="Savoy, Jacques" uniqKey="Savoy J" first="Jacques" last="Savoy">Jacques Savoy</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000467 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000467 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:C91D592F774C00982EE4EC0D095E758DDCDE70F5
|texte= Information Retrieval Strategies for Digitized Handwritten Medieval Documents
}}
| This area was generated with Dilib version V0.6.32. |  |