Aligning Portuguese and Chinese Parallel Texts Using Confidence Bands
Identifieur interne : 001C41 ( Main/Exploration ); précédent : 001C40; suivant : 001C42Aligning Portuguese and Chinese Parallel Texts Using Confidence Bands
Auteurs : Ant Nio Ribeiro [Portugal] ; Gabriel Lopes [Portugal] ; João Mexia [Portugal]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2000.
Abstract
Abstract: This paper describes a language independent method that makes use of tokens which are homograph for a pair of languages, in order to align parallel texts. We will show that even for such different languages as Portuguese and Chinese it is possible to use homographs with great reliability. This work was originally inspired and extends work done by Pascale Fung & Kathleen McKeown, and Melamed. In order to filter out words that may cause misalignment, we use confidence bands of linear regression lines instead of statistically unsupported heuristics. This is a completely statistically supported alignment algorithm.
Url:
DOI: 10.1007/3-540-44533-1_63
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 003436
- to stream Istex, to step Curation: 003181
- to stream Istex, to step Checkpoint: 001243
- to stream Main, to step Merge: 001D40
- to stream Main, to step Curation: 001C41
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct:series"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Aligning Portuguese and Chinese Parallel Texts Using Confidence Bands</title>
<author><name sortKey="Ribeiro, Ant Nio" sort="Ribeiro, Ant Nio" uniqKey="Ribeiro A" first="Ant Nio" last="Ribeiro">Ant Nio Ribeiro</name>
</author>
<author><name sortKey="Lopes, Gabriel" sort="Lopes, Gabriel" uniqKey="Lopes G" first="Gabriel" last="Lopes">Gabriel Lopes</name>
</author>
<author><name sortKey="Mexia, Joao" sort="Mexia, Joao" uniqKey="Mexia J" first="João" last="Mexia">João Mexia</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:51282AE0623B0209933DF5B2A25D67A08BB2A84C</idno>
<date when="2000" year="2000">2000</date>
<idno type="doi">10.1007/3-540-44533-1_63</idno>
<idno type="url">https://api.istex.fr/document/51282AE0623B0209933DF5B2A25D67A08BB2A84C/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">003436</idno>
<idno type="wicri:Area/Istex/Curation">003181</idno>
<idno type="wicri:Area/Istex/Checkpoint">001243</idno>
<idno type="wicri:doubleKey">0302-9743:2000:Ribeiro A:aligning:portuguese:and</idno>
<idno type="wicri:Area/Main/Merge">001D40</idno>
<idno type="wicri:Area/Main/Curation">001C41</idno>
<idno type="wicri:Area/Main/Exploration">001C41</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Aligning Portuguese and Chinese Parallel Texts Using Confidence Bands</title>
<author><name sortKey="Ribeiro, Ant Nio" sort="Ribeiro, Ant Nio" uniqKey="Ribeiro A" first="Ant Nio" last="Ribeiro">Ant Nio Ribeiro</name>
<affiliation wicri:level="1"><country xml:lang="fr">Portugal</country>
<wicri:regionArea>Faculdade de Ciências e Tecnologia, Departamento de Informática, Universidade Nova de Lisboa, Quinta da Torre, P-2825-114, Monte da Caparica</wicri:regionArea>
<wicri:noRegion>Monte da Caparica</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Portugal</country>
</affiliation>
</author>
<author><name sortKey="Lopes, Gabriel" sort="Lopes, Gabriel" uniqKey="Lopes G" first="Gabriel" last="Lopes">Gabriel Lopes</name>
<affiliation wicri:level="1"><country xml:lang="fr">Portugal</country>
<wicri:regionArea>Faculdade de Ciências e Tecnologia, Departamento de Informática, Universidade Nova de Lisboa, Quinta da Torre, P-2825-114, Monte da Caparica</wicri:regionArea>
<wicri:noRegion>Monte da Caparica</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Mexia, Joao" sort="Mexia, Joao" uniqKey="Mexia J" first="João" last="Mexia">João Mexia</name>
<affiliation wicri:level="1"><country xml:lang="fr">Portugal</country>
<wicri:regionArea>Faculdade de Ciências e Tecnologia, Departamento de Informática, Universidade Nova de Lisboa, Quinta da Torre, P-2825-114, Monte da Caparica</wicri:regionArea>
<wicri:noRegion>Monte da Caparica</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Portugal</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2000</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">51282AE0623B0209933DF5B2A25D67A08BB2A84C</idno>
<idno type="DOI">10.1007/3-540-44533-1_63</idno>
<idno type="ChapterID">63</idno>
<idno type="ChapterID">Chap63</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 a language independent method that makes use of tokens which are homograph for a pair of languages, in order to align parallel texts. We will show that even for such different languages as Portuguese and Chinese it is possible to use homographs with great reliability. This work was originally inspired and extends work done by Pascale Fung & Kathleen McKeown, and Melamed. In order to filter out words that may cause misalignment, we use confidence bands of linear regression lines instead of statistically unsupported heuristics. This is a completely statistically supported alignment algorithm.</div>
</front>
</TEI>
<affiliations><list><country><li>Portugal</li>
</country>
</list>
<tree><country name="Portugal"><noRegion><name sortKey="Ribeiro, Ant Nio" sort="Ribeiro, Ant Nio" uniqKey="Ribeiro A" first="Ant Nio" last="Ribeiro">Ant Nio Ribeiro</name>
</noRegion>
<name sortKey="Lopes, Gabriel" sort="Lopes, Gabriel" uniqKey="Lopes G" first="Gabriel" last="Lopes">Gabriel Lopes</name>
<name sortKey="Mexia, Joao" sort="Mexia, Joao" uniqKey="Mexia J" first="João" last="Mexia">João Mexia</name>
<name sortKey="Mexia, Joao" sort="Mexia, Joao" uniqKey="Mexia J" first="João" last="Mexia">João Mexia</name>
<name sortKey="Ribeiro, Ant Nio" sort="Ribeiro, Ant Nio" uniqKey="Ribeiro A" first="Ant Nio" last="Ribeiro">Ant Nio Ribeiro</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 001C41 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001C41 | 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:51282AE0623B0209933DF5B2A25D67A08BB2A84C |texte= Aligning Portuguese and Chinese Parallel Texts Using Confidence Bands }}
This area was generated with Dilib version V0.6.32. |