Integrating text formatting and text generation
Identifieur interne : 000455 ( Main/Exploration ); précédent : 000454; suivant : 000456Integrating text formatting and text generation
Auteurs : Elsa Pascual [France]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 1996.
Abstract
Abstract: This paper presents a model for representing the architecture of documents for natural language generation. Document architecture is an abstract notion, perceptible through the formatting treatments applied to structural elements in a text: titles, organization of the text into chapters or sections, paragraphs, formulations such as theorems, definitions, introductions, etc. It can be seen as the visual structure of a text. The model of document architecture representation is constructed from a specialized sublanguage (in the sense of Z. Harris) of natural language. The sublanguage, a metalanguage for text architecture, is tailored to text production. We extracted about thirty classes of metasentences of this metalanguage, covering nearly the full scope of text architectural phenomena that appear in scientific and technical documents. A specific text is represented by a metadiscourse which is a list of instantiated metasentences, observing properties that ensure the coherence of the metadiscourse. This model has multiple applications: it can be used by systems of text manipulation and transformation through architecture (analysis, generation, formatting, editing, etc.). In the last part of this paper, we propose a brief survey of a system of formatted text generation, based on this model.
Url:
DOI: 10.1007/3-540-60800-1_31
Affiliations:
- France
- Midi-Pyrénées, Occitanie (région administrative)
- Toulouse
- Université Toulouse III - Paul Sabatier
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000422
- to stream Istex, to step Curation: 000422
- to stream Istex, to step Checkpoint: 000374
- to stream Main, to step Merge: 000486
- to stream Main, to step Curation: 000455
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Integrating text formatting and text generation</title>
<author><name sortKey="Pascual, Elsa" sort="Pascual, Elsa" uniqKey="Pascual E" first="Elsa" last="Pascual">Elsa Pascual</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:1AE0470F340EDF0B63B2CE43AB550BFFB1804981</idno>
<date when="1996" year="1996">1996</date>
<idno type="doi">10.1007/3-540-60800-1_31</idno>
<idno type="url">https://api.istex.fr/document/1AE0470F340EDF0B63B2CE43AB550BFFB1804981/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000422</idno>
<idno type="wicri:Area/Istex/Curation">000422</idno>
<idno type="wicri:Area/Istex/Checkpoint">000374</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000374</idno>
<idno type="wicri:doubleKey">0302-9743:1996:Pascual E:integrating:text:formatting</idno>
<idno type="wicri:Area/Main/Merge">000486</idno>
<idno type="wicri:Area/Main/Curation">000455</idno>
<idno type="wicri:Area/Main/Exploration">000455</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Integrating text formatting and text generation</title>
<author><name sortKey="Pascual, Elsa" sort="Pascual, Elsa" uniqKey="Pascual E" first="Elsa" last="Pascual">Elsa Pascual</name>
<affiliation wicri:level="4"><country xml:lang="fr">France</country>
<wicri:regionArea>IRIT/PRESCOT, Université Paul Sabatier, 118 route de Narbonne, 31 062, Toulouse Cedex</wicri:regionArea>
<orgName type="university">Université Toulouse III - Paul Sabatier</orgName>
<placeName><settlement type="city">Toulouse</settlement>
<region type="region" nuts="2">Occitanie (région administrative)</region>
<region type="old region" nuts="2">Midi-Pyrénées</region>
</placeName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">France</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<title level="s" type="sub">Lecture Notes in Artificial Intelligence</title>
<imprint><date>1996</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">1AE0470F340EDF0B63B2CE43AB550BFFB1804981</idno>
<idno type="DOI">10.1007/3-540-60800-1_31</idno>
<idno type="ChapterID">11</idno>
<idno type="ChapterID">Chap11</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 presents a model for representing the architecture of documents for natural language generation. Document architecture is an abstract notion, perceptible through the formatting treatments applied to structural elements in a text: titles, organization of the text into chapters or sections, paragraphs, formulations such as theorems, definitions, introductions, etc. It can be seen as the visual structure of a text. The model of document architecture representation is constructed from a specialized sublanguage (in the sense of Z. Harris) of natural language. The sublanguage, a metalanguage for text architecture, is tailored to text production. We extracted about thirty classes of metasentences of this metalanguage, covering nearly the full scope of text architectural phenomena that appear in scientific and technical documents. A specific text is represented by a metadiscourse which is a list of instantiated metasentences, observing properties that ensure the coherence of the metadiscourse. This model has multiple applications: it can be used by systems of text manipulation and transformation through architecture (analysis, generation, formatting, editing, etc.). In the last part of this paper, we propose a brief survey of a system of formatted text generation, based on this model.</div>
</front>
</TEI>
<affiliations><list><country><li>France</li>
</country>
<region><li>Midi-Pyrénées</li>
<li>Occitanie (région administrative)</li>
</region>
<settlement><li>Toulouse</li>
</settlement>
<orgName><li>Université Toulouse III - Paul Sabatier</li>
</orgName>
</list>
<tree><country name="France"><region name="Occitanie (région administrative)"><name sortKey="Pascual, Elsa" sort="Pascual, Elsa" uniqKey="Pascual E" first="Elsa" last="Pascual">Elsa Pascual</name>
</region>
<name sortKey="Pascual, Elsa" sort="Pascual, Elsa" uniqKey="Pascual E" first="Elsa" last="Pascual">Elsa Pascual</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Ticri/explor/TeiVM2/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000455 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000455 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Ticri |area= TeiVM2 |flux= Main |étape= Exploration |type= RBID |clé= ISTEX:1AE0470F340EDF0B63B2CE43AB550BFFB1804981 |texte= Integrating text formatting and text generation }}
This area was generated with Dilib version V0.6.31. |