@inproceedings{santini-2005-clustering,
title = "Clustering Web Pages to Identify Emerging Textual Patterns",
author = "Santini, Marina",
editor = "Hernandez, Nicolas and
Pitel, Guillaume",
booktitle = "Actes de la 12{\`e}me conf{\'e}rence sur le Traitement Automatique des Langues Naturelles. REncontres jeunes Chercheurs en Informatique pour le Traitement Automatique des Langues (articles courts)",
month = jun,
year = "2005",
address = "Dourdan, France",
publisher = "ATALA",
url = "https://aclanthology.org/2005.jeptalnrecital-recitalcourt.12",
pages = "703--708",
abstract = "The Web has triggered many adjustments in many fields. It also has had a strong impact on the genre repertoire. Novel genres have already emerged, e.g. blog and FAQs. Presumably, other new genres are still in formation, because the Web is still fluid and in constant change. In this paper we present an experiment that explores the possibility of automatically detecting the emerging textual patterns that are slowly taking shape on the Web. Emerging textual patterns can develop into novel Web genres or novel text types in the near future. The experimental set up includes a collection of unclassified web pages, two sets of features and the use of cluster analysis. Results are encouraging and deserve further investigation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="santini-2005-clustering">
<titleInfo>
<title>Clustering Web Pages to Identify Emerging Textual Patterns</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Santini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2005-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Actes de la 12ème conférence sur le Traitement Automatique des Langues Naturelles. REncontres jeunes Chercheurs en Informatique pour le Traitement Automatique des Langues (articles courts)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Pitel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ATALA</publisher>
<place>
<placeTerm type="text">Dourdan, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Web has triggered many adjustments in many fields. It also has had a strong impact on the genre repertoire. Novel genres have already emerged, e.g. blog and FAQs. Presumably, other new genres are still in formation, because the Web is still fluid and in constant change. In this paper we present an experiment that explores the possibility of automatically detecting the emerging textual patterns that are slowly taking shape on the Web. Emerging textual patterns can develop into novel Web genres or novel text types in the near future. The experimental set up includes a collection of unclassified web pages, two sets of features and the use of cluster analysis. Results are encouraging and deserve further investigation.</abstract>
<identifier type="citekey">santini-2005-clustering</identifier>
<location>
<url>https://aclanthology.org/2005.jeptalnrecital-recitalcourt.12</url>
</location>
<part>
<date>2005-06</date>
<extent unit="page">
<start>703</start>
<end>708</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clustering Web Pages to Identify Emerging Textual Patterns
%A Santini, Marina
%Y Hernandez, Nicolas
%Y Pitel, Guillaume
%S Actes de la 12ème conférence sur le Traitement Automatique des Langues Naturelles. REncontres jeunes Chercheurs en Informatique pour le Traitement Automatique des Langues (articles courts)
%D 2005
%8 June
%I ATALA
%C Dourdan, France
%F santini-2005-clustering
%X The Web has triggered many adjustments in many fields. It also has had a strong impact on the genre repertoire. Novel genres have already emerged, e.g. blog and FAQs. Presumably, other new genres are still in formation, because the Web is still fluid and in constant change. In this paper we present an experiment that explores the possibility of automatically detecting the emerging textual patterns that are slowly taking shape on the Web. Emerging textual patterns can develop into novel Web genres or novel text types in the near future. The experimental set up includes a collection of unclassified web pages, two sets of features and the use of cluster analysis. Results are encouraging and deserve further investigation.
%U https://aclanthology.org/2005.jeptalnrecital-recitalcourt.12
%P 703-708
Markdown (Informal)
[Clustering Web Pages to Identify Emerging Textual Patterns](https://aclanthology.org/2005.jeptalnrecital-recitalcourt.12) (Santini, JEP/TALN/RECITAL 2005)
ACL
- Marina Santini. 2005. Clustering Web Pages to Identify Emerging Textual Patterns. In Actes de la 12ème conférence sur le Traitement Automatique des Langues Naturelles. REncontres jeunes Chercheurs en Informatique pour le Traitement Automatique des Langues (articles courts), pages 703–708, Dourdan, France. ATALA.