@inproceedings{falco-etal-2012-kitten,
title = "{K}itten: a tool for normalizing {HTML} and extracting its textual content",
author = "Falco, Mathieu-Henri and
Moriceau, V{\'e}ronique and
Vilnat, Anne",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/467_Paper.pdf",
pages = "2261--2267",
abstract = "The web is composed of a gigantic amount of documents that can be very useful for information extraction systems. Most of them are written in HTML and have to be rendered by an HTML engine in order to display the data they contain on a screen. HTML file thus mix both informational and rendering content. Our goal is to design a tool for informational content extraction. A linear extraction with only a basic filtering of rendering content would not be enough as objects such as lists and tables are linearly coded but need to be read in a non-linear way to be well interpreted. Besides these HTML pages are often incorrectly coded from an HTML point of view and use a segmentation of blocks based on blank space that cannot be transposed in a text filewithout confusing syntactic parsers. For this purpose, we propose the Kitten tool that first normalizes HTML file into unicode XHTML file, then extracts the informational content into a text filewith a special processing for sentences, lists and tables.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="falco-etal-2012-kitten">
<titleInfo>
<title>Kitten: a tool for normalizing HTML and extracting its textual content</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mathieu-Henri</namePart>
<namePart type="family">Falco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Véronique</namePart>
<namePart type="family">Moriceau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Vilnat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The web is composed of a gigantic amount of documents that can be very useful for information extraction systems. Most of them are written in HTML and have to be rendered by an HTML engine in order to display the data they contain on a screen. HTML file thus mix both informational and rendering content. Our goal is to design a tool for informational content extraction. A linear extraction with only a basic filtering of rendering content would not be enough as objects such as lists and tables are linearly coded but need to be read in a non-linear way to be well interpreted. Besides these HTML pages are often incorrectly coded from an HTML point of view and use a segmentation of blocks based on blank space that cannot be transposed in a text filewithout confusing syntactic parsers. For this purpose, we propose the Kitten tool that first normalizes HTML file into unicode XHTML file, then extracts the informational content into a text filewith a special processing for sentences, lists and tables.</abstract>
<identifier type="citekey">falco-etal-2012-kitten</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/467_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2261</start>
<end>2267</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Kitten: a tool for normalizing HTML and extracting its textual content
%A Falco, Mathieu-Henri
%A Moriceau, Véronique
%A Vilnat, Anne
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F falco-etal-2012-kitten
%X The web is composed of a gigantic amount of documents that can be very useful for information extraction systems. Most of them are written in HTML and have to be rendered by an HTML engine in order to display the data they contain on a screen. HTML file thus mix both informational and rendering content. Our goal is to design a tool for informational content extraction. A linear extraction with only a basic filtering of rendering content would not be enough as objects such as lists and tables are linearly coded but need to be read in a non-linear way to be well interpreted. Besides these HTML pages are often incorrectly coded from an HTML point of view and use a segmentation of blocks based on blank space that cannot be transposed in a text filewithout confusing syntactic parsers. For this purpose, we propose the Kitten tool that first normalizes HTML file into unicode XHTML file, then extracts the informational content into a text filewith a special processing for sentences, lists and tables.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/467_Paper.pdf
%P 2261-2267
Markdown (Informal)
[Kitten: a tool for normalizing HTML and extracting its textual content](http://www.lrec-conf.org/proceedings/lrec2012/pdf/467_Paper.pdf) (Falco et al., LREC 2012)
ACL