@inproceedings{sassolini-cinini-2010-cultural,
title = "Cultural Heritage: Knowledge Extraction from Web Documents",
author = "Sassolini, Eva and
Cinini, Alessandra",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/415_Paper.pdf",
abstract = "This article presents the use of NLP techniques (text mining, text analysis) to develop specific tools that allow to create linguistic resources related to the cultural heritage domain. The aim of our approach is to create tools for the building of an online knowledge network, automatically extracted from text materials concerning this domain. A particular methodology was experimented by dividing the automatic acquisition of texts, and consequently, the creation of reference corpus in two phases. In the first phase, on-line documents have been extracted from lists of links provided by human experts. All documents extracted from the web by means of automatic spider have been stored in a repository of text materials. On the basis of these documents, automatic parsers create the reference corpus for the cultural heritage domain. Relevant information and semantic concepts are then extracted from this corpus. In a second phase, all these semantically relevant elements (such as proper names, names of institutions, names of places, and other relevant terms) have been used as basis for a new search strategy of text materials from heterogeneous sources. In this case also specialized crawlers (TP-crawler) have been used to work on a bulk of text materials available on line.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sassolini-cinini-2010-cultural">
<titleInfo>
<title>Cultural Heritage: Knowledge Extraction from Web Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Sassolini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandra</namePart>
<namePart type="family">Cinini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article presents the use of NLP techniques (text mining, text analysis) to develop specific tools that allow to create linguistic resources related to the cultural heritage domain. The aim of our approach is to create tools for the building of an online knowledge network, automatically extracted from text materials concerning this domain. A particular methodology was experimented by dividing the automatic acquisition of texts, and consequently, the creation of reference corpus in two phases. In the first phase, on-line documents have been extracted from lists of links provided by human experts. All documents extracted from the web by means of automatic spider have been stored in a repository of text materials. On the basis of these documents, automatic parsers create the reference corpus for the cultural heritage domain. Relevant information and semantic concepts are then extracted from this corpus. In a second phase, all these semantically relevant elements (such as proper names, names of institutions, names of places, and other relevant terms) have been used as basis for a new search strategy of text materials from heterogeneous sources. In this case also specialized crawlers (TP-crawler) have been used to work on a bulk of text materials available on line.</abstract>
<identifier type="citekey">sassolini-cinini-2010-cultural</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/415_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cultural Heritage: Knowledge Extraction from Web Documents
%A Sassolini, Eva
%A Cinini, Alessandra
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F sassolini-cinini-2010-cultural
%X This article presents the use of NLP techniques (text mining, text analysis) to develop specific tools that allow to create linguistic resources related to the cultural heritage domain. The aim of our approach is to create tools for the building of an online knowledge network, automatically extracted from text materials concerning this domain. A particular methodology was experimented by dividing the automatic acquisition of texts, and consequently, the creation of reference corpus in two phases. In the first phase, on-line documents have been extracted from lists of links provided by human experts. All documents extracted from the web by means of automatic spider have been stored in a repository of text materials. On the basis of these documents, automatic parsers create the reference corpus for the cultural heritage domain. Relevant information and semantic concepts are then extracted from this corpus. In a second phase, all these semantically relevant elements (such as proper names, names of institutions, names of places, and other relevant terms) have been used as basis for a new search strategy of text materials from heterogeneous sources. In this case also specialized crawlers (TP-crawler) have been used to work on a bulk of text materials available on line.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/415_Paper.pdf
Markdown (Informal)
[Cultural Heritage: Knowledge Extraction from Web Documents](http://www.lrec-conf.org/proceedings/lrec2010/pdf/415_Paper.pdf) (Sassolini & Cinini, LREC 2010)
ACL