@inproceedings{weiser-watrin-2012-extraction,
title = "Extraction of unmarked quotations in Newspapers",
author = "Weiser, St{\'e}phanie and
Watrin, Patrick",
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/566_Paper.pdf",
pages = "559--562",
abstract = "This paper presents work in progress to automatically extract quotation sentences from newspaper articles. The focus is the extraction and annotation of unmarked quotation sentences. A linguistic study shows that unmarked quotation sentences can be formalised into 16 patterns that can be used to develop an extraction grammar. The question of unmarked quotation boundaries identification is also raised as they are often ambiguous. An annotation scheme allowing to describe all the elements that can take place in a quotation sentence is defined. This paper presents the creation of two resources necessary to our system. A dictionary of verbs introducing quotations has been automatically built using a grammar of marked quotations sentences to identify the verbs able to introduce quotations. A grammar formalising the patterns of unmarked quotation sentences ― using the tool Unitex, based on finite state machines ― has been developed. A short experiment has been performed on two patterns and shows some promising results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weiser-watrin-2012-extraction">
<titleInfo>
<title>Extraction of unmarked quotations in Newspapers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stéphanie</namePart>
<namePart type="family">Weiser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Watrin</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>This paper presents work in progress to automatically extract quotation sentences from newspaper articles. The focus is the extraction and annotation of unmarked quotation sentences. A linguistic study shows that unmarked quotation sentences can be formalised into 16 patterns that can be used to develop an extraction grammar. The question of unmarked quotation boundaries identification is also raised as they are often ambiguous. An annotation scheme allowing to describe all the elements that can take place in a quotation sentence is defined. This paper presents the creation of two resources necessary to our system. A dictionary of verbs introducing quotations has been automatically built using a grammar of marked quotations sentences to identify the verbs able to introduce quotations. A grammar formalising the patterns of unmarked quotation sentences ― using the tool Unitex, based on finite state machines ― has been developed. A short experiment has been performed on two patterns and shows some promising results.</abstract>
<identifier type="citekey">weiser-watrin-2012-extraction</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/566_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>559</start>
<end>562</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extraction of unmarked quotations in Newspapers
%A Weiser, Stéphanie
%A Watrin, Patrick
%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 weiser-watrin-2012-extraction
%X This paper presents work in progress to automatically extract quotation sentences from newspaper articles. The focus is the extraction and annotation of unmarked quotation sentences. A linguistic study shows that unmarked quotation sentences can be formalised into 16 patterns that can be used to develop an extraction grammar. The question of unmarked quotation boundaries identification is also raised as they are often ambiguous. An annotation scheme allowing to describe all the elements that can take place in a quotation sentence is defined. This paper presents the creation of two resources necessary to our system. A dictionary of verbs introducing quotations has been automatically built using a grammar of marked quotations sentences to identify the verbs able to introduce quotations. A grammar formalising the patterns of unmarked quotation sentences ― using the tool Unitex, based on finite state machines ― has been developed. A short experiment has been performed on two patterns and shows some promising results.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/566_Paper.pdf
%P 559-562
Markdown (Informal)
[Extraction of unmarked quotations in Newspapers](http://www.lrec-conf.org/proceedings/lrec2012/pdf/566_Paper.pdf) (Weiser & Watrin, LREC 2012)
ACL
- Stéphanie Weiser and Patrick Watrin. 2012. Extraction of unmarked quotations in Newspapers. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 559–562, Istanbul, Turkey. European Language Resources Association (ELRA).