@inproceedings{williams-power-2010-fact,
title = "A Fact-aligned Corpus of Numerical Expressions",
author = "Williams, Sandra and
Power, Richard",
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/185_Paper.pdf",
abstract = "We describe a corpus of numerical expressions, developed as part of the NUMGEN project. The corpus contains newspaper articles and scientific papers in which exactly the same numerical facts are presented many times (both within and across texts). Some annotations of numerical facts are original: for example, numbers are automatically classified as round or non-round by an algorithm derived from Jansen and Pollmann (2001); also, numerical hedges such as about or a little under are marked up and classified semantically using arithmetical relations. Through explicit alignment of phrases describing the same fact, the corpus can support research on the influence of various contextual factors (e.g., document position, intended readership) on the way in which numerical facts are expressed. As an example we present results from an investigation showing that when a fact is mentioned more than once in a text, there is a clear tendency for precision to increase from first to subsequent mentions, and for mathematical level either to remain constant or to increase.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="williams-power-2010-fact">
<titleInfo>
<title>A Fact-aligned Corpus of Numerical Expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Power</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>We describe a corpus of numerical expressions, developed as part of the NUMGEN project. The corpus contains newspaper articles and scientific papers in which exactly the same numerical facts are presented many times (both within and across texts). Some annotations of numerical facts are original: for example, numbers are automatically classified as round or non-round by an algorithm derived from Jansen and Pollmann (2001); also, numerical hedges such as about or a little under are marked up and classified semantically using arithmetical relations. Through explicit alignment of phrases describing the same fact, the corpus can support research on the influence of various contextual factors (e.g., document position, intended readership) on the way in which numerical facts are expressed. As an example we present results from an investigation showing that when a fact is mentioned more than once in a text, there is a clear tendency for precision to increase from first to subsequent mentions, and for mathematical level either to remain constant or to increase.</abstract>
<identifier type="citekey">williams-power-2010-fact</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/185_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Fact-aligned Corpus of Numerical Expressions
%A Williams, Sandra
%A Power, Richard
%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 williams-power-2010-fact
%X We describe a corpus of numerical expressions, developed as part of the NUMGEN project. The corpus contains newspaper articles and scientific papers in which exactly the same numerical facts are presented many times (both within and across texts). Some annotations of numerical facts are original: for example, numbers are automatically classified as round or non-round by an algorithm derived from Jansen and Pollmann (2001); also, numerical hedges such as about or a little under are marked up and classified semantically using arithmetical relations. Through explicit alignment of phrases describing the same fact, the corpus can support research on the influence of various contextual factors (e.g., document position, intended readership) on the way in which numerical facts are expressed. As an example we present results from an investigation showing that when a fact is mentioned more than once in a text, there is a clear tendency for precision to increase from first to subsequent mentions, and for mathematical level either to remain constant or to increase.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/185_Paper.pdf
Markdown (Informal)
[A Fact-aligned Corpus of Numerical Expressions](http://www.lrec-conf.org/proceedings/lrec2010/pdf/185_Paper.pdf) (Williams & Power, LREC 2010)
ACL
- Sandra Williams and Richard Power. 2010. A Fact-aligned Corpus of Numerical Expressions. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).